@deftai/directive-content 0.105.0 → 0.107.0

package/packs/skills/skills-pack-0.1.json

@@ -29,7 +29,7 @@
       ],
       "path": "skills/deft-directive-build/SKILL.md",
       "version": "0.1",
-      "body": "# Deft Directive Build\n\nImplements a project from its scope xBRIEFs following Deft Directive standards.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n## When to Use\n\n- After `deft-directive-setup` completes and generates `PROJECT-DEFINITION.xbrief.json`\n- User says \"build this\", \"implement the spec\", or \"start building\"\n- Resuming a partially-built project that has story xBRIEFs in `xbrief/active/`\n\n## Ordered-plan / cohort exhaustion (#2402)\n\n## Multi-scope turn/cache budget (epic #3009)\n\nMulti-scope greenfield (app-bank pins, N story scopes) multiplies agent turns when ceremony, promote, check, and render are re-run per scope. Apply the following after offline seed.\n\n### Offline seed vs implement phase (#3010)\n\n! Distinguish **offline seed** (operator or harness already ran `directive init` / deposit, pin-copied scopes into `xbrief/proposed/`, and recorded session ritual) from the **agent implement phase**.\n\n! When seed + session ritual are already complete for the engagement:\n- ⊗ Run `directive init` again\n- ⊗ Run full cold `session:start` unless hooks deny writes and recovery is required\n- ⊗ Run `directive migrate` or re-copy scopes already present\n- ! Prefer recovery via `session:ready` (or re-arm) when PreToolUse denies — not full re-init\n- ! Documented consumer/harness contract: seed is done once; implement agents only activate+implement\n\n### Batch promote; one active implement (#3011)\n\n! For a multi-scope pin, batch-stage scopes with `task scope:promote -- --batch` (all `proposed/`) or `task scope:promote -- --batch <path>…`.\n! Implement path remains **one** `scope:activate` + implement at a time — no multi-active write fence.\n! When pin order is known, do **not** re-list the entire lifecycle tree every scope; walk the known ordered list.\n⊗ Activate all scopes at once or drop the one-active-scope / story-ready stack.\n\n### Quality check once at end of multi-scope batch (#3012)\n\n! On an approved multi-scope batch (operator-approved multi-story branch, swarm cohort, or pin walk): run full `task check` (merge chokepoint) **once at the end of the batch** (or after the last scope), not after every scope.\n! Exception: if the last full check **failed**, fix loops MAY re-run check until green.\n! Pre-PR / merge-ready gates remain end-of-unit — this does not weaken them.\n! Iteration lane (affected tests / `verify:forward-coverage` / `coverage:hotspots`) still applies **per scope** during implementation (#1704).\n⊗ Spam full `directive check` / `task check` after every scope when the batch is still mid-flight and the last merge-chokepoint check was green.\n\n### One-shot project:render (#3013)\n\n! Greenfield init seeds a minimal render-ready `PROJECT-DEFINITION`. Treat `task project:render` as a **refresh of items from lifecycle folders**, not multi-turn identity research.\n⊗ Invent project identity across many turns when seed already stamped the skeleton.\n\n\n! When processing an approved multi-story cohort or an active ordered-plan sequence, stop after the final approved entry. Do not promote or dispatch adjacent stories from queue intuition. Continuation language advances only within the approved order; skill-chaining is non-authorizing.\n\n## Step 0 -- Implementation Preflight (#810)\n\n- ! Before starting any new implementation story or switching from one story to another, MUST run `git status --short --branch`.\n- ! If the working tree is dirty, MUST stop and summarize the current branch, modified/untracked files, and whether the changes appear related to the target story. Ask the operator to choose one path: commit existing work, stash existing work, include existing work in the current story, or stop.\n- ⊗ Begin a new story while unrelated dirty work is present without explicit operator approval.\n- ! Resolve exactly one target story xBRIEF path by default. One story is the default implementation unit for this skill; if the user asks for a phase/epic, decompose or ask which story to start.\n- ! Batching multiple stories in one branch/PR requires explicit operator approval and a short rationale recorded in the handoff.\n- ! **Swarm-cohort dispatch carve-out**: when this skill is invoked as part of a swarm cohort allocated by `skills/deft-directive-swarm/SKILL.md`, the approved Phase 5 allocation plan satisfies the \"explicit operator approval and short rationale recorded in the handoff\" requirement above -- the dispatched xBRIEF paths and allocation rationale ARE the consent token. Process each assigned story sequentially under the checkpoint-commit + `task scope:complete` discipline below. Do NOT re-prompt the parent for batching approval mid-cohort -- the all-or-nothing dispatch envelope rule (`AGENTS.md` `## Multi-agent orchestration discipline (#954)`) forbids mid-scope user-approval gates.\n- ! **Structured consent-token recognition (#1378)**: the canonical recognition path for the carve-out above is the structured `## Allocation context` section of the dispatch envelope (the frozen schema in `templates/agent-prompt-preamble.md`, Story A of #1378). When that section reports `dispatch_kind: swarm-cohort` with a non-null `allocation_plan_id` AND a non-null `batching_rationale`, the consent token is satisfied mechanically -- read `cohort_vbriefs` as the authoritative file boundary and process each entry sequentially under the checkpoint-commit + `task scope:complete` discipline below, without re-prompting the parent for batching approval mid-cohort. When the `## Allocation context` section is ABSENT (pre-#1378 dispatches, solo-interactive sessions), fall back to the #1371 prose carve-out immediately above -- the prose carve-out remains the recognition path of record for un-elevated envelopes.\n- ! **Within a cohort, between stories**: the working tree MUST be clean after each story's checkpoint commit + `task scope:complete`. If `git status --short` shows uncommitted state between stories (e.g. a missed `task scope:complete` move, an unstaged file from the prior story), checkpoint-commit it and proceed -- do NOT pause to ask the operator. The dirty-tree \"ask the operator\" branch above applies only at the FIRST story-start of a fresh branch, where uncommitted operator work might legitimately exist.\n- ! If the target story is in `xbrief/proposed/`, run `task scope:promote -- <path>` first (or `task scope:promote -- --batch` for a multi-scope pin — #3011); if it is in `xbrief/pending/`, run `task scope:activate -- <path>`. After activation, update the path to the active-file location before preflight.\n- ! **Effort estimate gate (#1581):** before `task scope:activate` / `task vbrief:activate`, scan `plan.items` (including nested `items` / `subItems`) for `effort`. Time anchors: `S` <2h, `M` half-day (2-4h), `L` 1-2 days, `XL` needs breakdown. The activate path fails closed while any item still has `effort: \"XL\"` — break XL work into S/M/L items (or re-estimate) first. Omitted `effort` remains valid (field is optional). Plan-item effort is **post-planning** authority (confirms/corrects intake estimates); it is **not** session-start ritual input — ceremony depth (#3214) uses two-stage rapid→escalate, not a required plan-item read at cold start. Headless: no operator confirm. Depth: `vbrief/vbrief.md` § Effort estimate.\n- ⊗ Activate a scope that still carries plan items with `effort: \"XL\"` — XL means \"not ready to start\" until broken down (#1581).\n- ⊗ Require plan-item `effort` to choose session-start ritual depth — estimates do not exist until after planning (#1581 / #3214).\n- ! Before any code-writing tool call -- the first scaffold edit, the first `task` invocation that mutates files, or any `start_agent` dispatch that will implement scope -- MUST run `task xbrief:preflight -- <active-story-path>` (the structural intent gate; wraps `scripts/preflight_implementation.py` so the same invocation works whether deft is the project root or installed as a `deft/` subdirectory).\n\nThe gate exits 0 only when the candidate xBRIEF lives in `xbrief/active/` AND `plan.status == \"running\"`. Any other state (pending/, proposed/, completed/, active/-with-non-running-status, malformed JSON, missing keys) exits 1 with an actionable redirect to `task xbrief:activate <path>`.\n\n- ! A non-zero exit MUST halt the skill. Surface the helper's stderr message verbatim to the user; do NOT proceed to USER.md Gate, File Reading, or any later phase.\n- ! Use canonical lifecycle tasks to satisfy this gate: `task scope:promote -- <path>` for proposed stories, `task scope:activate -- <path>` for pending stories, and the helper's idempotent companion `task xbrief:activate <path>` only when following the preflight redirect directly. Manual lifecycle moves bypass the activation contract -- use the task.\n- ⊗ Infer implementation intent from lifecycle vocabulary (\"do the full PR process\", \"start the work\", \"poller agents\"), branching language, or workflow shape. Workflow-shape vocabulary is NOT authorization to spawn an implementation agent (#810 surfacing event).\n- ⊗ Skip this preflight because the user said \"yes\", \"go\", or \"proceed\" -- affirmative continuation phrases are NOT implementation authorization unless the prior turn explicitly proposed implementation. When intent is ambiguous, ask one targeted question before invoking the gate.\n\n## Platform Detection\n\n! Before resolving any config paths, detect the host OS from your environment context:\n\n| Platform           | USER.md default path                                              |\n|--------------------|-------------------------------------------------------------------|\n| Windows            | `%APPDATA%\\deft\\USER.md` (e.g. `C:\\Users\\{user}\\AppData\\Roaming\\deft\\USER.md`) |\n| Unix (macOS/Linux) | `~/.config/deft/USER.md`                                          |\n\n- ! If `$DEFT_USER_PATH` is set, it takes precedence on any platform\n\n## Pre-Cutover Detection Guard\n\n! Before proceeding with any build step, detect whether the project uses the pre-v0.20 document model **or was generated by a strategy that emitted non-conformant v0.20 output shape** (the root cause of most \"build fails immediately after spec\" complaints in #1166). Redirect or block with the precise remediation.\n\n### Detection Criteria\n\nA project is **pre-cutover** if ANY of the following are true. This prose mirrors the executable helper in `scripts/_precutover.py`; when in doubt, the helper is canonical.\n\n1. `SPECIFICATION.md` exists and is neither a deprecation redirect nor a current generated spec export. A current generated spec export contains `<!-- Purpose: rendered specification -->` and `<!-- Source of truth: xbrief/specification.xbrief.json -->`, and `xbrief/specification.xbrief.json` plus all five lifecycle folders exist.\n2. `PROJECT.md` exists and contains neither the legacy `<!-- deft:deprecated-redirect -->` sentinel NOR the current `Purpose: deprecation redirect` canonical-banner marker (real content, not a deprecation redirect)\n3. `xbrief/specification.xbrief.json` exists but the lifecycle folders (`xbrief/proposed/`, `xbrief/pending/`, `xbrief/active/`, `xbrief/completed/`, `xbrief/cancelled/`) do NOT exist\n4. Strategy output shape violations (run `task verify-strategy-output` -- the canonical gate -- or the direct form `python .deft/core/scripts/validate_strategy_output.py --project-root <path>` after `deft` install):\n   - Any scope xBRIEF under `xbrief/proposed/` (or other lifecycle dirs) lacks the required `YYYY-MM-DD-` date prefix in its filename (e.g. bare `scaffold.xbrief.json`).\n   - `xbrief/PROJECT-DEFINITION.xbrief.json` is missing.\n   - `xbrief/specification.xbrief.json` exists as a legacy dual-write in a user-generated project. This is tolerated only for the framework source tree or a complete post-cutover full-spec consumer where all lifecycle folders exist and `SPECIFICATION.md` is rendered from `xbrief/specification.xbrief.json`.\n\n### Action on Detection\n\n! If pre-cutover or strategy-nonconformant state is detected, **stop immediately** and display an actionable message that cites the exact validator:\n\n> \"This project was generated with pre-v0.20 or non-conformant strategy output. Run the deterministic validator and follow its remediation: `task verify-strategy-output` (works in source and after `deft` package install) or `python .deft/core/scripts/validate_strategy_output.py --project-root .`. For document-model migration, follow UPGRADING.md § Frozen pre-v0.20 document-model migration (#2068): pin v0.59.0, then run `task migrate:vbrief` from that payload. Otherwise `task project:render` / strategy re-run as indicated.\"\n\n! Include specific details about what was detected (the validator output is authoritative):\n\n- Legacy specification.xbrief.json or missing lifecycle folders: \"Follow the frozen v0.59.0 migrator path (#2068) or run `task migrate:preflight` for current-release guidance\"\n- Non-date-prefixed xBRIEFs: \"Re-run the emitting strategy after the v0.20 migrations (#1166 s1+s2+...) or manually rename files to `YYYY-MM-DD-<slug>.xbrief.json` and `task scope:promote`\"\n- Missing `PROJECT-DEFINITION.xbrief.json`: \"Run `task project:render` to generate the project definition\"\n- `SPECIFICATION.md` / `PROJECT.md` without sentinel: the classic pre-cutover messages\n- Scope xBRIEF in wrong folder: \"Status is '{status}' but file is in {folder}/ -- run `task scope:activate <file>` to fix\"\n\n! After the validator reports clean, re-run this guard before continuing.\n\n⊗ Proceed with build when pre-cutover or strategy-nonconformant artifacts are detected -- always redirect to the frozen migration path first (or run the validator) and surface the exact remediation.\n⊗ Silently ignore these artifacts or guess at fixes -- the validator (wired into `task check` and this guard) is the deterministic gate.\n\n## USER.md Gate\n\n! Before proceeding, verify USER.md exists at the platform-appropriate path\n(resolved via Platform Detection above, or `$DEFT_USER_PATH` if set).\n\n- ! If USER.md is not found: inform the user and redirect to `deft-directive-setup`\n  Phase 1 before continuing -- do not proceed without user preferences\n- ! Once USER.md exists, continue with the Cost Phase Gate below\n\n### Forge-outage drop-back (#3422)\n\n! On attributed platform outage or repeated REST 429/502/503 during YOLO / through-merge implement: drop GitHub I/O, report once to the human in chat, and re-probe on `plan.policy.forgeOutageRetryMinutes` (default **30**; USER.md Personal wins; min 5; `task policy:show --field=forgeOutageRetryMinutes`). Local edit/test/commit MAY continue. Depth: [`scm/github.md`](../../scm/github.md) § #3180 / #3422. Complements #3167 / #3180.\n\n⊗ Tight retry, empty-commit thrash, or sending the human to github.com as the only remediation.\n\n## Cost Phase Gate (#739)\n\n! Before proceeding to File Reading, verify the project has gone through the\npre-build cost & budget transparency phase from `skills/deft-directive-cost/SKILL.md`.\nThis closes the adoption-blocker surfaced by issue #739 (refs #151 umbrella) where\nusers finished the spec flow and stopped at build because deft offered no cost\nsignal.\n\n### Detection\n\n- ! Check for `COST-ESTIMATE.md` in the project root.\n- ! Check that the file contains a recorded decision (the **Decision recorded**\n  block populated with one of: `build`, `rescope`, `no-build`, `skip`).\n- ! For `skip`, `rescope`, or `no-build` decisions: the **Reason** field MUST be\n  populated (one or two sentences in plain language). A skip with no reason\n  recorded is treated the same as no decision.\n\n### Action\n\n- ! If `COST-ESTIMATE.md` is missing OR the **Decision recorded** block is\n  unpopulated OR a `skip`/`rescope`/`no-build` decision has no reason recorded:\n  stop immediately and redirect the user:\n\n  > \"This project has not gone through the pre-build cost & budget transparency\n  > phase. Run `skills/deft-directive-cost/SKILL.md` to produce a plain-English\n  > `COST-ESTIMATE.md`, then re-run the build skill once the user has chosen\n  > build / rescope / no-build / skip(+reason).\"\n\n- ! On a `build` or `skip` decision: continue with File Reading below.\n- ! On a `rescope` decision: stop and redirect the user back to spec edits\n  (chain to `skills/deft-directive-refinement/SKILL.md` to pull spec scope\n  back, or the interview), then re-run `skills/deft-directive-cost/SKILL.md`\n  before re-attempting build.\n- ! On a `no-build` decision: stop and exit; do NOT proceed to File Reading.\n  The user has explicitly stopped the project at the cost phase.\n- ⊗ Proceed to File Reading or any subsequent phase when `COST-ESTIMATE.md` is\n  missing, when the decision is unpopulated, or when a skip / rescope / no-build\n  decision has no reason recorded.\n- ⊗ Treat a `rescope` or `no-build` decision as if it were a `build` -- the\n  build skill MUST honor the recorded decision.\n\n## File Reading\n\n- ! Read in order, lazy load:\n  1. `./xbrief/active/` -- scope xBRIEFs for work items to build (required)\n  2. `./xbrief/PROJECT-DEFINITION.xbrief.json` -- project identity, tech stack, architecture\n  3. `./.planning/codebase/MAP.md` -- generated codebase orientation projection, if present (advisory)\n  4. USER.md at the platform-appropriate path (see Platform Detection) -- Personal section is highest precedence; Defaults are fallback\n  5. `deft/main.md` -- framework guidelines\n  6. `deft/coding/coding.md` -- coding standards\n  7. `deft/coding/testing.md` -- testing requirements\n  8. `deft/coding/toolchain.md` -- toolchain validation rules\n  9. `deft/languages/{language}.md` -- only for languages this project uses\n- ~ If the MAP is absent or may be stale and the current scope needs broad codebase orientation, run `task codebase:map` and `task verify:codebase-map-fresh` when those commands resolve. Treat absence/staleness as advisory unless the task edits `plan.architecture.codeStructure`, a configured provider artifact, or the generated MAP itself.\n- ! Treat `plan.architecture.codeStructure` and selected provider artifacts as authoritative. The MAP is a generated projection.\n- ⊗ Read all language/interface/tool files upfront\n- ⊗ Hand-edit `.planning/codebase/MAP.md` or block unrelated implementation solely because the MAP is stale or absent\n\n## Rule Precedence\n\n```\nUSER.md Personal                  <- HIGHEST (name, custom rules -- always wins)\nPROJECT-DEFINITION.xbrief.json   <- Project-specific (tech stack, architecture, config)\nUSER.md Defaults                  <- Fallback defaults (used when PROJECT-DEFINITION doesn't specify)\n{language}.md                     <- Language standards\ncoding.md                         <- General coding\nmain.md                           <- Framework defaults\nScope xBRIEFs                     <- LOWEST\n```\n\n- ! USER.md Personal section always wins over any other file\n- ! For project-scoped settings, PROJECT-DEFINITION.xbrief.json overrides USER.md Defaults\n\n## Change Lifecycle Gate\n\n! Before any implementation that touches 3+ files, verify that a `/deft:change <name>` proposal exists and has been confirmed by the user:\n\n- ! Check `history/changes/` for an active `proposal.xbrief.json` matching this work\n- ! If no proposal exists: propose `/deft:change <name>` and present the change name for explicit confirmation (e.g. \"Confirm? yes/no\")\n- ! The user must reply with an affirmative (`yes`, `confirmed`, `approve`) — a general 'proceed', 'do it', or 'go ahead' does NOT satisfy this gate\n- ? For solo projects: this gate is RECOMMENDED but not mandatory for changes fully covered by `task check`; it remains mandatory for cross-cutting, architectural, or high-risk changes\n- ⊗ Skip this gate because the user has already said \"proceed\" or \"go ahead\"\n\n## Build Process\n\nAll xBRIEFs (including those read from `xbrief/active/` and any new xBRIEFs this skill emits) MUST use `\"xBRIEFInfo\": { \"version\": \"0.6\" }`. The validator rejects any other version (see [`../../conventions/references.md`](../../conventions/references.md)).\n\n### Step 1: Understand the Scope\n\n- ! Read story xBRIEFs from `xbrief/active/` and `PROJECT-DEFINITION.xbrief.json`\n- ! Identify phases, dependencies, starting point from scope xBRIEF acceptance criteria\n- ~ Use `.planning/codebase/MAP.md`, when present, to orient broad codebase scanning. If the MAP conflicts with current code or canonical metadata, surface the drift and trust `plan.architecture.codeStructure` / provider artifacts plus the working tree over generated prose.\n- ! When scanning the existing codebase during scope understanding, MUST surface any contradicting patterns (two error-handling shapes, two state-management approaches, two naming conventions, etc.) before implementation begins -- apply `coding/hygiene.md` `## Surface Conflicts: Pick One, Explain, Flag the Other (#1005)` and choose ONE pattern (more recent OR more tested), explain the choice in the scope summary, and flag the other for cleanup\n- ⊗ Begin implementation against an averaged blend of two contradicting patterns -- \"average code that satisfies both rules is the worst code\" (#1005)\n- ! Present brief summary to user:\n\n> \"Here's what I see: {N} story xBRIEFs in active/. I'll start with {name}. Ready?\"\n\n### Step 2: Verify Toolchain\n\n- ! Before any implementation, verify all tools required by this project are installed and functional — see `deft/coding/toolchain.md` for full rules\n- ! At minimum: confirm task runner (`task --version`), language compiler/runtime, and platform SDK (if applicable) are available\n- ! If any required tool is missing, stop and report — do not proceed to Step 3\n- ⊗ Assume tools are available because the spec references them\n\n### Gate throughput — iteration fast lane vs merge chokepoint (#1704)\n\n> **Invariant:** every change MUST pass the full gate at least once before merge. Iteration MAY use a cheaper proxy; the merge chokepoint MUST NOT be skipped.\n\n- ! **Iteration lane (agents + humans):** during implementation commits, use affected/static gates — targeted tests on changed paths (`vitest run --coverage <paths>` or project equivalent), static `verify:*` gates relevant to touched files, and `task coverage:hotspots` / `task verify:forward-coverage` — NOT full `task check` on every commit.\n- ! **Merge chokepoint:** run full `task check` (or `task check:merge` in the framework source repo) once before push/PR and again when CI merge gate runs. Pre-PR skill exit and review-cycle fix batches still require a green full gate.\n- ! **Escape-rate safety (#1703 Tier-1):** before tightening fast-lane defaults fleet-wide, consult `#1703` measurement — `task eval:health` (Tier 0) and Tier-1 session telemetry (`helped/crud-metrics.jsonl` via instrumented CRUD / workflow metrics). Do NOT invent a separate fast-lane escape-rate surface (#1704 LockedDecisions).\n- ~ **In-engine incrementality (#1713):** content-hash task cache and runner-delegated affected selection are sibling work — not required for this policy face.\n- ⊗ Run full `task check` on every iteration commit when a cheaper proxy suffices — reserve the full gate for PR/merge (#1704).\n- ⊗ Skip the merge chokepoint because the iteration lane passed — the fast lane is convenience only.\n\n**Cost model (swarm-heavy path):** moves from roughly `O(commits × full-gate)` toward `O(merges × full-gate) + O(iterations × cheap-proxy)` when workers iterate with affected/static gates and run full `task check` only at PR/merge.\n\n### Dual stop — multi-iteration implement and pre-PR loops (#2442)\n\nMulti-iteration implement-fix and pre-PR polish loops MUST carry **both** a success stop and a failure/budget stop (`main.md` `## Dual Stop Rule (#2442)`). Single-turn edits and one-shot probes are exempt.\n\n**Defaults for this skill (override only with an explicit operator envelope or xBRIEF field):**\n\n| Loop class | Success stop | Default failure stop |\n|------------|--------------|----------------------|\n| Implement / quality fix (tests, lint, typecheck, coverage, AC) | Affected/static gates green for the change; AC met | **max 5** fix iterations **or** **3** consecutive identical outcomes (same failing command + same primary error class) with no material code/config change |\n| Pre-PR polish (`deft-directive-pre-pr` Read-Write-Lint-Diff) | Full pass with zero further edits | **max 3** polish passes **or** **2** consecutive no-diff / same-diff outcomes |\n| Full `task check` re-run after a red merge chokepoint | `task check` green | Counts toward the implement/quality fix envelope above (do not open a separate unbounded check-retry loop) |\n\n**On failure stop:**\n\n- ! Halt the loop. Surface an **operator-visible halt report** with: (1) iterations attempted and which stop fired (max-iter / no-progress / budget), (2) commands and primary failure fingerprints tried, (3) what is still red or missing, (4) the human decision needed (unblock dependency, rescope AC, waive with audit, abandon).\n- ! Prefer a structured `BLOCKED:` terminal (preamble §11 / #2843) when exiting a drive-to:merge-ready or parent-dispatched unit early because the envelope is exhausted.\n- ⊗ Continue \"one more fix\" after the envelope is exhausted.\n- ⊗ Reset the counter by opening a new commit, rewording the same change, or swapping workers while the same failure class remains.\n\n\n### Budget-aware effort - bank the pass before deepening (#3266)\n\nWhen a hard turn or cost budget is detectable (session:start `effort_budget` / env `DEFT_MAX_TURNS` / `DEFT_MAX_BUDGET` / host descriptor #1461), size effort to the **stated** acceptance bar first. This is the success-side analog of dual-stop (#2442): dual-stop stops thrash on failure; bank-the-pass stops budget exhaustion on over-deepening.\n\n- ! At implement start, read the session effort-budget signal (`task session:start` lines or JSON `effort_budget`, or env). When `posture=hard-capped`, treat the run as budget-constrained.\n- ! **Bank the pass first:** satisfy stated acceptance criteria (xBRIEF items / issue AC / official checker) and produce the passing artifact **before** any self-imposed deeper verification suite that exceeds the stated bar.\n- ! Only with **remaining** budget after the stated pass, extend verification depth. Never deepen past the point where a found defect could not also be fixed within budget (default reserve: enough turns/cost for one fix batch).\n- ! Self-verification scope scales with remaining budget - prefer the official/stated checks under a tight cap.\n- ! When deepening is skipped for budget, MUST say so in the run summary / handoff (`deepening_skipped=true` + reason) - fail-loud (#1006). Use `formatDeepeningSkippedNote` semantics from `packages/core/src/session/effort-budget.ts`.\n- ~ When no hard budget is detected (`posture=unbounded`), normal dual-stop defaults still apply; bank-the-pass is optional discipline, not a license to skip stated AC.\n- ⊗ Exhaust the turn/cost budget on self-imposed gold-plating after the stated bar is already within reach (#3266).\n- ⊗ Silently skip deepening without naming it, or silently gold-plate under a hard cap (#1006 / #3266).\n- ⊗ Treat bank-the-pass as permission to ship without meeting stated AC - stated AC remains the success stop.\n\nCore helper: `packages/core/src/session/effort-budget.ts` (`detectHardEffortBudget`, `recommendVerificationDepth`). Composes #2442, #1581, #3214, #1006.\n**Enforcement note:** skill defaults are behavioral. Durable delivery/acceptance circuit-breaker: **#3143** `packages/core/src/delivery-attempt/` (`evaluatePreDispatch`, `.deft/delivery-attempts/`). Docs: `docs/delivery-attempt.md`. Route delivery/acceptance automatic retries through that gate; do not invent a parallel ledger in this skill.\n\n### AC-pass banking checkpoint - finalize on green (#3285)\n\nSharpens #3266: the **first** moment stated/official acceptance criteria pass is a **banking checkpoint**, not a license to keep spending the turn budget on self-imposed depth.\n\n- ! When stated acceptance criteria first pass (`task verify:ac` / product-first done-gate #3284 / official checker), the **next** action is **FINALIZE**: checkpoint-commit the green state and record the bank (durable under `.deft/ac-pass-banks/`; optional run-summary line when `DEFT_RUN_SUMMARY_PATH` is set).\n- ! **Deepening after the bank requires surplus budget.** Self-imposed extra verification, refactors, or polish are permitted only when remaining budget meets `plan.policy.acPassBanking.surplusThreshold` (default **0.2** = 20% of max turns/cost still remaining) **and** the absolute reserve from #3266. Env override: `DEFT_AC_PASS_SURPLUS_THRESHOLD`.\n- ! Deepening, when allowed, happens **on top of** the committed checkpoint so a failed experiment can revert to banked green.\n- ! **Post-bank discoveries are reported, not chased** when surplus is insufficient: file a note/issue in the deliverable for out-of-scope defects unless they **regress stated AC** (then fix-regression). Finding beyond the bar is a win; thrashing a dying budget into a zero is the failure mode this rule closes.\n- ! When surplus is insufficient, ship the banked state and fail-loud (`deepening_skipped=true` + surplus reason) via `evaluateAcPassBanking` / `formatDeepeningSkippedNote` semantics.\n- ~ When no hard budget is detected, dual-stop still applies; bank-on-first-AC-pass remains good discipline but is not a hard surplus gate.\n- ⊗ Convert a banked official pass into a scored failure by chasing post-bank polish until the turn budget dies (#3285).\n- ⊗ Start post-bank deepening without a finalize checkpoint when a hard budget is active (#3285).\n- ⊗ Chase out-of-scope post-bank findings when surplus is below threshold (#3285).\n\nCore helpers: `packages/core/src/session/ac-pass-banking.ts` (`evaluateAcPassBanking`, `bankAcPass`, `decidePostBankFinding`, `simulateSurplusInsufficientRun`); policy: `packages/core/src/policy/ac-pass-banking.ts` (`plan.policy.acPassBanking`). Composes #3266, #3284, #3282 (optional bank-event JSONL), #1006.\n\n## Step 3: Build Phase by Phase\n\nFor each phase:\n\n1. ! **Scaffold** — file structure, dependencies, config\n2. ! **Test first** — write tests before implementation (TDD)\n3. ! **Implement** — make tests pass, following deft coding standards\n4. ! **Verify (iteration lane)** — run affected/static gates per `#1704` fast lane above; fix failures before checkpoint commits\n5. ! **Origin sync** — when this phase materially changed an origin-linked scope xBRIEF (`plan.references` includes `x-xbrief/github-issue`), run `task issue:sync-from-xbrief -- <path>` (or `--dry-run` to preview) so the linked GitHub issue receives a sync comment; if skipped, document why in the PR or session notes (#2540)\n6. ! **Checkpoint** — tell user what's done, what's next\n\n- ⊗ Move to next phase until current phase passes all checks\n\n### Step 4: Quality Gates\n\nAfter EVERY phase (iteration lane — #1704):\n\n```bash\nvitest run --coverage <changed-paths>   # or project test runner on touched modules\ntask coverage:hotspots                  # branch headroom before merge\ntask verify:forward-coverage            # new-source coverage (#1310)\n```\n\nBefore PR / phase handoff (merge chokepoint):\n\n```bash\ntask check          # Full gate — format, lint, typecheck, tests, coverage, verify:*\ntask test:coverage  # >=85% or PROJECT-DEFINITION.xbrief.json override\n```\n\n- ! Phase checkpoint commits MAY use the iteration lane; phase is NOT done for PR handoff until full `task check` passes at the merge chokepoint\n- ⊗ Skip quality gates or claim they passed without running\n- ⊗ Treat iteration-lane green as merge-ready without full `task check`\n- ! **Multi-scope batch (#3012):** when implementing an approved multi-scope pin/cohort, reserve full `task check` for end-of-batch (or after last scope) unless the last full check failed — then re-run on the fix loop. Do not run full check after every intermediate scope.\n- ⊗ Re-run full install/session ceremony after offline seed when ritual is already complete (#3010) — use `session:ready` for recovery only.\n\n\n## Product-first done-gate (#3284) / literal AC (#3267)\n\nAt intake, capture the task statement's **exact** acceptance commands as executable AC (`plan.acceptance.commands` + #3267 `literal_acceptance_commands`). Empty is allowed only with `none_stated: true` (ladder: stated → derived → project_floor). Before declaring done, run them **verbatim** — same paths, same flags, same working directory. Self-chosen verification is supplementary, never a substitute. Extends #973. `task check` runs `verify:ac` **first** (fail-fast); hygiene is second and may become advisory under pressure. Rapid ceremony = **AC-only**.\n\n- ! When reading the active scope xBRIEF / issue body at story start, capture stated shell acceptance commands into `plan.acceptance.commands` (issue:ingest stamps this + the #3267 ledger automatically). Do not paraphrase.\n- ! Before claiming phase or story done (and before merge-chokepoint PR handoff), run:\n```\ntask verify:ac -- <active-story-path>\n```\n  Exit 0 = pass or none stated with valid marker; exit 1 = a stated command failed; exit 2 = config. (`verify:literal-ac` is the #3267 mechanism alias.)\n- ! Quote the literal invocations and their outputs in the completion note when commands were stated.\n- ⊗ Substitute a self-chosen approximation (`pnpm test` when the statement said `pnpm exec vitest run packages/core/src`) for the stated command.\n- ⊗ Skip this gate because ceremony dial is rapid/minimal — rapid's positive content is exactly this check (#3284).\n- ⊗ Leave `plan.acceptance.commands` empty without `none_stated: true` — absence must be an explicit decision.\n\n## Product-oracle gate integrity (#3322 / #3156)\n\nA red product verification may be resolved only by a product change or an independently re-derived oracle (both sides rebuilt from scratch, different method). In-place repair of the failing comparison then pass is not a pass — it is an unresolved discrepancy.\n\n- ! When a product oracle is red, resolve it by changing the product or by independently re-deriving the oracle, and record `independent_rederivation` on the run-summary `verification` event.\n- ! Emit a run-summary verification event `{check_id, method_fingerprint, outcome}` for each product-oracle attempt when `DEFT_RUN_SUMMARY_PATH` is set. `fail` then a different `method_fingerprint` then `pass` on one check id is machine-flagged.\n- ! `task verify:ac` treats comparison-method mutation as unresolved (exit non-zero) unless independent re-derivation is recorded. Lead the done report with any unresolved discrepancy (#1006).\n- ⊗ Self-adjudicate a red product oracle by editing the comparison (reference file, diff invocation, one-sided regenerate) and shipping the new pass as success.\n\n## Operator-log hygiene (lazy-load, #1940)\n\nWhen the story touches **operator-facing** services (dashboards, multi-process\nworkers, WARN/ERROR operators triage):\n\n- ~ SHOULD load `patterns/operator-log-hygiene.md` and apply the copy-paste\n  checklist in `docs/operator-log-hygiene-checklist.md` to story AC or probe\n  locked decisions before claiming logging done\n- ⊗ MUST NOT treat this as Product Insights (#2603) or LLM-call telemetry\n  (#481) — those are different lanes\n- ⊗ MUST NOT assume core `deft check` enforces a log schema by default —\n  consumer-owned shape; optional pack stub under\n  `docs/operator-log-hygiene-consumer-pack-stub.md`\n\nDiscovery keywords: operator log, operator-facing logs, observability checklist\n— also indexed in `REFERENCES.md`.\n\n## Goal-gate determinism (lazy-load, #852)\n\nWhen authoring or tightening story acceptance criteria, quality gates, or skill\nsteps during build:\n\n- ~ SHOULD load `patterns/goal-gate-determinism.md` — goals, AC, gates, exit,\n  scope, stop, and preserve are rigid; pure execution path is flexible guidance\n- ⊗ MUST NOT treat \"all process steps done\" as verification — outcomes and\n  gates own \"done\" (see also `verification/verification.md` and Fail Loud #1006)\n\nDiscovery keywords: goal-gate-determinism, rigid goals flexible path — also\nindexed in `REFERENCES.md`.\n\n## Coding Standards (Summary)\n\nRead full files when you need detail:\n\n- ! TDD: write tests first — implementation incomplete without passing tests\n- ! Coverage: ≥85% lines, functions, branches, statements\n- ~ Files: stay small; line counts live in the file-size-thresholds policy module (review trigger, not a hard cap; #1488 / #3424)\n- ~ Naming: hyphens for filenames unless language idiom dictates otherwise\n- ! Contracts first: define interfaces/types before implementation\n- ! Secrets: in `secrets/` dir with `.example` templates; ⊗ secrets in code\n- ! Commits: Conventional Commits format; ! use iteration fast lane before checkpoint commits; ! run full `task check` at PR/merge chokepoint only (#1704)\n\nSee `deft/coding/coding.md` and `deft/coding/testing.md` for full rules.\n\n## Pre-Commit File Review\n\n! Before every commit, re-read ALL modified files and explicitly check for:\n\n1. ! **Encoding errors** -- em-dashes corrupted to replacement characters, BOM artifacts, mojibake from round-trip read/write\n2. ! **Unintended duplication** -- accidental double entries in CHANGELOG.md, scope xBRIEF files, or structured data files\n3. ! **Structural issues** -- malformed CHANGELOG entries, broken table rows, mismatched index entries, invalid JSON/YAML\n4. ! **Semantic accuracy** -- verify that counts, claims, and summaries in CHANGELOG entries and ROADMAP changelog lines match the actual data in the commit (e.g. \"triaged 4 issues\" must match the number actually triaged, issue numbers cited must match the issues actually added)\n5. ! **Semantic contradictions** -- when adding a `!` or `⊗` rule that prohibits a specific command, pattern, or behavior, search the same file for any `~`, `≉`, or prose that recommends or permits the same command/pattern -- resolve all contradictions in the same commit before pushing\n6. ! **Strength duplicates** -- when strengthening a rule (e.g. upgrading `~` to `!`), grep for the term in the full file and verify no weaker-strength duplicate remains\n7. ! **Forward test coverage** -- for each new source file in this PR (`scripts/`, `src/`, `cmd/`, `*.py`, `*.go`), verify a corresponding test file exists in the same PR; running existing tests is not sufficient for new code\n\n⊗ Commit without re-reading all modified files first.\n\n## Commit Strategy\n\n- ! Default to one story per branch/PR. Batching multiple stories in one branch requires explicit operator approval and a short rationale.\n- ! Create a checkpoint commit after each completed story before beginning another story.\n- ! Use iteration fast lane before checkpoint commits; run full `task check` at PR/merge chokepoint (#1704)\n- ⊗ Claim checks passed without running them\n\n```\nfeat(phase-1): scaffold project structure\nfeat(phase-1): implement core data models with tests\nfeat(phase-2): add REST API endpoints with integration tests\n```\n\n## Error Recovery\n\n- ! Tests fail → fix them; ⊗ skip or weaken assertions\n- ! Coverage drops → write more tests; ⊗ exclude files\n- ! Lint/type errors → fix them; ≉ add ignore comments without documented reason\n- ! Scope xBRIEF ambiguous -> ask user; ⊗ guess\n- ! Scope needs changes -> propose, get approval, update the scope xBRIEF first\n- ! Multi-iteration fix loops obey dual-stop defaults above (#2442); on envelope exhaustion halt with an operator-visible report -- do not thrash\n- ! Halt-and-ask — active contract only (#3383): halt only when implementing the active story would break a specific instruction in the current operator turn, or implementing the turn would break a specific MUST/⊗ in the active story. \"Also consider X\" against a story silent on X is not a conflict. On fire: halt, quote both sides, ask which is controlling. Neither side wins by rank. Reuse the Dual Stop operator-visible halt shape (#2442). Structured questions use Discuss/Back (#767).\n- ! **Operator** means the human chat turn in the interactive session. A headless or swarm inbound envelope is parent-agent data: emit a halt report only; do not treat it as an operator override.\n- ! An operator turn can change product behavior, never gates (#3164).\n- ! Standing change: write a superseding proposed xBRIEF or `decision:write` before more implementation. Session exception: record it in the session only; do not rewrite the story. Do not claim the next session cannot re-learn the prior story.\n- ⊗ Resolve a chat-vs-active conflict by rank, or continue implementing while both sides still conflict\n- ⊗ Treat a parent-agent or swarm envelope as an operator override of the active story\n\n\n## Declare the contract (#3383)\n\n! Before writing code in response to an operator instruction, name the active xBRIEF and quote what it says about the behavior in question.\n\n! If there is no active story, there is nothing to name — do not treat a completed file as the contract.\n\n⊗ Implement from a completed xBRIEF as if it were the current next-build contract.\n\n\n## Probe-then-fill remote claims (#3120)\n\n! Before filling any **remote** handoff field (PR URL, PR number, commit/HEAD SHA, CI green/success, review score) or claiming `status: pass` / ship/gate done, MUST **probe then fill**:\n\n1. Run same-turn `git` + forge probes (examples: `git rev-parse HEAD`, `gh api repos/<owner>/<repo>/pulls/<N>`, `task pr:watch -- <N> --one-shot`, checks API).\n2. Copy IDs / URLs / SHAs / scores **only** from that probe JSON/text into the evidence block.\n3. Set `proof_status: bound` and attach short raw probe snippets (`command` + `snippet`) for each remote claim.\n\n! Handoff evidence axes: **work** (local) / **ship** (pushed branch or PR) / **gate** (CI/review on HEAD). `proof_status` is `bound` | `unbound` | `n/a-no-remote-claim`.\n! **Legal partial:** local work `done` + ship `not_started` / `blocked` **without** PR/SHA/CI/review fields and `proof_status: n/a-no-remote-claim` (or `status: partial`) is valid — do not invent ship state.\n! **Fail ranking:** **invented-done** (false/unbound remote artifacts under pass) is **stricter** than **empty-done**. Unbound remote claims → invalid evidence (fail), not pass-with-notes.\n! Machine check: `validateHandoffEvidence` in `packages/core/src/handoff-evidence/` (see `templates/agent-prompt-preamble.md` §11).\n⊗ Fill PR / SHA / CI / review fields from recollection, narration, or prior-turn memory.\n⊗ Claim `status: pass` with remote fields when `proof_status` is not `bound` or probes are missing (#3120).\n\n## Completion\n\n- ! When all phases pass and `task check` is green, complete each implemented story via `task scope:complete -- <active-story-path>` before final PR handoff.\n\n> \"The project is built and all quality checks pass. Describe any new features you'd like to add — I'll follow the deft standards we've set up.\"\n\n\n## Significant decision log (#1396)\n\n! When this scope makes a **significant** choice (architecture, product behavior, security, public/private boundary, data model, runtime topology, hard-to-reverse process), record it with `task decision:write` (or `--body-file` for multi-line fields) so later agents load rationale without inventing it.\n\n~ Prefer attaching with `--scope <active-xbrief>` when the decision is bound to this story; use standalone `xbrief/decisions/` for cross-cutting / multi-scope process choices.\n\n~ Before claiming a process/architecture path was 'already decided', run `task decision:list -- --query <topic>` (or `--issue N`).\n\n⊗ Require a decision record for every trivial scope or routine fix.\n⊗ Merge lessons (#1513) into decision records, or replace ADRs under `docs/decisions/ADR-*.md`.\n\nDocs: `docs/decision-log.md` · `xbrief/decisions/README.md`.\n\n## Anti-Patterns\n\n- ⊗ Skip tests or write them after implementation\n- ⊗ Ignore `task check` failures\n- ⊗ Implement things not in scope xBRIEF without asking\n- ⊗ Read every deft file upfront\n- ⊗ Move to next phase before current passes checks\n- ⊗ Make commits without running iteration-lane validation; ⊗ skip full `task check` at PR/merge chokepoint (#1704)\n- ⊗ Proceed without USER.md -- always run the USER.md Gate first\n- ⊗ Re-run `directive init`, cold `session:start`, migrate, or re-copy pin scopes after offline seed when ritual is already complete (#3010)\n- ⊗ Run full `task check` after every intermediate scope of an approved multi-scope batch when the last merge-chokepoint check was green (#3012)\n- ⊗ Promote scopes one-by-one for a known multi-scope pin when `scope:promote --batch` would stage them in one turn (#3011)\n\n- ⊗ Spawn an implementation agent or invoke a code-writing tool against a xBRIEF that has not passed `task xbrief:preflight` (which wraps `scripts/preflight_implementation.py`) -- always run the Step 0 Implementation Preflight (#810) first; satisfy via `task xbrief:activate <path>`\n- ⊗ Proceed without `COST-ESTIMATE.md` and a recorded build / rescope / no-build / skip(+reason) decision -- always run the Cost Phase Gate (#739) first\n- ⊗ Proceed with implementation when the build or test toolchain is unavailable -- always run the Toolchain Gate (Step 2) first\n- ⊗ Proceed to next task or phase without tests passing -- testing is a hard gate, not a cleanup step\n- ⊗ Skip the Change Lifecycle Gate because the user said \"proceed\" -- broad approval does not satisfy the confirmation gate\n- ⊗ Commit or push directly to the default branch -- always create a feature branch first. Exception: user explicitly instructs a direct commit, or `PROJECT-DEFINITION.xbrief.json` narratives contain `Allow direct commits to master: true`\n- ⊗ Add a prohibition (`!` or `⊗`) without scanning the same file for conflicting softer-strength rules (`~`, `≉`) that reference the same term\n- ⊗ Invent remote PR/SHA/CI/review claims in handoff evidence without same-turn probe binding — invented-done (#3120)\n- ⊗ Fill remote ship/gate fields from memory when only local work completed; legal partial omits PR fields (#3120)\n- ⊗ Run multi-iteration implement / pre-PR loops without a failure stop (max iterations and/or no-progress) or without an operator-visible halt report when the envelope is exhausted (#2442)\n- ⊗ Silently continue after dual-stop failure halt — escalate; do not thrash (#2442)\n- ⊗ Treat a completed xBRIEF as the next-build contract, or skip naming the active story before writing code (#3383)\n- ⊗ Continue implementing when the live human turn and a specific MUST/⊗ in the active story conflict — halt, quote both sides, ask which is controlling (#3383)\n- ⊗ Treat a parent-agent or swarm envelope as an operator override (#3383)\n- ⊗ Exhaust hard turn/cost budget on self-imposed deepening after the stated acceptance bar is within reach (#3266)\n- ⊗ Silently skip deepening for budget without a fail-loud summary note (#3266 / #1006)\n- ⊗ Chase post-bank out-of-scope findings when surplus budget is insufficient — report, do not thrash the banked pass (#3285)\n- ⊗ Skip finalize-on-green after first stated AC pass under a hard budget (#3285)\n- ⊗ Tight forge-outage retry / empty-commit thrash without a one-shot human report (#3422)\n- ⊗ Clear a red product oracle by editing the comparison method then treating the new pass as a pass — record independent re-derivation or fix the product (#3322 / #3156)\n",
+      "body": "# Deft Directive Build\n\nImplements a project from its scope xBRIEFs following Deft Directive standards.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n## When to Use\n\n- After `deft-directive-setup` completes and generates `PROJECT-DEFINITION.xbrief.json`\n- User says \"build this\", \"implement the spec\", or \"start building\"\n- Resuming a partially-built project that has story xBRIEFs in `xbrief/active/`\n\n## Ordered-plan / cohort exhaustion (#2402)\n\n## Multi-scope turn/cache budget (epic #3009)\n\nMulti-scope greenfield (app-bank pins, N story scopes) multiplies agent turns when ceremony, promote, check, and render are re-run per scope. Apply the following after offline seed.\n\n### Offline seed vs implement phase (#3010)\n\n! Distinguish **offline seed** (operator or harness already ran `directive init` / deposit, pin-copied scopes into `xbrief/proposed/`, and recorded session ritual) from the **agent implement phase**.\n\n! When seed + session ritual are already complete for the engagement:\n- ⊗ Run `directive init` again\n- ⊗ Run full cold `session:start` unless hooks deny writes and recovery is required\n- ⊗ Run `directive migrate` or re-copy scopes already present\n- ! Prefer recovery via `session:ready` (or re-arm) when PreToolUse denies — not full re-init\n- ! Documented consumer/harness contract: seed is done once; implement agents only activate+implement\n\n### Batch promote; one active implement (#3011)\n\n! For a multi-scope pin, batch-stage scopes with `task scope:promote -- --batch` (all `proposed/`) or `task scope:promote -- --batch <path>…`.\n! Implement path remains **one** `scope:activate` + implement at a time — no multi-active write fence.\n! When pin order is known, do **not** re-list the entire lifecycle tree every scope; walk the known ordered list.\n⊗ Activate all scopes at once or drop the one-active-scope / story-ready stack.\n\n### Quality check once at end of multi-scope batch (#3012)\n\n! On an approved multi-scope batch (operator-approved multi-story branch, swarm cohort, or pin walk): run full `task check` (merge chokepoint) **once at the end of the batch** (or after the last scope), not after every scope.\n! Exception: if the last full check **failed**, fix loops MAY re-run check until green.\n! Pre-PR / merge-ready gates remain end-of-unit — this does not weaken them.\n! Iteration lane (affected tests / `verify:forward-coverage` / `coverage:hotspots`) still applies **per scope** during implementation (#1704).\n⊗ Spam full `directive check` / `task check` after every scope when the batch is still mid-flight and the last merge-chokepoint check was green.\n\n### One-shot project:render (#3013)\n\n! Greenfield init seeds a minimal render-ready `PROJECT-DEFINITION`. Treat `task project:render` as a **refresh of items from lifecycle folders**, not multi-turn identity research.\n⊗ Invent project identity across many turns when seed already stamped the skeleton.\n\n\n! When processing an approved multi-story cohort or an active ordered-plan sequence, stop after the final approved entry. Do not promote or dispatch adjacent stories from queue intuition. Continuation language advances only within the approved order; skill-chaining is non-authorizing.\n\n## Step 0 -- Implementation Preflight (#810)\n\n- ! Before starting any new implementation story or switching from one story to another, MUST run `git status --short --branch`.\n- ! If the working tree is dirty, MUST stop and summarize the current branch, modified/untracked files, and whether the changes appear related to the target story. Ask the operator to choose one path: commit existing work, stash existing work, include existing work in the current story, or stop.\n- ⊗ Begin a new story while unrelated dirty work is present without explicit operator approval.\n- ! Resolve exactly one target story xBRIEF path by default. One story is the default implementation unit for this skill; if the user asks for a phase/epic, decompose or ask which story to start.\n- ! Batching multiple stories in one branch/PR requires explicit operator approval and a short rationale recorded in the handoff.\n- ! **Swarm-cohort dispatch carve-out**: when this skill is invoked as part of a swarm cohort allocated by `skills/deft-directive-swarm/SKILL.md`, the approved Phase 5 allocation plan satisfies the \"explicit operator approval and short rationale recorded in the handoff\" requirement above -- the dispatched xBRIEF paths and allocation rationale ARE the consent token. Process each assigned story sequentially under the checkpoint-commit + `task scope:complete` discipline below. Do NOT re-prompt the parent for batching approval mid-cohort -- the all-or-nothing dispatch envelope rule (`AGENTS.md` `## Multi-agent orchestration discipline (#954)`) forbids mid-scope user-approval gates.\n- ! **Structured consent-token recognition (#1378)**: the canonical recognition path for the carve-out above is the structured `## Allocation context` section of the dispatch envelope (the frozen schema in `templates/agent-prompt-preamble.md`, Story A of #1378). When that section reports `dispatch_kind: swarm-cohort` with a non-null `allocation_plan_id` AND a non-null `batching_rationale`, the consent token is satisfied mechanically -- read `cohort_vbriefs` as the authoritative file boundary and process each entry sequentially under the checkpoint-commit + `task scope:complete` discipline below, without re-prompting the parent for batching approval mid-cohort. When the `## Allocation context` section is ABSENT (pre-#1378 dispatches, solo-interactive sessions), fall back to the #1371 prose carve-out immediately above -- the prose carve-out remains the recognition path of record for un-elevated envelopes.\n- ! **Within a cohort, between stories**: the working tree MUST be clean after each story's checkpoint commit + `task scope:complete`. If `git status --short` shows uncommitted state between stories (e.g. a missed `task scope:complete` move, an unstaged file from the prior story), checkpoint-commit it and proceed -- do NOT pause to ask the operator. The dirty-tree \"ask the operator\" branch above applies only at the FIRST story-start of a fresh branch, where uncommitted operator work might legitimately exist.\n- ! If the target story is in `xbrief/proposed/`, run `task scope:promote -- <path>` first (or `task scope:promote -- --batch` for a multi-scope pin — #3011); if it is in `xbrief/pending/`, run `task scope:activate -- <path>`. After activation, update the path to the active-file location before preflight.\n- ! **Effort estimate gate (#1581):** before `task scope:activate` / `task vbrief:activate`, scan `plan.items` (including nested `items` / `subItems`) for `effort`. Time anchors: `S` <2h, `M` half-day (2-4h), `L` 1-2 days, `XL` needs breakdown. The activate path fails closed while any item still has `effort: \"XL\"` — break XL work into S/M/L items (or re-estimate) first. Omitted `effort` remains valid (field is optional). Plan-item effort is **post-planning** authority (confirms/corrects intake estimates); it is **not** session-start ritual input — ceremony depth (#3214) uses two-stage rapid→escalate, not a required plan-item read at cold start. Headless: no operator confirm. Depth: `vbrief/vbrief.md` § Effort estimate.\n- ⊗ Activate a scope that still carries plan items with `effort: \"XL\"` — XL means \"not ready to start\" until broken down (#1581).\n- ⊗ Require plan-item `effort` to choose session-start ritual depth — estimates do not exist until after planning (#1581 / #3214).\n- ! Before any code-writing tool call -- the first scaffold edit, the first `task` invocation that mutates files, or any `start_agent` dispatch that will implement scope -- MUST run `task xbrief:preflight -- <active-story-path>` (the structural intent gate; wraps `scripts/preflight_implementation.py` so the same invocation works whether deft is the project root or installed as a `deft/` subdirectory).\n\nThe gate exits 0 only when the candidate xBRIEF lives in `xbrief/active/` AND `plan.status == \"running\"`. Any other state (pending/, proposed/, completed/, active/-with-non-running-status, malformed JSON, missing keys) exits 1 with an actionable redirect to `task xbrief:activate <path>`.\n\n- ! A non-zero exit MUST halt the skill. Surface the helper's stderr message verbatim to the user; do NOT proceed to USER.md Gate, File Reading, or any later phase.\n- ! Use canonical lifecycle tasks to satisfy this gate: `task scope:promote -- <path>` for proposed stories, `task scope:activate -- <path>` for pending stories, and the helper's idempotent companion `task xbrief:activate <path>` only when following the preflight redirect directly. Manual lifecycle moves bypass the activation contract -- use the task.\n- ⊗ Infer implementation intent from lifecycle vocabulary (\"do the full PR process\", \"start the work\", \"poller agents\"), branching language, or workflow shape. Workflow-shape vocabulary is NOT authorization to spawn an implementation agent (#810 surfacing event).\n- ⊗ Skip this preflight because the user said \"yes\", \"go\", or \"proceed\" -- affirmative continuation phrases are NOT implementation authorization unless the prior turn explicitly proposed implementation. When intent is ambiguous, ask one targeted question before invoking the gate.\n\n## Platform Detection\n\n! Before resolving any config paths, detect the host OS from your environment context:\n\n| Platform           | USER.md default path                                              |\n|--------------------|-------------------------------------------------------------------|\n| Windows            | `%APPDATA%\\deft\\USER.md` (e.g. `C:\\Users\\{user}\\AppData\\Roaming\\deft\\USER.md`) |\n| Unix (macOS/Linux) | `~/.config/deft/USER.md`                                          |\n\n- ! If `$DEFT_USER_PATH` is set, it takes precedence on any platform\n\n## Pre-Cutover Detection Guard\n\n! Before proceeding with any build step, detect whether the project uses the pre-v0.20 document model **or was generated by a strategy that emitted non-conformant v0.20 output shape** (the root cause of most \"build fails immediately after spec\" complaints in #1166). Redirect or block with the precise remediation.\n\n### Detection Criteria\n\nA project is **pre-cutover** if ANY of the following are true. This prose mirrors the executable helper in `scripts/_precutover.py`; when in doubt, the helper is canonical.\n\n1. `SPECIFICATION.md` exists and is neither a deprecation redirect nor a current generated spec export. A current generated spec export contains `<!-- Purpose: rendered specification -->` and `<!-- Source of truth: xbrief/specification.xbrief.json -->`, and `xbrief/specification.xbrief.json` plus all five lifecycle folders exist.\n2. `PROJECT.md` exists and contains neither the legacy `<!-- deft:deprecated-redirect -->` sentinel NOR the current `Purpose: deprecation redirect` canonical-banner marker (real content, not a deprecation redirect)\n3. `xbrief/specification.xbrief.json` exists but the lifecycle folders (`xbrief/proposed/`, `xbrief/pending/`, `xbrief/active/`, `xbrief/completed/`, `xbrief/cancelled/`) do NOT exist\n4. Strategy output shape violations (run `task verify-strategy-output` -- the canonical gate -- or the direct form `python .deft/core/scripts/validate_strategy_output.py --project-root <path>` after `deft` install):\n   - Any scope xBRIEF under `xbrief/proposed/` (or other lifecycle dirs) lacks the required `YYYY-MM-DD-` date prefix in its filename (e.g. bare `scaffold.xbrief.json`).\n   - `xbrief/PROJECT-DEFINITION.xbrief.json` is missing.\n   - `xbrief/specification.xbrief.json` exists as a legacy dual-write in a user-generated project. This is tolerated only for the framework source tree or a complete post-cutover full-spec consumer where all lifecycle folders exist and `SPECIFICATION.md` is rendered from `xbrief/specification.xbrief.json`.\n\n### Action on Detection\n\n! If pre-cutover or strategy-nonconformant state is detected, **stop immediately** and display an actionable message that cites the exact validator:\n\n> \"This project was generated with pre-v0.20 or non-conformant strategy output. Run the deterministic validator and follow its remediation: `task verify-strategy-output` (works in source and after `deft` package install) or `python .deft/core/scripts/validate_strategy_output.py --project-root .`. For document-model migration, follow UPGRADING.md § Frozen pre-v0.20 document-model migration (#2068): pin v0.59.0, then run `task migrate:vbrief` from that payload. Otherwise `task project:render` / strategy re-run as indicated.\"\n\n! Include specific details about what was detected (the validator output is authoritative):\n\n- Legacy specification.xbrief.json or missing lifecycle folders: \"Follow the frozen v0.59.0 migrator path (#2068) or run `task migrate:preflight` for current-release guidance\"\n- Non-date-prefixed xBRIEFs: \"Re-run the emitting strategy after the v0.20 migrations (#1166 s1+s2+...) or manually rename files to `YYYY-MM-DD-<slug>.xbrief.json` and `task scope:promote`\"\n- Missing `PROJECT-DEFINITION.xbrief.json`: \"Run `task project:render` to generate the project definition\"\n- `SPECIFICATION.md` / `PROJECT.md` without sentinel: the classic pre-cutover messages\n- Scope xBRIEF in wrong folder: \"Status is '{status}' but file is in {folder}/ -- run `task scope:activate <file>` to fix\"\n\n! After the validator reports clean, re-run this guard before continuing.\n\n⊗ Proceed with build when pre-cutover or strategy-nonconformant artifacts are detected -- always redirect to the frozen migration path first (or run the validator) and surface the exact remediation.\n⊗ Silently ignore these artifacts or guess at fixes -- the validator (wired into `task check` and this guard) is the deterministic gate.\n\n## USER.md Gate\n\n! Before proceeding, verify USER.md exists at the platform-appropriate path\n(resolved via Platform Detection above, or `$DEFT_USER_PATH` if set).\n\n- ! If USER.md is not found: inform the user and redirect to `deft-directive-setup`\n  Phase 1 before continuing -- do not proceed without user preferences\n- ! Once USER.md exists, continue with the Cost Phase Gate below\n\n### Forge-outage drop-back (#3422)\n\n! On attributed platform outage or repeated REST 429/502/503 during YOLO / through-merge implement: drop GitHub I/O, report once to the human in chat, and re-probe on `plan.policy.forgeOutageRetryMinutes` (default **30**; USER.md Personal wins; min 5; `task policy:show --field=forgeOutageRetryMinutes`). Local edit/test/commit MAY continue. Depth: [`scm/github.md`](../../scm/github.md) § #3180 / #3422. Complements #3167 / #3180.\n\n⊗ Tight retry, empty-commit thrash, or sending the human to github.com as the only remediation.\n\n## Cost Phase Gate (#739)\n\n! Before proceeding to File Reading, verify the project has gone through the\npre-build cost & budget transparency phase from `skills/deft-directive-cost/SKILL.md`.\nThis closes the adoption-blocker surfaced by issue #739 (refs #151 umbrella) where\nusers finished the spec flow and stopped at build because deft offered no cost\nsignal.\n\n### Detection\n\n- ! Check for `COST-ESTIMATE.md` in the project root.\n- ! Check that the file contains a recorded decision (the **Decision recorded**\n  block populated with one of: `build`, `rescope`, `no-build`, `skip`).\n- ! For `skip`, `rescope`, or `no-build` decisions: the **Reason** field MUST be\n  populated (one or two sentences in plain language). A skip with no reason\n  recorded is treated the same as no decision.\n\n### Action\n\n- ! If `COST-ESTIMATE.md` is missing OR the **Decision recorded** block is\n  unpopulated OR a `skip`/`rescope`/`no-build` decision has no reason recorded:\n  stop immediately and redirect the user:\n\n  > \"This project has not gone through the pre-build cost & budget transparency\n  > phase. Run `skills/deft-directive-cost/SKILL.md` to produce a plain-English\n  > `COST-ESTIMATE.md`, then re-run the build skill once the user has chosen\n  > build / rescope / no-build / skip(+reason).\"\n\n- ! On a `build` or `skip` decision: continue with File Reading below.\n- ! On a `rescope` decision: stop and redirect the user back to spec edits\n  (chain to `skills/deft-directive-refinement/SKILL.md` to pull spec scope\n  back, or the interview), then re-run `skills/deft-directive-cost/SKILL.md`\n  before re-attempting build.\n- ! On a `no-build` decision: stop and exit; do NOT proceed to File Reading.\n  The user has explicitly stopped the project at the cost phase.\n- ⊗ Proceed to File Reading or any subsequent phase when `COST-ESTIMATE.md` is\n  missing, when the decision is unpopulated, or when a skip / rescope / no-build\n  decision has no reason recorded.\n- ⊗ Treat a `rescope` or `no-build` decision as if it were a `build` -- the\n  build skill MUST honor the recorded decision.\n\n## File Reading\n\n- ! Read in order, lazy load:\n  1. `./xbrief/active/` -- scope xBRIEFs for work items to build (required)\n  2. `./xbrief/PROJECT-DEFINITION.xbrief.json` -- project identity, tech stack, architecture\n  3. `./.planning/codebase/MAP.md` -- generated codebase orientation projection, if present (advisory)\n  4. USER.md at the platform-appropriate path (see Platform Detection) -- Personal section is highest precedence; Defaults are fallback\n  5. `deft/main.md` -- framework guidelines\n  6. `deft/coding/coding.md` -- coding standards\n  7. `deft/coding/testing.md` -- testing requirements\n  8. `deft/coding/toolchain.md` -- toolchain validation rules\n  9. `deft/languages/{language}.md` -- only for languages this project uses\n- ~ If the MAP is absent or may be stale and the current scope needs broad codebase orientation, run `task codebase:map` and `task verify:codebase-map-fresh` when those commands resolve. Treat absence/staleness as advisory unless the task edits `plan.architecture.codeStructure`, a configured provider artifact, or the generated MAP itself.\n- ! Treat `plan.architecture.codeStructure` and selected provider artifacts as authoritative. The MAP is a generated projection.\n- ⊗ Read all language/interface/tool files upfront\n- ⊗ Hand-edit `.planning/codebase/MAP.md` or block unrelated implementation solely because the MAP is stale or absent\n\n## Rule Precedence\n\n```\nUSER.md Personal                  <- HIGHEST (name, custom rules -- always wins)\nPROJECT-DEFINITION.xbrief.json   <- Project-specific (tech stack, architecture, config)\nUSER.md Defaults                  <- Fallback defaults (used when PROJECT-DEFINITION doesn't specify)\n{language}.md                     <- Language standards\ncoding.md                         <- General coding\nmain.md                           <- Framework defaults\nScope xBRIEFs                     <- LOWEST\n```\n\n- ! USER.md Personal section always wins over any other file\n- ! For project-scoped settings, PROJECT-DEFINITION.xbrief.json overrides USER.md Defaults\n\n## Change Lifecycle Gate\n\n! Before any implementation that touches 3+ files, verify that a `/deft:change <name>` proposal exists and has been confirmed by the user:\n\n- ! Check `history/changes/` for an active `proposal.xbrief.json` matching this work\n- ! If no proposal exists: propose `/deft:change <name>` and present the change name for explicit confirmation (e.g. \"Confirm? yes/no\")\n- ! The user must reply with an affirmative (`yes`, `confirmed`, `approve`) — a general 'proceed', 'do it', or 'go ahead' does NOT satisfy this gate\n- ? For solo projects: this gate is RECOMMENDED but not mandatory for changes fully covered by `task check`; it remains mandatory for cross-cutting, architectural, or high-risk changes\n- ⊗ Skip this gate because the user has already said \"proceed\" or \"go ahead\"\n\n## Build Process\n\nAll xBRIEFs (including those read from `xbrief/active/` and any new xBRIEFs this skill emits) MUST use `\"xBRIEFInfo\": { \"version\": \"0.6\" }`. The validator rejects any other version (see [`../../conventions/references.md`](../../conventions/references.md)).\n\n### Step 1: Understand the Scope\n\n- ! Read story xBRIEFs from `xbrief/active/` and `PROJECT-DEFINITION.xbrief.json`\n- ! Identify phases, dependencies, starting point from scope xBRIEF acceptance criteria\n- ~ Use `.planning/codebase/MAP.md`, when present, to orient broad codebase scanning. If the MAP conflicts with current code or canonical metadata, surface the drift and trust `plan.architecture.codeStructure` / provider artifacts plus the working tree over generated prose.\n- ! When scanning the existing codebase during scope understanding, MUST surface any contradicting patterns (two error-handling shapes, two state-management approaches, two naming conventions, etc.) before implementation begins -- apply `coding/hygiene.md` `## Surface Conflicts: Pick One, Explain, Flag the Other (#1005)` and choose ONE pattern (more recent OR more tested), explain the choice in the scope summary, and flag the other for cleanup\n- ⊗ Begin implementation against an averaged blend of two contradicting patterns -- \"average code that satisfies both rules is the worst code\" (#1005)\n- ! Present brief summary to user:\n\n> \"Here's what I see: {N} story xBRIEFs in active/. I'll start with {name}. Ready?\"\n\n### Step 2: Verify Toolchain\n\n- ! Before any implementation, verify all tools required by this project are installed and functional — see `deft/coding/toolchain.md` for full rules\n- ! At minimum: confirm task runner (`task --version`), language compiler/runtime, and platform SDK (if applicable) are available\n- ! If any required tool is missing, stop and report — do not proceed to Step 3\n- ⊗ Assume tools are available because the spec references them\n\n### Gate throughput — iteration fast lane vs merge chokepoint (#1704)\n\n> **Invariant:** every change MUST pass the full gate at least once before merge. Iteration MAY use a cheaper proxy; the merge chokepoint MUST NOT be skipped.\n\n- ! **Iteration lane (agents + humans):** during implementation commits, use affected/static gates — targeted tests on changed paths (`vitest run --coverage <paths>` or project equivalent), static `verify:*` gates relevant to touched files, and `task coverage:hotspots` / `task verify:forward-coverage` — NOT full `task check` on every commit.\n- ! **Merge chokepoint:** run full `task check` (or `task check:merge` in the framework source repo) once before push/PR and again when CI merge gate runs. Pre-PR skill exit and review-cycle fix batches still require a green full gate.\n- ! **Escape-rate safety (#1703 Tier-1):** before tightening fast-lane defaults fleet-wide, consult `#1703` measurement — `task eval:health` (Tier 0) and Tier-1 session telemetry (`helped/crud-metrics.jsonl` via instrumented CRUD / workflow metrics). Do NOT invent a separate fast-lane escape-rate surface (#1704 LockedDecisions).\n- ~ **In-engine incrementality (#1713):** content-hash task cache and runner-delegated affected selection are sibling work — not required for this policy face.\n- ⊗ Run full `task check` on every iteration commit when a cheaper proxy suffices — reserve the full gate for PR/merge (#1704).\n- ⊗ Skip the merge chokepoint because the iteration lane passed — the fast lane is convenience only.\n\n**Cost model (swarm-heavy path):** moves from roughly `O(commits × full-gate)` toward `O(merges × full-gate) + O(iterations × cheap-proxy)` when workers iterate with affected/static gates and run full `task check` only at PR/merge.\n\n### Dual stop — multi-iteration implement and pre-PR loops (#2442)\n\nMulti-iteration implement-fix and pre-PR polish loops MUST carry **both** a success stop and a failure/budget stop (`main.md` `## Dual Stop Rule (#2442)`). Single-turn edits and one-shot probes are exempt.\n\n**Defaults for this skill (override only with an explicit operator envelope or xBRIEF field):**\n\n| Loop class | Success stop | Default failure stop |\n|------------|--------------|----------------------|\n| Implement / quality fix (tests, lint, typecheck, coverage, AC) | Affected/static gates green for the change; AC met | **max 5** fix iterations **or** **3** consecutive identical outcomes (same failing command + same primary error class) with no material code/config change |\n| Pre-PR polish (`deft-directive-pre-pr` Read-Write-Lint-Diff) | Full pass with zero further edits | **max 3** polish passes **or** **2** consecutive no-diff / same-diff outcomes |\n| Full `task check` re-run after a red merge chokepoint | `task check` green | Counts toward the implement/quality fix envelope above (do not open a separate unbounded check-retry loop) |\n\n**On failure stop:**\n\n- ! Halt the loop. Surface an **operator-visible halt report** with: (1) iterations attempted and which stop fired (max-iter / no-progress / budget), (2) commands and primary failure fingerprints tried, (3) what is still red or missing, (4) the human decision needed (unblock dependency, rescope AC, waive with audit, abandon).\n- ! Prefer a structured `BLOCKED:` terminal (preamble §11 / #2843) when exiting a drive-to:merge-ready or parent-dispatched unit early because the envelope is exhausted.\n- ⊗ Continue \"one more fix\" after the envelope is exhausted.\n- ⊗ Reset the counter by opening a new commit, rewording the same change, or swapping workers while the same failure class remains.\n\n\n### Budget-aware effort - bank the pass before deepening (#3266)\n\nWhen a hard turn or cost budget is detectable (session:start `effort_budget` / env `DEFT_MAX_TURNS` / `DEFT_MAX_BUDGET` / host descriptor #1461), size effort to the **stated** acceptance bar first. This is the success-side analog of dual-stop (#2442): dual-stop stops thrash on failure; bank-the-pass stops budget exhaustion on over-deepening.\n\n- ! At implement start, read the session effort-budget signal (`task session:start` lines or JSON `effort_budget`, or env). When `posture=hard-capped`, treat the run as budget-constrained.\n- ! **Bank the pass first:** satisfy stated acceptance criteria (xBRIEF items / issue AC / official checker) and produce the passing artifact **before** any self-imposed deeper verification suite that exceeds the stated bar.\n- ! Only with **remaining** budget after the stated pass, extend verification depth. Never deepen past the point where a found defect could not also be fixed within budget (default reserve: enough turns/cost for one fix batch).\n- ! Self-verification scope scales with remaining budget - prefer the official/stated checks under a tight cap.\n- ! When deepening is skipped for budget, MUST say so in the run summary / handoff (`deepening_skipped=true` + reason) - fail-loud (#1006). Use `formatDeepeningSkippedNote` semantics from `packages/core/src/session/effort-budget.ts`.\n- ~ When no hard budget is detected (`posture=unbounded`), normal dual-stop defaults still apply; bank-the-pass is optional discipline, not a license to skip stated AC.\n- ⊗ Exhaust the turn/cost budget on self-imposed gold-plating after the stated bar is already within reach (#3266).\n- ⊗ Silently skip deepening without naming it, or silently gold-plate under a hard cap (#1006 / #3266).\n- ⊗ Treat bank-the-pass as permission to ship without meeting stated AC - stated AC remains the success stop.\n\nCore helper: `packages/core/src/session/effort-budget.ts` (`detectHardEffortBudget`, `recommendVerificationDepth`). Composes #2442, #1581, #3214, #1006.\n**Enforcement note:** skill defaults are behavioral. Durable delivery/acceptance circuit-breaker: **#3143** `packages/core/src/delivery-attempt/` (`evaluatePreDispatch`, `.deft/delivery-attempts/`). Docs: `docs/delivery-attempt.md`. Route delivery/acceptance automatic retries through that gate; do not invent a parallel ledger in this skill.\n\n### AC-pass banking checkpoint - finalize on green (#3285)\n\nSharpens #3266: the **first** moment stated/official acceptance criteria pass is a **banking checkpoint**, not a license to keep spending the turn budget on self-imposed depth.\n\n- ! When stated acceptance criteria first pass (`task verify:ac` / product-first done-gate #3284 / official checker), the **next** action is **FINALIZE**: checkpoint-commit the green state and record the bank (durable under `.deft/ac-pass-banks/`; optional run-summary line when `DEFT_RUN_SUMMARY_PATH` is set).\n- ! **Deepening after the bank requires surplus budget.** Self-imposed extra verification, refactors, or polish are permitted only when remaining budget meets `plan.policy.acPassBanking.surplusThreshold` (default **0.2** = 20% of max turns/cost still remaining) **and** the absolute reserve from #3266. Env override: `DEFT_AC_PASS_SURPLUS_THRESHOLD`.\n- ! Deepening, when allowed, happens **on top of** the committed checkpoint so a failed experiment can revert to banked green.\n- ! **Post-bank discoveries are reported, not chased** when surplus is insufficient: file a note/issue in the deliverable for out-of-scope defects unless they **regress stated AC** (then fix-regression). Finding beyond the bar is a win; thrashing a dying budget into a zero is the failure mode this rule closes.\n- ! When surplus is insufficient, ship the banked state and fail-loud (`deepening_skipped=true` + surplus reason) via `evaluateAcPassBanking` / `formatDeepeningSkippedNote` semantics.\n- ~ When no hard budget is detected, dual-stop still applies; bank-on-first-AC-pass remains good discipline but is not a hard surplus gate.\n- ⊗ Convert a banked official pass into a scored failure by chasing post-bank polish until the turn budget dies (#3285).\n- ⊗ Start post-bank deepening without a finalize checkpoint when a hard budget is active (#3285).\n- ⊗ Chase out-of-scope post-bank findings when surplus is below threshold (#3285).\n\nCore helpers: `packages/core/src/session/ac-pass-banking.ts` (`evaluateAcPassBanking`, `bankAcPass`, `decidePostBankFinding`, `simulateSurplusInsufficientRun`); policy: `packages/core/src/policy/ac-pass-banking.ts` (`plan.policy.acPassBanking`). Composes #3266, #3284, #3282 (optional bank-event JSONL), #1006.\n\n## Step 3: Build Phase by Phase\n\nFor each phase:\n\n1. ! **Scaffold** — file structure, dependencies, config\n2. ! **Test first** — write tests before implementation (TDD)\n3. ! **Implement** — make tests pass, following deft coding standards\n4. ! **Verify (iteration lane)** — run affected/static gates per `#1704` fast lane above; fix failures before checkpoint commits\n5. ! **Origin sync** — when this phase materially changed an origin-linked scope xBRIEF (`plan.references` includes `x-xbrief/github-issue`), run `task issue:sync-from-xbrief -- <path>` (or `--dry-run` to preview) so the linked GitHub issue receives a sync comment; if skipped, document why in the PR or session notes (#2540)\n6. ! **Checkpoint** — tell user what's done, what's next\n\n- ⊗ Move to next phase until current phase passes all checks\n\n### Step 4: Quality Gates\n\nAfter EVERY phase (iteration lane — #1704):\n\n```bash\nvitest run --coverage <changed-paths>   # or project test runner on touched modules\ntask coverage:hotspots                  # branch headroom before merge\ntask verify:forward-coverage            # new-source coverage (#1310)\n```\n\nBefore PR / phase handoff (merge chokepoint):\n\n```bash\ntask check          # Full gate — format, lint, typecheck, tests, coverage, verify:*\ntask test:coverage  # >=85% or PROJECT-DEFINITION.xbrief.json override\n```\n\n- ! Phase checkpoint commits MAY use the iteration lane; phase is NOT done for PR handoff until full `task check` passes at the merge chokepoint\n- ⊗ Skip quality gates or claim they passed without running\n- ⊗ Treat iteration-lane green as merge-ready without full `task check`\n- ! **Multi-scope batch (#3012):** when implementing an approved multi-scope pin/cohort, reserve full `task check` for end-of-batch (or after last scope) unless the last full check failed — then re-run on the fix loop. Do not run full check after every intermediate scope.\n- ⊗ Re-run full install/session ceremony after offline seed when ritual is already complete (#3010) — use `session:ready` for recovery only.\n\n\n## Product-first done-gate (#3284) / literal AC (#3267)\n\nAt intake, capture the task statement's **exact** acceptance commands as executable AC (`plan.acceptance.commands` + #3267 `literal_acceptance_commands`). Empty is allowed only with `none_stated: true` (ladder: stated → derived → project_floor). Before declaring done, run them **verbatim** — same paths, same flags, same working directory. Self-chosen verification is supplementary, never a substitute. Extends #973. `task check` runs `verify:ac` **first** (fail-fast); hygiene is second and may become advisory under pressure. Rapid ceremony = **AC-only**.\n\n- ! When reading the active scope xBRIEF / issue body at story start, capture stated shell acceptance commands into `plan.acceptance.commands` (issue:ingest stamps this + the #3267 ledger automatically). Do not paraphrase.\n- ! Before claiming phase or story done (and before merge-chokepoint PR handoff), run:\n```\ntask verify:ac -- <active-story-path>\n```\n  Exit 0 = pass or none stated with valid marker; exit 1 = a stated command failed; exit 2 = config. (`verify:literal-ac` is the #3267 mechanism alias.)\n- ! Quote the literal invocations and their outputs in the completion note when commands were stated.\n- ⊗ Substitute a self-chosen approximation (`pnpm test` when the statement said `pnpm exec vitest run packages/core/src`) for the stated command.\n- ⊗ Skip this gate because ceremony dial is rapid/minimal — rapid's positive content is exactly this check (#3284).\n- ⊗ Leave `plan.acceptance.commands` empty without `none_stated: true` — absence must be an explicit decision.\n\n## Product-oracle gate integrity (#3322 / #3156)\n\nA red product verification may be resolved only by a product change or an independently re-derived oracle (both sides rebuilt from scratch, different method). In-place repair of the failing comparison then pass is not a pass — it is an unresolved discrepancy.\n\n- ! When a product oracle is red, resolve it by changing the product or by independently re-deriving the oracle, and record `independent_rederivation` on the run-summary `verification` event.\n- ! Emit a run-summary verification event `{check_id, method_fingerprint, outcome}` for each product-oracle attempt when `DEFT_RUN_SUMMARY_PATH` is set. `fail` then a different `method_fingerprint` then `pass` on one check id is machine-flagged.\n- ! `task verify:ac` treats comparison-method mutation as unresolved (exit non-zero) unless independent re-derivation is recorded. Lead the done report with any unresolved discrepancy (#1006).\n- ⊗ Self-adjudicate a red product oracle by editing the comparison (reference file, diff invocation, one-sided regenerate) and shipping the new pass as success.\n\n## Operator-log hygiene (lazy-load, #1940)\n\nWhen the story touches **operator-facing** services (dashboards, multi-process\nworkers, WARN/ERROR operators triage):\n\n- ~ SHOULD load `patterns/operator-log-hygiene.md` and apply the copy-paste\n  checklist in `docs/operator-log-hygiene-checklist.md` to story AC or probe\n  locked decisions before claiming logging done\n- ⊗ MUST NOT treat this as Product Insights (#2603) or LLM-call telemetry\n  (#481) — those are different lanes\n- ⊗ MUST NOT assume core `deft check` enforces a log schema by default —\n  consumer-owned shape; optional pack stub under\n  `docs/operator-log-hygiene-consumer-pack-stub.md`\n\nDiscovery keywords: operator log, operator-facing logs, observability checklist\n— also indexed in `REFERENCES.md`.\n\n## Goal-gate determinism (lazy-load, #852)\n\nWhen authoring or tightening story acceptance criteria, quality gates, or skill\nsteps during build:\n\n- ~ SHOULD load `patterns/goal-gate-determinism.md` — goals, AC, gates, exit,\n  scope, stop, and preserve are rigid; pure execution path is flexible guidance\n- ⊗ MUST NOT treat \"all process steps done\" as verification — outcomes and\n  gates own \"done\" (see also `verification/verification.md` and Fail Loud #1006)\n\nDiscovery keywords: goal-gate-determinism, rigid goals flexible path — also\nindexed in `REFERENCES.md`.\n\n## Coding Standards (Summary)\n\nRead full files when you need detail:\n\n- ! TDD: write tests first — implementation incomplete without passing tests\n- ! Coverage: ≥85% lines, functions, branches, statements\n- ~ Files: stay small; line counts live in the file-size-thresholds policy module (review trigger, not a hard cap; #1488 / #3424)\n- ~ Naming: hyphens for filenames unless language idiom dictates otherwise\n- ! Contracts first: define interfaces/types before implementation\n- ! Secrets: in `secrets/` dir with `.example` templates; ⊗ secrets in code\n- ! Commits: Conventional Commits format; ! use iteration fast lane before checkpoint commits; ! run full `task check` at PR/merge chokepoint only (#1704)\n\nSee `deft/coding/coding.md` and `deft/coding/testing.md` for full rules.\n\n## Pre-Commit File Review\n\n! Before every commit, re-read ALL modified files and explicitly check for:\n\n1. ! **Encoding errors** -- em-dashes corrupted to replacement characters, BOM artifacts, mojibake from round-trip read/write\n2. ! **Unintended duplication** -- accidental double entries in CHANGELOG.md, scope xBRIEF files, or structured data files\n3. ! **Structural issues** -- malformed CHANGELOG entries, broken table rows, mismatched index entries, invalid JSON/YAML\n4. ! **Semantic accuracy** -- verify that counts, claims, and summaries in CHANGELOG entries and ROADMAP changelog lines match the actual data in the commit (e.g. \"triaged 4 issues\" must match the number actually triaged, issue numbers cited must match the issues actually added)\n5. ! **Semantic contradictions** -- when adding a `!` or `⊗` rule that prohibits a specific command, pattern, or behavior, search the same file for any `~`, `≉`, or prose that recommends or permits the same command/pattern -- resolve all contradictions in the same commit before pushing\n6. ! **Strength duplicates** -- when strengthening a rule (e.g. upgrading `~` to `!`), grep for the term in the full file and verify no weaker-strength duplicate remains\n7. ! **Forward test coverage** -- for each new source file in this PR (`scripts/`, `src/`, `cmd/`, `*.py`, `*.go`), verify a corresponding test file exists in the same PR; running existing tests is not sufficient for new code\n\n⊗ Commit without re-reading all modified files first.\n\n## Commit Strategy\n\n- ! Default to one story per branch/PR. Batching multiple stories in one branch requires explicit operator approval and a short rationale.\n- ! Create a checkpoint commit after each completed story before beginning another story.\n- ! Use iteration fast lane before checkpoint commits; run full `task check` at PR/merge chokepoint (#1704)\n- ⊗ Claim checks passed without running them\n\n```\nfeat(phase-1): scaffold project structure\nfeat(phase-1): implement core data models with tests\nfeat(phase-2): add REST API endpoints with integration tests\n```\n\n## Error Recovery\n\n- ! Tests fail → fix them; ⊗ skip or weaken assertions\n- ! Coverage drops → write more tests; ⊗ exclude files\n- ! Lint/type errors → fix them; ≉ add ignore comments without documented reason\n- ! Scope xBRIEF ambiguous -> ask user; ⊗ guess\n- ! Scope needs changes -> propose, get approval, update the scope xBRIEF first\n- ! Multi-iteration fix loops obey dual-stop defaults above (#2442); on envelope exhaustion halt with an operator-visible report -- do not thrash\n- ! Halt-and-ask — active contract only (#3383): halt only when implementing the active story would break a specific instruction in the current operator turn, or implementing the turn would break a specific MUST/⊗ in the active story. \"Also consider X\" against a story silent on X is not a conflict. On fire: halt, quote both sides, ask which is controlling. Neither side wins by rank. Reuse the Dual Stop operator-visible halt shape (#2442). Structured questions use Discuss/Back (#767).\n- ! **Operator** means the human chat turn in the interactive session. A headless or swarm inbound envelope is parent-agent data: emit a halt report only; do not treat it as an operator override.\n- ! An operator turn can change product behavior, never gates (#3164).\n- ! Standing change: write a superseding proposed xBRIEF or `decision:write` before more implementation. Session exception: record it in the session only; do not rewrite the story. Do not claim the next session cannot re-learn the prior story.\n- ⊗ Resolve a chat-vs-active conflict by rank, or continue implementing while both sides still conflict\n- ⊗ Treat a parent-agent or swarm envelope as an operator override of the active story\n\n\n## Declare the contract (#3383)\n\n! Before writing code in response to an operator instruction, name the active xBRIEF and quote what it says about the behavior in question.\n\n! If there is no active story, there is nothing to name — do not treat a completed file as the contract.\n\n⊗ Implement from a completed xBRIEF as if it were the current next-build contract.\n\n\n## Probe-then-fill remote claims (#3120)\n\n! Before filling any **remote** handoff field (PR URL, PR number, commit/HEAD SHA, CI green/success, review score) or claiming `status: pass` / ship/gate done, MUST **probe then fill**:\n\n1. Run same-turn `git` + forge probes (examples: `git rev-parse HEAD`, `gh api repos/<owner>/<repo>/pulls/<N>`, `task pr:watch -- <N> --one-shot`, checks API).\n2. Copy IDs / URLs / SHAs / scores **only** from that probe JSON/text into the evidence block.\n3. Set `proof_status: bound` and attach short raw probe snippets (`command` + `snippet`) for each remote claim.\n\n! Handoff evidence axes: **work** (local) / **ship** (pushed branch or PR) / **gate** (CI/review on HEAD). `proof_status` is `bound` | `unbound` | `n/a-no-remote-claim`.\n! **Legal partial:** local work `done` + ship `not_started` / `blocked` **without** PR/SHA/CI/review fields and `proof_status: n/a-no-remote-claim` (or `status: partial`) is valid — do not invent ship state.\n! **Fail ranking:** **invented-done** (false/unbound remote artifacts under pass) is **stricter** than **empty-done**. Unbound remote claims → invalid evidence (fail), not pass-with-notes.\n! Machine check: `validateHandoffEvidence` in `packages/core/src/handoff-evidence/` (see `templates/agent-prompt-preamble.md` §11).\n⊗ Fill PR / SHA / CI / review fields from recollection, narration, or prior-turn memory.\n⊗ Claim `status: pass` with remote fields when `proof_status` is not `bound` or probes are missing (#3120).\n\n## Completion\n\n- ! When all phases pass and `task check` is green, run `task scope:complete -- <active-story-path>` only as the post-merge scope lifecycle in `templates/agent-prompt-preamble.md` §9 (AGENTS.md `#2321`) specifies for `drive-to: merge-ready` versus `stop-at: pr-open`. That section is the single statement of the ordering; this skill does not restate it.\n\n> \"The project is built and all quality checks pass. Describe any new features you'd like to add — I'll follow the deft standards we've set up.\"\n\n\n## Significant decision log (#1396)\n\n! When this scope makes a **significant** choice (architecture, product behavior, security, public/private boundary, data model, runtime topology, hard-to-reverse process), record it with `task decision:write` (or `--body-file` for multi-line fields) so later agents load rationale without inventing it.\n\n~ Prefer attaching with `--scope <active-xbrief>` when the decision is bound to this story; use standalone `xbrief/decisions/` for cross-cutting / multi-scope process choices.\n\n~ Before claiming a process/architecture path was 'already decided', run `task decision:list -- --query <topic>` (or `--issue N`).\n\n⊗ Require a decision record for every trivial scope or routine fix.\n⊗ Merge lessons (#1513) into decision records, or replace ADRs under `docs/decisions/ADR-*.md`.\n\nDocs: `docs/decision-log.md` · `xbrief/decisions/README.md`.\n\n## Anti-Patterns\n\n- ⊗ Skip tests or write them after implementation\n- ⊗ Ignore `task check` failures\n- ⊗ Implement things not in scope xBRIEF without asking\n- ⊗ Read every deft file upfront\n- ⊗ Move to next phase before current passes checks\n- ⊗ Make commits without running iteration-lane validation; ⊗ skip full `task check` at PR/merge chokepoint (#1704)\n- ⊗ Proceed without USER.md -- always run the USER.md Gate first\n- ⊗ Re-run `directive init`, cold `session:start`, migrate, or re-copy pin scopes after offline seed when ritual is already complete (#3010)\n- ⊗ Run full `task check` after every intermediate scope of an approved multi-scope batch when the last merge-chokepoint check was green (#3012)\n- ⊗ Promote scopes one-by-one for a known multi-scope pin when `scope:promote --batch` would stage them in one turn (#3011)\n\n- ⊗ Spawn an implementation agent or invoke a code-writing tool against a xBRIEF that has not passed `task xbrief:preflight` (which wraps `scripts/preflight_implementation.py`) -- always run the Step 0 Implementation Preflight (#810) first; satisfy via `task xbrief:activate <path>`\n- ⊗ Proceed without `COST-ESTIMATE.md` and a recorded build / rescope / no-build / skip(+reason) decision -- always run the Cost Phase Gate (#739) first\n- ⊗ Proceed with implementation when the build or test toolchain is unavailable -- always run the Toolchain Gate (Step 2) first\n- ⊗ Proceed to next task or phase without tests passing -- testing is a hard gate, not a cleanup step\n- ⊗ Skip the Change Lifecycle Gate because the user said \"proceed\" -- broad approval does not satisfy the confirmation gate\n- ⊗ Commit or push directly to the default branch -- always create a feature branch first. Exception: user explicitly instructs a direct commit, or `PROJECT-DEFINITION.xbrief.json` narratives contain `Allow direct commits to master: true`\n- ⊗ Add a prohibition (`!` or `⊗`) without scanning the same file for conflicting softer-strength rules (`~`, `≉`) that reference the same term\n- ⊗ Invent remote PR/SHA/CI/review claims in handoff evidence without same-turn probe binding — invented-done (#3120)\n- ⊗ Fill remote ship/gate fields from memory when only local work completed; legal partial omits PR fields (#3120)\n- ⊗ Run multi-iteration implement / pre-PR loops without a failure stop (max iterations and/or no-progress) or without an operator-visible halt report when the envelope is exhausted (#2442)\n- ⊗ Silently continue after dual-stop failure halt — escalate; do not thrash (#2442)\n- ⊗ Treat a completed xBRIEF as the next-build contract, or skip naming the active story before writing code (#3383)\n- ⊗ Continue implementing when the live human turn and a specific MUST/⊗ in the active story conflict — halt, quote both sides, ask which is controlling (#3383)\n- ⊗ Treat a parent-agent or swarm envelope as an operator override (#3383)\n- ⊗ Exhaust hard turn/cost budget on self-imposed deepening after the stated acceptance bar is within reach (#3266)\n- ⊗ Silently skip deepening for budget without a fail-loud summary note (#3266 / #1006)\n- ⊗ Chase post-bank out-of-scope findings when surplus budget is insufficient — report, do not thrash the banked pass (#3285)\n- ⊗ Skip finalize-on-green after first stated AC pass under a hard budget (#3285)\n- ⊗ Tight forge-outage retry / empty-commit thrash without a one-shot human report (#3422)\n- ⊗ Clear a red product oracle by editing the comparison method then treating the new pass as a pass — record independent re-derivation or fix the product (#3322 / #3156)\n",
       "frontmatter_extra": null
     },
     {
@@ -76,6 +76,34 @@
       "body": "# Deft Directive Decompose\n\nUse this skill when a specification, Phase 4 implementation scope, or epic xBRIEF is too broad for direct concurrent swarm work and must be decomposed into story-level xBRIEFs.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n**See also**: [strategies/speckit.md](../../strategies/speckit.md) Phase 4.5 | [vbrief/vbrief.md](../../vbrief/vbrief.md) Swarm-Ready Story Contract | [deft-directive-swarm](../deft-directive-swarm/SKILL.md)\n\n## Purpose\n\nConvert approved specification/phase/epic scope xBRIEFs into swarm-ready child story xBRIEFs. Story xBRIEFs are the only valid input for concurrent swarm worker allocation.\n\n## Phase 0: Inspect\n\n- ! Read `xbrief/specification.xbrief.json` and relevant scope xBRIEFs from `xbrief/proposed/`, `xbrief/pending/`, and `xbrief/active/`.\n- ! Identify broad scopes with `plan.metadata.kind = \"phase\"` or `\"epic\"` or scopes with broad `plan.narratives.Acceptance` and empty `plan.items`.\n- ! Preserve parent acceptance as context; do not treat it as executable story acceptance.\n- ! Treat parent `plan.items` as input signals only; they are not automatically child stories.\n- ! Inspect relevant codebase paths before drafting file scope so stories reflect real product/code boundaries, not only parent scope prose.\n- ! Identify requirement traces, likely file scope, verification commands, outputs/evidence, dependencies, and conflict groups.\n- ⊗ Allocate a broad phase/epic scope to concurrent workers during this skill.\n\n## Phase 1: Draft\n\n- ! Draft a decomposition JSON proposal with child stories only; do not write child xBRIEFs yet.\n- ! Treat the draft JSON as a temporary proposal artifact, not a xBRIEF.\n- ! Write draft proposals under `xbrief/.triage-cache/decompositions/`, using a parent-derived slug such as `xbrief/.triage-cache/decompositions/ip001-auth.json`.\n- ! Derive `<parent-slug>` from the parent xBRIEF filename by removing `.xbrief.json` and any leading `YYYY-MM-DD-` date prefix; for example, `xbrief/pending/2026-05-12-ip001-auth.xbrief.json` uses `ip001-auth`, while `xbrief/pending/feature-xyz.xbrief.json` uses `feature-xyz`.\n- ⊗ Agents MUST NOT leave decomposition draft JSON files at the workspace root.\n- ! Each story MUST include `id`, `title`, `Description`, `ImplementationPlan`, `UserStory`, executable `items` or `acceptance`, `traces` or explicit trace justification, `swarm.file_scope`, `swarm.verify_commands`, `swarm.expected_outputs`, `swarm.depends_on`, `swarm.conflict_group`, `swarm.size`, `swarm.file_scope_confidence`, and `swarm.model_tier`.\n- ! `Description` MUST provide at least two concrete sentences explaining the user/product behavior, boundaries, and why this story is independently buildable.\n- ! `ImplementationPlan` MUST provide at least two concrete implementation steps that identify the expected code path, state/data changes, and test/evidence approach.\n- ! `UserStory` MUST use the exact product-story shape `As a <role>, I want <capability>, so that <outcome>.`.\n- ! Each ready story MUST have 2-5 concrete acceptance criteria unless `swarm.acceptance_criteria_justification` explains the exception.\n- ! Acceptance criteria MUST be observable behavior, preferably Given/When/Then or equivalent testable product behavior.\n- ⊗ Mark a story ready when acceptance says only \"to refine from parent scope\", duplicates the title/description, is placeholder text, or is vague docs-only acceptance.\n- ⊗ Mark a story ready with broad write scope such as `backend/**`, `frontend/**`, `docs/**`, `xbrief/**`, or any other directory glob.\n- ⊗ Mark a story ready when verification is only generic validation such as `task check`.\n- ⊗ Mark a story ready with `parallel_safe: false` or `file_scope_confidence: low`; use `readiness: sequential` or `readiness: needs_refinement` instead.\n- ! Model dependencies as story IDs and ensure they form a DAG.\n- ~ Draft sequential-safe or low-confidence work as `readiness: sequential` or `readiness: needs_refinement`; it is not eligible for concurrent allocation.\n- ⊗ Use deprecated `subItems` in newly drafted story items; use `items`.\n\n## Phase 2: Approval\n\n- ! Present the decomposition draft to the user before writing files.\n- ! Ask for explicit approval to apply the draft.\n- ! If the user requests changes, revise the draft and re-present it.\n- ! After explicit approval, run `task scope:decompose ... --check`, then apply without `--check`.\n- ? Run `task scope:decompose ... --check` before explicit approval only to validate a draft without writing files.\n- ⊗ Apply `task scope:decompose` without `--check` before explicit approval.\n\n## Phase 3: Apply\n\n- ! Validate the approved draft first:\n\n```bash\ntask scope:decompose -- xbrief/pending/2026-05-12-ip001-auth.xbrief.json --draft xbrief/.triage-cache/decompositions/ip001-auth.json --check\n```\n\n- ! Apply the approved draft:\n\n```bash\ntask scope:decompose -- xbrief/pending/2026-05-12-ip001-auth.xbrief.json --draft xbrief/.triage-cache/decompositions/ip001-auth.json\n```\n\nThe command creates generated child story xBRIEFs as lifecycle artifacts, defaulting to `xbrief/pending/`. It preserves origin/provenance references, sets each child `planRef` to the parent, updates parent references to include the children, rejects dependency cycles, and rejects ready stories missing executable acceptance, user-story shape, concrete acceptance, narrow file scope, focused verify commands, or traces.\n\n## Phase 4: Pending Readiness\n\n- ! Run readiness against the generated pending child story paths after decomposition:\n\n```bash\ntask swarm:readiness -- xbrief/pending/<child-story-1>.xbrief.json xbrief/pending/<child-story-2>.xbrief.json\n```\n\n- ! Treat this as a dry readiness review before activation; do not allocate workers from pending paths.\n- ! Route blocked or overlapping stories back to Phase 1 for draft refinement.\n- ! Leave lifecycle promotion/activation to the existing approved flow (`task scope:promote`, `task scope:activate`, and the swarm skill lifecycle bridge).\n- ⊗ Promote or activate child stories solely because decomposition succeeded.\n\n## Exit\n\ndeft-directive-decompose complete -- exiting skill. Next, activate the approved child story xBRIEFs through the existing lifecycle flow, then run `skills/deft-directive-swarm/SKILL.md` for concurrent allocation.\n",
       "frontmatter_extra": null
     },
+    {
+      "id": "deft-directive-design-critique",
+      "description": "Thin router for the design-critique motion: triggers and pointer stops into the contract, including the operator-gated loop. Use when the operator asks for a design critique, design-critique, critique panel, or mechanism-shaped triage. Do NOT trigger on ordinary implement, build, or swarm work.",
+      "triggers": [
+        "design critique",
+        "design-critique",
+        "critique panel",
+        "mechanism-shaped triage"
+      ],
+      "path": "skills/deft-directive-design-critique/SKILL.md",
+      "version": "0.1",
+      "body": "# Design Critique\n\nThin router into the design-critique contract. Operator dispatches from the brief template.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n## When to Use\n\n- Operator asks for a design critique, a design-critique, a critique panel, or mechanism-shaped triage\n- ⊗ Ordinary implement, build, or swarm work\n\n## Stops\n\nNormative rules live in [`contracts/design-critique.md`](../../contracts/design-critique.md). Fill [`templates/design-critique-brief.md`](../../templates/design-critique-brief.md) and dispatch from there. Phase 1 gate: [`docs/decisions/ADR-005-design-critique-judgment-gate.md`](../../../docs/decisions/ADR-005-design-critique-judgment-gate.md). Parent-audit principle: [`docs/decisions/ADR-006-parent-side-substantiation.md`](../../../docs/decisions/ADR-006-parent-side-substantiation.md).\n\n1. Stop 1 — Gate\n2. Stop 2 — Variant selection\n3. Stop 3 — Critic envelope\n4. Stop 4 — Residual reiteration\n5. Stop 5 — Verified synthesis\n\nComment lead (model then role): Stop 3 — Critic envelope.\nOperator-gated loop. Successor lean. Parent-side substantiation. Operator verbs. Dual stop. Halt line. Bind after accepted synthesis.\nAfter critic post: posted successor lean, then verbs.\nAuto-stamp after operator confirm; not while same-round siblings outstanding.\nWalk / walk all. Auto-stamp when agents agree: Operator verbs.\nParent chip write: scm:issue:design-critique-chip.\n\nEach critic dispatch EXITs after posting.\n\n⊗ Auto-dispatch critics from this skill.\n⊗ Copy the variant table, synthesis rules, or other contract bodies into this skill.\n\n## EXIT\n\ndeft-directive-design-critique complete -- exiting skill. Next: fill the brief template and dispatch.\n",
+      "frontmatter_extra": "triggers:\n  - design critique\n  - design-critique\n  - critique panel\n  - mechanism-shaped triage"
+    },
+    {
+      "id": "deft-directive-issue-eval",
+      "description": "Thin router for Stage A issue evaluation: isolated origin/master validity, parent WIP census, named gitignored sink. Use when the operator asks to evaluate issues, run issue-eval, or triage:evaluate. Do NOT trigger on ordinary implement, build, swarm, or design-critique dispatch.",
+      "triggers": [
+        "issue-eval",
+        "issue eval",
+        "triage:evaluate",
+        "evaluate issues"
+      ],
+      "path": "skills/deft-directive-issue-eval/SKILL.md",
+      "version": "0.1",
+      "body": "# Issue Eval\n\nThin router into the issue-eval contract. Operator runs `task triage:evaluate`.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n## When to Use\n\n- Operator asks to evaluate issues, run issue-eval, or `triage:evaluate`\n- ⊗ Ordinary implement, build, swarm, or design-critique dispatch\n\n## Stops\n\nNormative rules live in [`contracts/issue-eval.md`](../../contracts/issue-eval.md).\n\n1. Split read sources\n2. Verdict sink\n3. Evaluator worktrees\n4. Value advice grammar\n5. No GitHub writes\n6. Fan-out\n\n⊗ Emit `design-critique: warranted | not warranted, because` from evaluation.\n⊗ Reuse `swarm:launch` until #3649.\n⊗ Write `xbrief/proposed/` or GitHub from this skill.\n\n## EXIT\n\ndeft-directive-issue-eval complete -- exiting skill. Next: run `task triage:evaluate`, then decide with existing `triage:*` verbs.\n",
+      "frontmatter_extra": "triggers:\n  - issue-eval\n  - issue eval\n  - triage:evaluate\n  - evaluate issues"
+    },
     {
       "id": "deft-directive-feedback",
       "description": "Batched session-end gap escalation for directive consumers. Collects friction/gap reports, drafts deduped framework-gap issues against deftai/directive, and files upstream only after explicit operator confirmation. Gated on plan.policy.valueFeedback upstreamPrompt.",
@@ -88,7 +116,7 @@
       ],
       "path": "skills/deft-directive-feedback/SKILL.md",
       "version": "0.1",
-      "body": "# Deft Directive Feedback -- gap escalation to upstream\n\nConversational batched flow for filing framework gaps discovered during consumer sessions. Mirrors the confirmation gate from `deft-directive-article-review` -- the agent drafts and dedups; the operator approves before any upstream issue is created.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n## When to Use\n\n- Session end when `friction:*` ledger signals or operator reports a directive shortfall\n- Operator says \"file this upstream\", \"report a framework gap\", or \"directive feedback\"\n- After enabling `plan.policy.valueFeedback.upstreamPrompt` during onboarding\n\n## Preconditions\n\n- ! Run only from a **consumer project** -- the filing path no-ops inside the directive maintainer repo\n- ! `plan.policy.valueFeedback.upstreamPrompt` MUST be ON (`task policy:show --field=valueFeedback`)\n- ⊗ File upstream issues without explicit operator confirmation\n- ⊗ Invoke when `valueFeedback.enabled` is OFF\n\n## Phase 1 -- Collect (batched)\n\n- ! Gather concrete gap reports from the session: what was expected, what happened, and minimal reproduction context\n- ! Batch multiple friction items into one upstream issue when they share a root cause; otherwise prepare separate drafts\n- ~ Prefer attributed phrasing (\"encoding gate blocked a valid file\") over vague quality claims\n\n## Phase 2 -- Draft + dedup\n\n- ! For each candidate report, run a dry draft:\n\n```bash\ntask feedback:file -- --summary \"<one-line summary>\" --context \"<session context>\" --expected \"<expected>\" --actual \"<actual>\" --notes \"<optional>\"\n```\n\n- ! Read the printed draft title/body with the operator before proceeding\n- ! If the command reports a duplicate open issue, STOP and link the existing issue instead of filing again\n- ⊗ Proceed past a duplicate-detection block without operator override\n\n## Phase 3 -- Confirm + file\n\n- ! Present the final draft and ask for explicit yes/no confirmation\n- ! Only after approval, re-run with `--confirm`:\n\n```bash\ntask feedback:file -- --summary \"<one-line summary>\" --context \"<session context>\" --expected \"<expected>\" --actual \"<actual>\" --confirm\n```\n\n- ! Print the filed issue URL to the operator\n- ⊗ Use `Closes`/`Fixes`/`Resolves` in the upstream body -- use `Refs #1709` only\n\n## Phase 4 -- Handoff\n\n- ~ Record the upstream issue URL in the session handoff or continue checkpoint if the operator tracks follow-ups locally\n- ~ Return to the prior workflow; gap escalation does not block story completion\n\n## Anti-Patterns\n\n- ⊗ Filing from the maintainer framework repo (consumer-only guard)\n- ⊗ Skipping dedup review when the command reports an existing open issue\n- ⊗ Treating `--confirm` as implicit from broad session approval -- require an explicit filing confirmation step\n",
+      "body": "# Deft Directive Feedback -- gap escalation to upstream\n\nConversational batched flow for filing framework gaps discovered during consumer sessions. Mirrors the confirmation gate from `deft-directive-article-review` -- the agent drafts and dedups; the operator approves before any upstream issue is created.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n## When to Use\n\n- Session end when `friction:*` ledger signals or operator reports a directive shortfall\n- Operator says \"file this upstream\", \"report a framework gap\", or \"directive feedback\"\n- After enabling `plan.policy.valueFeedback.upstreamPrompt` during onboarding\n\n## Preconditions\n\n- ! Run only from a **consumer project** -- the filing path no-ops inside the directive maintainer repo\n- ! `plan.policy.valueFeedback.upstreamPrompt` MUST be ON (`task policy:show --field=valueFeedback`)\n- ⊗ File upstream issues without explicit operator confirmation\n- ⊗ Invoke when `valueFeedback.enabled` is OFF\n\n## Phase 1 -- Collect (batched)\n\n- ! Gather concrete gap reports from the session: what was expected, what happened, and minimal reproduction context\n- ! Batch multiple friction items into one upstream issue when they share a root cause; otherwise prepare separate drafts\n- ~ Prefer attributed phrasing (\"encoding gate blocked a valid file\") over vague quality claims\n\n## Phase 1.5 -- Adoption-blocker judgment\n\n- ! Ask whether the gap blocks adoption. A gap blocks adoption when the consumer cannot complete an intended Directive flow and has no reasonable workaround.\n- ! When the answer is yes, collect the body evidence a privileged actor needs before applying `adoption-blocker`: affected consumer flow and version; documented alternatives attempted, or why they are not a reasonable workaround; observed recovery cost. Pass `--blocker` (and `--flow`, `--alternatives`, `--recovery-cost` when known) so the title carries `BLOCKER` and the body carries those sections.\n- ! When the answer is no or unknown, omit `--blocker`. Absence of the token does not mean \"not a blocker\" -- it means not classified.\n- ⊗ Apply or request the `adoption-blocker` ranking label from a consumer-authored title. The label is a privileged write after the body-evidence test.\n\n## Phase 2 -- Draft + dedup\n\n- ! For each candidate report, run a dry draft:\n\n```bash\ntask feedback:file -- --summary \"<one-line summary>\" --context \"<session context>\" --expected \"<expected>\" --actual \"<actual>\" --notes \"<optional>\" [--blocker --flow \"<flow and version>\" --alternatives \"<alts>\" --recovery-cost \"<cost>\"]\n```\n\n- ! Read the printed draft title/body with the operator before proceeding\n- ! If the command reports a duplicate open issue, STOP and link the existing issue instead of filing again\n- ⊗ Proceed past a duplicate-detection block without operator override\n\n## Phase 3 -- Confirm + file\n\n- ! Present the final draft and ask for explicit yes/no confirmation\n- ! Only after approval, re-run with `--confirm`:\n\n```bash\ntask feedback:file -- --summary \"<one-line summary>\" --context \"<session context>\" --expected \"<expected>\" --actual \"<actual>\" --confirm [--blocker]\n```\n\n- ! Print the filed issue URL to the operator\n- ⊗ Use `Closes`/`Fixes`/`Resolves` in the upstream body -- use `Refs #1709` only\n\n## Phase 4 -- Handoff\n\n- ~ Record the upstream issue URL in the session handoff or continue checkpoint if the operator tracks follow-ups locally\n- ~ Return to the prior workflow; gap escalation does not block story completion\n\n## Anti-Patterns\n\n- ⊗ Filing from the maintainer framework repo (consumer-only guard)\n- ⊗ Skipping dedup review when the command reports an existing open issue\n- ⊗ Treating `--confirm` as implicit from broad session approval -- require an explicit filing confirmation step\n- ⊗ Infer \"not a blocker\" from an unmarked report -- absence of `BLOCKER` means not classified\n- ⊗ Auto-apply `adoption-blocker` from a consumer-authored title\n",
       "frontmatter_extra": null
     },
     {
@@ -189,7 +217,7 @@
       ],
       "path": "skills/deft-directive-probe/SKILL.md",
       "version": "0.1",
-      "body": "# Deft Directive Probe\n\nStress-test a plan before committing to it — relentless interrogation until every branch of the decision tree is resolved.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n> Strategy reference: [strategies/probe.md](../../strategies/probe.md). Probe is adversarial discovery — it assumes the plan has holes and sets out to find them.\n\n## When to Use\n\n- ~ Before committing to any significant design decision or architecture choice\n- ~ When a plan has been drafted but not yet stress-tested\n- ! When the user explicitly asks to be probed or challenged on their plan\n- ? Skip when the path forward is unambiguous and small in scope\n\n## No-Artifact Guard (active until probe complete)\n\nWhile probe completion criteria (below) are NOT met:\n\n- ⊗ Write or update any xBRIEF file (`xbrief/proposed/`, `xbrief/active/`, plan items, narratives)\n- ⊗ Update `xbrief/plan.xbrief.json` or register probe artifacts\n- ⊗ Post GitHub completion comments, close issues, or open PRs on behalf of the probe session\n- ⊗ Produce probe output markdown files instead of the canonical xBRIEF contract\n\n! Read existing context and interrogate only — artifacts land in the Output phase after completion.\n\n## Workflow\n\n### Step 1: Establish the plan\n\n- ! Read whatever plan, design, or spec exists in the conversation context\n- ~ If no plan is in context, ask ONE question: \"What's the plan you want me to probe?\"\n- ~ If codebase context is relevant, explore it to answer what you can before asking\n- ⊗ Ask follow-up questions before reading available context\n\n### Step 2: Interrogate relentlessly\n\nWalk the decision tree depth-first. For each unresolved branch:\n\n- ! Ask **ONE** focused question per message\n- ! For each question, provide your recommended answer with brief reasoning\n- ! If the codebase can answer a question, explore it instead of asking the user\n- ~ Follow the thread — if an answer opens new branches, pursue them before moving on\n- ⊗ Ask multiple questions at once\n- ⊗ Present batched decision lists, numbered option menus, or multi-item checklists in a single turn\n- ⊗ Accept vague answers — push back: \"What does that mean concretely?\"\n- ⊗ Move to the next branch before the current one is fully resolved\n\n#### First-turn contract\n\n! The first user-facing probe turn after loading this skill MUST contain exactly **one** focused question plus your recommended answer — nothing else that asks the user to decide among multiple items.\n\n- ⊗ Open with a summary of every open branch, a decision matrix, or a list of questions\n- ⊗ Batch \"here are the areas we need to cover\" bullets that substitute for the single-question rule\n\n#### Question focus areas\n\n- ! **Assumptions** — \"This assumes X is guaranteed — is it?\"\n- ! **Edge cases** — \"What happens when Y is empty / null / at the limit?\"\n- ! **Dependencies** — \"This requires Z to exist — what if it doesn't?\"\n- ! **Failure modes** — \"How does this fail? How is that surfaced to the user?\"\n- ! **Scaling** — \"Does this hold at 10× the expected volume?\"\n- ~ **Security surface** — \"Who can reach this? What's the blast radius if it's wrong?\"\n- ~ **Reversibility** — \"Can this decision be changed later? What's the migration cost?\"\n\n### Transition criteria (probe complete)\n\n- ! All major decision branches have been resolved\n- ! No open assumptions remain\n- ~ User has acknowledged the risks of any deliberately deferred decisions\n- ~ No new branches are surfaced by the last 2–3 questions\n\n## Output (after completion only)\n\n! Before writing output artifacts, follow the [Preparatory Guard](../../strategies/artifact-guards.md#preparatory-guard-light).\n\n`{scope}` is the project name from `PROJECT-DEFINITION.xbrief.json`, or the feature/component name if probing a sub-scope. Use the same value consistently throughout the session.\n\n- ! Produce a `xbrief/proposed/{scope}-probe.xbrief.json` scope xBRIEF with three mandatory narratives:\n  - `LockedDecisions` — what was resolved and why\n  - `SurfacedRisks` — concerns raised, even if not fully resolved\n  - `DeferredDecisions` — explicitly acknowledged items with justification\n- ! Each entry includes: **question asked**, **answer given**, **status** (locked / deferred / risk-accepted)\n- ! Persist significant decisions as xBRIEF narratives on the relevant plan items\n- ⊗ Write probe output to a hand-authored markdown file — use xBRIEF narratives for machine-consumable downstream work\n\n## Chaining Gate\n\nAfter the probe is complete and `xbrief/proposed/{scope}-probe.xbrief.json` is written:\n\n- ! Register artifacts in `./xbrief/plan.xbrief.json` (`completedStrategies`, `artifacts`)\n- ! Return to [interview.md Chaining Gate](../../strategies/interview.md#chaining-gate) when invoked from the interview flow\n- ! Locked decisions, surfaced risks, and deferred decisions MUST flow into subsequent strategies and spec generation\n- ⊗ End the session after probe without returning to the chaining gate or the invoking strategy's next-step menu\n\n**Standalone context:** If invoked from a standalone strategy menu rather than the interview chaining gate, return to the invoking strategy's menu instead.\n\n## Anti-Patterns\n\n- ⊗ Accepting \"we'll figure it out later\" without marking it as explicitly deferred\n- ⊗ Asking generic checklist questions instead of following the decision tree\n- ⊗ Letting vague answers pass without pushing for concrete specifics\n- ⊗ Stopping when the conversation feels comfortable — stop when no new branches emerge\n- ⊗ Writing artifacts before transition criteria are met\n\n## EXIT\n\nWhen probe output is written and chaining instructions are delivered, confirm: **deft-directive-probe complete -- exiting skill.** Return to the invoking strategy's chaining gate or next-step menu.\n",
+      "body": "# Deft Directive Probe\n\nStress-test a plan before committing to it — relentless interrogation until every branch of the decision tree is resolved.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n> Strategy reference: [strategies/probe.md](../../strategies/probe.md). Probe is adversarial discovery — it assumes the plan has holes and sets out to find them.\n\n## When to Use\n\n- ~ Before committing to any significant design decision or architecture choice\n- ~ When a plan has been drafted but not yet stress-tested\n- ! When the user explicitly asks to be probed or challenged on their plan\n- ? Skip when the path forward is unambiguous and small in scope\n\n## No-Artifact Guard (active until probe complete)\n\nWhile probe completion criteria (below) are NOT met:\n\n- ⊗ Write or update any xBRIEF file (`xbrief/proposed/`, `xbrief/active/`, plan items, narratives)\n- ⊗ Update `xbrief/plan.xbrief.json` or register probe artifacts\n- ⊗ Post GitHub completion comments, close issues, or open PRs on behalf of the probe session\n- ⊗ Produce probe output markdown files instead of the canonical xBRIEF contract\n\n! Read existing context and interrogate only — artifacts land in the Output phase after completion.\n\n**Waiver (#3556):** This skill keeps the no-artifact guard and does not require `deft probe-session`. The probe strategy names `deft probe-session`. Silence is not agreement.\n\n## Workflow\n\n### Step 1: Establish the plan\n\n- ! Read whatever plan, design, or spec exists in the conversation context\n- ~ If no plan is in context, ask ONE question: \"What's the plan you want me to probe?\"\n- ~ If codebase context is relevant, explore it to answer what you can before asking\n- ⊗ Ask follow-up questions before reading available context\n\n### Step 2: Interrogate relentlessly\n\nWalk the decision tree depth-first. For each unresolved branch:\n\n- ! Ask **ONE** focused question per message\n- ! For each question, provide your recommended answer with brief reasoning\n- ! If the codebase can answer a question, explore it instead of asking the user\n- ~ Follow the thread — if an answer opens new branches, pursue them before moving on\n- ⊗ Ask multiple questions at once\n- ⊗ Present batched decision lists, numbered option menus, or multi-item checklists in a single turn\n- ⊗ Accept vague answers — push back: \"What does that mean concretely?\"\n- ⊗ Move to the next branch before the current one is fully resolved\n\n#### First-turn contract\n\n! The first user-facing probe turn after loading this skill MUST contain exactly **one** focused question plus your recommended answer — nothing else that asks the user to decide among multiple items.\n\n- ⊗ Open with a summary of every open branch, a decision matrix, or a list of questions\n- ⊗ Batch \"here are the areas we need to cover\" bullets that substitute for the single-question rule\n\n#### Question focus areas\n\n- ! **Assumptions** — \"This assumes X is guaranteed — is it?\"\n- ! **Edge cases** — \"What happens when Y is empty / null / at the limit?\"\n- ! **Dependencies** — \"This requires Z to exist — what if it doesn't?\"\n- ! **Failure modes** — \"How does this fail? How is that surfaced to the user?\"\n- ! **Scaling** — \"Does this hold at 10× the expected volume?\"\n- ~ **Security surface** — \"Who can reach this? What's the blast radius if it's wrong?\"\n- ~ **Reversibility** — \"Can this decision be changed later? What's the migration cost?\"\n\n### Transition criteria (probe complete)\n\n- ! All major decision branches have been resolved\n- ! No open assumptions remain\n- ~ User has acknowledged the risks of any deliberately deferred decisions\n- ~ No new branches are surfaced by the last 2–3 questions\n\n## Output (after completion only)\n\n! Before writing output artifacts, follow the [Preparatory Guard](../../strategies/artifact-guards.md#preparatory-guard-light).\n\n`{scope}` is the project name from `PROJECT-DEFINITION.xbrief.json`, or the feature/component name if probing a sub-scope. Use the same value consistently throughout the session.\n\n- ! Produce a `xbrief/proposed/YYYY-MM-DD-{scope}-probe.xbrief.json` scope xBRIEF with three mandatory narratives:\n  - `LockedDecisions` — what was resolved and why\n  - `SurfacedRisks` — concerns raised, even if not fully resolved\n  - `DeferredDecisions` — explicitly acknowledged items with justification\n- ! Each entry includes: **question asked**, **answer given**, **status** (locked / deferred / risk-accepted)\n- ! Persist significant decisions as xBRIEF narratives on the relevant plan items\n- ⊗ Write probe output to a hand-authored markdown file — use xBRIEF narratives for machine-consumable downstream work\n\n## Chaining Gate\n\nAfter the probe is complete and `xbrief/proposed/YYYY-MM-DD-{scope}-probe.xbrief.json` is written:\n\n- ! Register artifacts in `./xbrief/plan.xbrief.json` (`completedStrategies`, `artifacts`)\n- ! Return to [interview.md Chaining Gate](../../strategies/interview.md#chaining-gate) when invoked from the interview flow\n- ! Locked decisions, surfaced risks, and deferred decisions MUST flow into subsequent strategies and spec generation\n- ⊗ End the session after probe without returning to the chaining gate or the invoking strategy's next-step menu\n\n**Standalone context:** If invoked from a standalone strategy menu rather than the interview chaining gate, return to the invoking strategy's menu instead.\n\n## Anti-Patterns\n\n- ⊗ Accepting \"we'll figure it out later\" without marking it as explicitly deferred\n- ⊗ Asking generic checklist questions instead of following the decision tree\n- ⊗ Letting vague answers pass without pushing for concrete specifics\n- ⊗ Stopping when the conversation feels comfortable — stop when no new branches emerge\n- ⊗ Writing artifacts before transition criteria are met\n\n## EXIT\n\nWhen probe output is written and chaining instructions are delivered, confirm: **deft-directive-probe complete -- exiting skill.** Return to the invoking strategy's chaining gate or next-step menu.\n",
       "frontmatter_extra": "triggers:\n  - run probe\n  - /deft:run:probe\n  - probe\n  - probe my plan\n  - stress test"
     },
     {
@@ -236,7 +264,7 @@
       ],
       "path": "skills/deft-directive-release/SKILL.md",
       "version": "0.1",
-      "body": "# Deft Directive Release\n\nStructured 8-phase workflow for cutting a v0.X.Y release of the deft framework. Operationalizes the `task release` / `task release:publish` / `task release:rollback` / `task release:e2e` surface introduced in #716 (safety hardening of #74).\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n**See also**: [deft-directive-swarm](../deft-directive-swarm/SKILL.md) Phase 6 Step 5 (Slack announcement template re-used by Phase 8 below) | [deft-directive-review-cycle](../deft-directive-review-cycle/SKILL.md) (user-gate pattern) | [deft-directive-refinement](../deft-directive-refinement/SKILL.md) (conversational phased flow).\n\n## Platform Requirements\n\n! GitHub as the SCM platform; the **GitHub CLI (`gh`)** must be installed and authenticated. The full pipeline plus the rehearsal target (`task release:e2e`) all dispatch through `gh`.\n\n## Branch-Protection Policy Guard\n\n! Before any Phase 1 state mutation, run the skill-level branch-policy guard documented in `scripts/policy.py` / `scripts/preflight_branch.py` (#746 / #747). Releases run on the configured base branch (default `master`), so the operator MUST be on the explicit-opt-in side of the policy before the pipeline starts writing files.\n\n**Preferred path — typed direct-commit policy opt-out (#1553).** For a release session on the default branch, prefer the audited typed flag over the emergency env-var bypass:\n\n```\ntask policy:allow-direct-commits -- --confirm\n```\n\nThis writes `plan.policy.allowDirectCommitsToMaster = true` on `xbrief/PROJECT-DEFINITION.xbrief.json` with a capability-cost disclosure. After the release completes (or if the session aborts), restore enforcement **and commit the restore in the same closeout** (#2623):\n\n```\ntask policy:enforce-branches\n# enforce flips the typed flag to false locally — the commit that lands that\n# flip cannot use the typed opt-in anymore. Scope the emergency env bypass to\n# ONLY this closeout commit+push (do NOT export it for the whole session):\nDEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1 git add xbrief/PROJECT-DEFINITION.xbrief.json meta/policy-changes.log\nDEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1 git commit -m \"chore(policy): restore branch protection after vX.Y.Z\"\nDEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1 git push origin HEAD\n```\n\n⊗ Leave `allowDirectCommitsToMaster=true` on origin after publish. ⊗ Run `policy:enforce-branches` and leave the dirty restore under protection ON without committing (forces a follow-up PR — the v0.79.0 / #2619 failure mode).\n\n**Branch-guard probe (either path).** Regardless of which opt-out path you chose, confirm the guard passes before Phase 1 mutates state:\n\n```\nuv run python scripts/preflight_branch.py --project-root . --quiet || exit 1\n```\n\nor invoke `task verify:branch`. This is the canonical surface that surfaces the policy state to the operator before the pipeline starts writing files. The release pipeline's other safety surfaces (the dirty-tree guard, base-branch check, `task ci:local` gate) remain independent of this check.\n\n**Emergency env-var bypass — narrow scope only (#1553).** `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1` is process-wide: every child process, nested test, and temporary repository spawned from the same shell inherits it. During the v0.43.0 release attempt, wrapping the entire `task release` invocation in this env var let the bypass leak into the Step 5 `task ci:local` preflight, which caused `TestWriteConsumerGitHooks_VendoredCommitBlocked_RealGit` to fail because the vendored test repo allowed a direct `master` commit the test expected the hook to block.\n\n- ! Prefer `task policy:allow-direct-commits -- --confirm` for release sessions instead of exporting `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1` for the whole shell.\n- ⊗ Wrap `task release`, `task ci:local`, or `task check` in `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1` -- the env var is inherited by every subprocess and can produce false preflight failures before any release mutation.\n- ? If the env-var path is unavoidable, scope it to a **single** branch-guard probe only (e.g. `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1 task verify:branch`) and do NOT export it for the release session. The release pipeline itself passes the bypass only in scoped subprocess `env=` for its authorised commit/tag/push mutations (#867); operators MUST NOT mirror that pattern at the shell level.\n\nThe release pipeline's Step 9/10/11 git mutations carry the bypass in subprocess `env=` only (`scripts/release.py::_release_subprocess_env`, #867) so the parent shell stays clean. Operator-side env-var exports defeat that isolation.\n\n## Deterministic Questions Contract\n\n! Every numbered-menu prompt rendered in this skill (Phase 1 version-bump magnitude check, Phase 2 dry-run review `yes`/`back`/`quit`, Phase 5 optional `defer`/`rollback`/`Discuss` (happy path auto-publishes after draft QA)) MUST follow [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md): the final two numbered options MUST be `Discuss` and `Back`, in that order. Existing `back`/`quit` options remain valid; this contract simply adds `Discuss` as a peer alongside `Back`. The Discuss-pause semantic is documented verbatim in the contract -- implicit resumption is forbidden.\n\n## When to Use\n\n- User says \"release\", \"cut release\", \"v0.X.Y\", \"publish release\", \"ship a release\"\n- The framework's `[Unreleased]` CHANGELOG section is non-empty and the operator wants to cut a tagged release\n- A previous release rehearsal succeeded and the operator is ready for the production cut\n\n## Phase 1 — Pre-flight\n\n! Validate the local + remote state before any irreversible action.\n\n\n### Parallel prep — #1880 Gap D (#2692)\n\n! Phase 1 long steps (`task reconcile:issues -- --apply-lifecycle-fixes`, cache refresh when ritual-stale, `task ci:local` / `task check`) and Phase 3 `task release:e2e` MUST be backgrounded or subagent-dispatched when the host supports it (Cursor: Task tool `run_in_background: true`), with progress surfaced via DONE/heartbeat — same ownership as review-cycle / merge-ready workers (#1880 Gap D). The operator conversation MUST stay interactive for version magnitude confirmation, `--summary`, and the Phase 2 dry-run `yes`/`back`/`quit` gate while prep runs.\n\n! **Checklist:** Phase 1 prep parallelized — long prep started in background before (or while) collecting version magnitude / summary / npm irrevocability disclosure.\n\n! On Windows PowerShell, do NOT wrap long task output in `Select-Object -Last` (it buffers until the process exits); stream to the terminal or log to a file and read incrementally. See `scm/github.md` § #2646 / Windows encoding guidance for related PS pitfalls.\n\n⊗ Foreground-block the operator chat on reconcile / `ci:local` / `release:e2e` when background dispatch is available (#1880 Gap D / #2692).\n\n### Fixable check failure — file-and-merge before resume (#2859)\n\n! When Step 4 (`task ci:local` or `task check`) fails on a **fixable product or test defect** (hang, failing test, validation bug — not operator env misconfiguration), the release cut MUST pause and route the blocker through normal issue → xBRIEF → feature branch → PR → merge before resuming Phase 1.\n\n? **Step 5 branch-coverage threshold misses** during `task release` (Vitest branch coverage below 85% with no other failure mode) are carved out to § Step 5 branch-coverage threshold — open-issue ledger hatch (#2866) below — not this file-and-merge path.\n\n**Required path:**\n1. File a GitHub issue with root cause, recurrence signature, and acceptance criteria.\n2. Ingest / promote / activate scope xBRIEF; implement on a feature branch with `drive-to: merge-ready`.\n3. Merge; confirm `task check` / `ci:local` is green for the failure mode.\n4. Resume the release cut from Phase 1 (re-run Step 4).\n\n⊗ Lead with an inline-only hotfix on the release branch / default branch without a tracked issue and merged PR.\n⊗ Suggest untracked `--skip-ci` or `--allow-skip-ci` without a **tracked issue number** as the first recovery when the failure is a clear, shippable bug.\n⊗ Continue the cut with \"raise timeouts,\" \"fix it here,\" or other shortcut theater before file-and-merge completes.\n\n? **`--skip-ci` / `--allow-skip-ci=#N` remains valid** only under explicit operator incident review with a **tracked issue** cited on the flag (Phase 4 contract). It is NOT a substitute for filing and merging a fixable defect discovered in Phase 1.\n\n**AGENTS.md bulk rejected (#2859):** Expanding `AGENTS.md` / `content/templates/agents-entry.md` with an always-on pin for this release-phase reminder was considered and **rejected**. This rule lives in the release skill (and optional lesson); do NOT add AGENTS.md / agents-entry bulk for it.\n\nSee [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Fixable check failure during release for the operator runbook and the existing `--allow-skip-ci=#N` incident contract.\n\n### Step 5 branch-coverage threshold — open-issue ledger hatch (#2866 / #3187)\n\n! When **`task release` Step 5** fails on Vitest coverage below the 85% goal, apply this hatch **only** when **branches** is the **sole** metric below 85% (hairline branch miss — lines, functions, and statements all ≥ 85%). Confirm via the Step 5 failure output, `coverage/coverage-final.json`, or `task coverage:hotspots` before hatching. If **any other metric** is also below 85%, or the failure is a hang / failing test / non-coverage defect, STOP — use § Fixable check failure — file-and-merge before resume (#2859) instead.\n\n**Runtime disclosure (#2573):** `--allow-coverage-debt=#N` sets vitest coverage thresholds to zero for the release Step 5 run (`vitest.config.ts`). The hatch is justified only for branch-only hairlines; the filed debt issue MUST require restoring **all four metrics** (lines, functions, branches, statements) to ≥ 85% before close.\n\n**Auto-hatch in `task release` Step 5 (#3187):** the pipeline classifies a non-zero Step 5 as `REAL_FAILURE` | `BRANCH_HAIRLINE` | `OTHER_COVERAGE` | `UNKNOWN` after **one** suite run.\n\n1. `REAL_FAILURE` | `OTHER_COVERAGE` | `UNKNOWN` → **fail closed** (no auto-issue). Route product defects via #2859.\n2. `BRANCH_HAIRLINE` + **any open** coverage-debt ledger entry → **fail closed** (\"restore coverage; close `#N` first\") — consecutive soft-pass ban (#2866).\n3. `BRANCH_HAIRLINE` + **empty** open debt ledger → **auto-file** `#N` with markers `coverage-debt` and `--allow-coverage-debt`, measured metrics, cut version, and acceptance (all four metrics ≥ 85%); mark Step 5 `PASS_WITH_DEBT(#N)`; **continue the cut without re-running vitest**. Loud stderr banner + cite `#N` in CHANGELOG / release notes.\n\n! **File before continue** — never soft-pass without a durable issue number.\n\n? Operators MAY still pass `--allow-coverage-debt=#N` manually (PowerShell-safe: `--allow-coverage-debt=N` or `--allow-coverage-debt=\"#N\"` — #2621) when re-running after a pre-filed debt issue.\n\n**SHA suite stamp (#3187, coordinates with #3188 check ordering):** after suite **green** or `PASS_WITH_DEBT`, write a local SHA-bound stamp under `.deft/release-suite-stamp.json` (gitignored). Re-entry at the **same clean HEAD** skips the suite; dirty tree or different HEAD invalidates the stamp. ⊗ CI never trusts the stamp (GHA has no committed stamp; `CI`/`GITHUB_ACTIONS` force miss).\n\n**Open-issue ledger (release-scoped only):**\n\n1. Check for an **open coverage-debt tracking issue** (unpaid hatch from a prior cut) — union all three probes and dedupe by issue number:\n   - **Marker search** (new-format debt issues):\n     ```\n     gh issue list --repo <owner>/<repo> --state open --search \"coverage-debt in:title,body\" --limit 20\n     gh issue list --repo <owner>/<repo> --state open --search \"allow-coverage-debt in:body\" --limit 20\n     ```\n   - **CHANGELOG citation scan** (legacy hatch issues filed before markers were mandatory): parse `CHANGELOG.md` `[Unreleased]` plus the last three `## [version]` sections for `--allow-coverage-debt=#N` / `allow-coverage-debt=#N` citations; for each `#N`, probe issue state via REST — `OPEN` (or unknown) counts as unpaid debt even when title/body lack the new markers (#2866).\n2. If **no open coverage-debt issue exists** → auto-hatch files `#N` (or operator files manually) with title prefix `coverage-debt:` and body containing both markers. The open `#N` remains WIP until coverage is restored and the issue is closed.\n3. If an **open coverage-debt issue from a prior hatch still exists** → ⊗ soft-pass again; restore real coverage (all four metrics ≥ 85%) and close the debt issue before the cut proceeds.\n\n**Framework-release-first (#3187):** auto-hatch applies to framework `task release` Step 5 (e.g. deftai/directive). Consumer expansion of auto-hatch via `plan.policy.coverageDebt` is reserved; consumer expansion is not implemented (#3314). Refuse when unset or off. Live hatch is `--allow-coverage-debt=#N` (#2866). Do not auto-file debt on the framework repo from consumer trees; consumer ledger is always the consumer repo.\n\n⊗ Auto-pass on a near-miss band without `#N` (#2573).\n⊗ Silent soft-pass with no tracked issue.\n⊗ File a debt issue without `coverage-debt` / `allow-coverage-debt` markers in title or body — the ledger query will miss it and permit a consecutive soft-pass (#2866).\n⊗ Use this carve-out when lines, functions, or statements are also below 85%, or for hangs, failing tests, or non-coverage Step 5 failures — those stay under #2859 file-and-merge.\n⊗ Treat file-debt-then-hatch as the default for ordinary PR / `task check` work outside a release cut — this hatch is release-scoped only.\n⊗ Trust a laptop suite stamp in CI or after HEAD/tree drift (#3187).\n\nSee [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Coverage debt hatch during release.\n\n### Routine vs hard cut for Step 5 (#2953)\n\n! Treat **hard cut** as the default: full Step 5 (`task check` + Vitest coverage) with no `--skip-ci`.\n\n~ Treat **routine cut** as the same full Step 5, sped up by default-excluding `.deft-scratch/` (and legacy `swarm-worktrees/`) from content/link/path/build-dist walks, plus pre-cut hygiene (green required checks on the tip SHA; prune stale `.deft-scratch/worktrees`).\n\n! Confirm required CI is green on the tip you will tag when aiming for a calm routine cut — green tip CI is a precondition, not a replacement for Step 5.\n\n⊗ Invent a silent lighter Step 5 that skips or soft-passes coverage without an explicit hatch (`--allow-coverage-debt=#N` for branch-only hairlines, or `--skip-ci` + `--allow-skip-ci=#N` for incidents). Silent soft-pass is forbidden in every mode.\n\n~ Prefer pruning abandoned worktrees / cutting from a clean clone over re-scanning scratch noise.\n\nSee [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Routine vs hard cut for Step 5 (#2953).\n\n\n~ **Frozen Go-installer bridge (#1912 / #1972 / #1987):** by default a release tag *above* the frozen line (the `LAST_GO_INSTALLER` constant in `packages/core/src/legacy-bridge/sot.ts`) will NOT rebuild the 6 Go binaries -- the CI `freeze-gate` job in `.github/workflows/release.yml` skips the build (the run stays green; npm still ships from the separate `npm-publish.yml`). If this release must rebuild the Go installer, follow the runbook in [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Frozen Go-installer bridge: roll `LAST_GO_INSTALLER` forward to the cut tag BEFORE tagging (pinning to the exact cut tag both releases the gate AND re-freezes at the new line), then see that section's \"After the release\" step for the re-pin.\n\n1. ! Verify the operator is on the configured base branch (default `master`) and the working tree is clean\n2. ! Confirm the next version number (`X.Y.Z`) with the user. Major / minor / patch decision flows from the `[Unreleased]` content (breaking change → major; new feature → minor; fix-only → patch)\n3. ! Inspect `[Unreleased]` content vs the proposed version bump. If a breaking change appears in `### Changed` / `### Removed` but only a patch is proposed, surface the mismatch and ask the user to choose\n4. ! Verify `task ci:local` passes locally (or `task check` as the graceful-degradation fallback per `tasks/release.yml` line 9-10). The `task release` script will refuse to proceed otherwise -- but Phase 1 catches it earlier — **on failure from a fixable defect, STOP and follow § Fixable check failure below (#2859); do NOT proceed to step 5**\n5. ! Verify `gh auth status` reports authenticated (`task release` will refuse otherwise)\n6. ! **Run `task reconcile:issues -- --apply-lifecycle-fixes` to clear any closed-issue / non-completed-folder xBRIEFs before invoking `task release`** (#734). The release pipeline carries the deterministic gate at Step 3 (`scripts/release.py::check_vbrief_lifecycle_sync`, refuses with `EXIT_VIOLATION` on any Section (c) mismatch), but Phase 1 is the operator's first-line defence -- running the apply-mode flag here is the canonical clean path; `--allow-vbrief-drift` on the pipeline exists only as the explicit-acknowledgment escape hatch (analogous to `--allow-dirty`). The recurrence record is the v0.21.0 cut, which surfaced 13 stranded xBRIEFs (8 cycle-relevant + 5 historical residue) post-publish; the gate now blocks that drift before any irreversible action\n7. ! **Verify the proposed `v<version>` tag is not already in use locally, on origin, or as a published GitHub release** (#784). The release pipeline carries the deterministic gate at Step 4 (`scripts/release.py::check_tag_available`, refuses with `EXIT_VIOLATION` before any state mutation -- CHANGELOG promotion, ROADMAP refresh, build, commit), but Phase 1 is the operator's first-line defence. Quickly probe with `git tag -l v<version>` (local), `git ls-remote --tags origin refs/tags/v<version>` (remote), and `gh release view v<version> --repo <owner>/<repo>` (release-only, where `gh release view` exits 0 only when the release exists). The recurrence record is the v0.22.0 → v0.23.0 release attempt on 2026-05-01: the operator typed `0.22.0` (the prior release from 12 hours earlier) and the legacy pipeline ran 8 steps before failing at `git tag` -- leaving a wrong-version local commit + `dist/deft-0.22.0.zip` orphan + manual `git reset --hard` recovery. The new pre-flight gate blocks that mode before any irreversible action\n8. ! **Verify the npm credential path is configured before cutting the tag** (#1910, #1909). A `v*` tag now auto-triggers `.github/workflows/npm-publish.yml`, which publishes the four `@deftai/directive*` packages with `npm publish --provenance`. Confirm the publish path can authenticate: either the `NPM_TOKEN` repo secret is present (`gh secret list --repo <owner>/<repo>` shows `NPM_TOKEN`) OR an npm OIDC trusted publisher is configured for the `@deftai/directive*` packages. If neither is in place, WARN loudly that the tag will fire a publish job that fails (red X on the tag, no packages) -- the operator may still proceed for a GitHub-only release, but the npm channel will not land until #1909's credential is provisioned. Cross-reference #1909.\n9. ! **Disclose npm irrevocability before any tag push (#1972, #2002).** A `v<version>` tag push is the **real npm publish gate** -- NOT Phase 5 or `task release:publish`. Tag push fires `.github/workflows/npm-publish.yml` in a separate workflow that is NOT draft-gated; npm packages ship immediately and **cannot be retracted** (`npm unpublish` is forbidden). Recovery is forward-only: deprecate, dist-tag, or ship a patch. The operator's explicit `yes` in Phase 2 (dry-run) and the decision to invoke `task release` in Phase 4 are the last human gates before npm goes live. Phase 5 only controls GitHub release visibility (draft → public); it does NOT gate npm.\n10. ~ Ask the operator for an optional one-line release **summary** (recommended 80-160 chars; can be skipped). The summary is the canonical narrative for THIS release across three audiences: (a) injected as a Markdown blockquote at the top of the promoted `CHANGELOG.md [<version>]` section, (b) auto-flowed into the GitHub release body via the existing `_section_for_version` pickup, and (c) populated VERBATIM into the Phase 8 Slack `*Summary*:` slot. Capture the wording once here; do NOT regenerate per-audience downstream\n\n⊗ Skip the version-bump magnitude check -- a patch release that ships breaking changes is the kind of regression that Repair Authority [AXIOM] (#709) is designed to prevent.\n\n⊗ Skip the xBRIEF-lifecycle-sync check (#734); the gate exists because operators consistently forget the manual `task scope:complete` move step. The v0.21.0 cut surfaced 13 stranded xBRIEFs (8 cycle-relevant + 5 historical residue) post-publish as the recurrence record this gate prevents. If `task release` reports `[3/13] Pre-flight xBRIEF lifecycle sync... FAIL (<count> mismatches; run task reconcile:issues -- --apply-lifecycle-fixes to fix)`, the canonical recovery is the apply-mode invocation -- `--allow-vbrief-drift` is reserved for cases where the operator has explicitly reviewed the drift and chosen to defer the lifecycle reconcile to the next refinement pass (e.g. an emergency hot-fix release).\n\n⊗ Skip the tag-availability check (#784); the gate exists because the legacy 12-step pipeline only invoked `git tag` at Step 9, after Steps 1-8 had already mutated state (CHANGELOG promoted, ROADMAP refreshed, dist built, release commit made locally). A duplicate-tag failure at Step 9 stranded the operator with an unpushed wrong-version commit + orphaned `dist/deft-<wrong>.zip` artifact + manual `git reset --hard` recovery (forbidden by AGENTS.md SCM rules without explicit permission). The recurrence record is the v0.22.0 → v0.23.0 release attempt on 2026-05-01. If `task release` reports `[4/13] Pre-flight tag availability... FAIL (<surface> tag v<version> already exists ...)`, the canonical recovery is to choose a different version (the most likely cause is operator typo of a prior release).\n\n⊗ Hand-write a different one-line narrative for each of the three downstream surfaces (CHANGELOG / GitHub release / Slack) -- that drift is exactly the gap the `--summary` flag is designed to close. If the operator insists on per-audience tone, populate the canonical `--summary` ONCE here and document the deviation in the Phase 8 anti-pattern.\n\n## Phase 2 — Dry-run review\n\n! Invoke `task release -- <version> --dry-run --skip-tag --skip-release` and present the plan to the user. If Phase 1 collected an operator summary, also pass `--summary \"<text>\"` so the dry-run preview reflects the canonical narrative the operator just authored.\n\n```\ntask release -- <version> --dry-run --skip-tag --skip-release --summary \"<text>\"\n```\n\nThe dry-run prints `[N/13] <step>... DRYRUN (would <action>)` for every pipeline step (Step 13 is the post-create verify-isDraft gate added by #724; Step 4 is the tag-availability pre-flight gate added by #784). Step 6 (CHANGELOG promotion) surfaces whether a summary was supplied (truncated to ~60 chars in the preview) so the operator can validate the wording before any file is written. Capture the output and present it to the user, then wait for explicit confirmation before continuing.\n\n! Wait for explicit user confirmation: `yes` / `back` / `quit`. Remind the operator that Phase 4's tag push will irrevocably publish npm (#1972) -- this `yes` is the last safe abort before that channel opens.\n- `yes` (or `confirmed` / `approve`) → proceed to Phase 3\n- `back` → return to Phase 1 for re-validation (e.g. user wants to amend the version or `[Unreleased]` content)\n- `quit` → abort the workflow cleanly; no state changes\n\n⊗ Skip the dry-run preview. The dry-run is the operator's last opportunity to catch a bad version number, malformed CHANGELOG, or wrong base branch before the pipeline starts writing files.\n\n## Phase 3 — E2E sanity\n\n! Invoke `task release:e2e` against an auto-created temp repo to verify the full pipeline shape works end-to-end before touching the real repo.\n\n! **#1880 Gap D (#2692):** `task release:e2e` is a long-running step — MUST background / subagent-dispatch it when the host supports it so Phase 2 confirmation and other human gates stay interactive. Do not wrap its output in PowerShell `Select-Object -Last`.\n\n```\ntask release:e2e\n```\n\nThe harness provisions `deftai/deftai-release-test-<ts>-<uuid6>`, runs the smoke-test rehearsal, and **by default keeps** the temp repo (#2572). Stderr always includes the full `owner/slug` and a copy-pasteable manual-cleanup command (`gh repo delete <owner>/<slug> --yes`). Privileged environments (CI or an operator with `delete_repo`) MAY pass `task release:e2e -- --destroy-repo` to attempt auto-delete; destroy failure emits a WARN and does **not** block Phase 4 when the rehearsal succeeded.\n\n! After Phase 3, the agent MUST NOT retry or escalate temp-repo deletion. Include any leftover temp repo(s) in the phase summary for the operator to clean up manually.\n\n! Treat a non-zero exit from `task release:e2e` as a hard refusal to proceed to Phase 4. Surface the diagnostic and ask whether to debug (return to Phase 1) or abort (`quit`).\n\n? **Skip allowed** when the operator has just run `task release:e2e` successfully against the same branch in the past 30 minutes. Note the prior run timestamp in the user-facing summary.\n\n! **`task release:e2e` now also rehearses the npm publish (#1910).** Unless `--skip-npm` is passed (or `npm` is absent from PATH, which soft-skips), the rehearsal runs `npm publish --dry-run --access public` for all four `@deftai/directive*` packages against the throwaway clone in dependency order (types -> core -> content -> cli), after `pnpm install` + `pnpm -w run build` and a version-alignment pass. This catches a broken `files` allowlist, a version-drift bug, or a dependency-order error BEFORE the real `v*` tag fires the publish workflow -- without touching the real registry. The install+build exceeds the <90s fast budget, so pass `task release:e2e -- --skip-npm` when you only need the GitHub-pipeline shape check.\n\n! **Tag -> npm coupling + irrevocability (#1910, #1972, #2002).** A `v<version>` tag is a TWO-channel action: the GitHub release (this skill's pipeline) AND `.github/workflows/npm-publish.yml`, which runs in a SEPARATE workflow that does NOT block the GitHub release and is NOT draft-gated. The npm workflow derives the published version from the tag (`${GITHUB_REF_NAME#v}`); this skill owns the version chosen in Phase 1. These MUST stay consistent -- the tag you cut IS the npm version that ships; there is no separate npm version bump. **npm publish is irrevocable** (#1972): once the tag fires, packages are live on npm and cannot be unpulled; `task release:rollback` does NOT retract npm (forward-only recovery). A red npm job on a green GitHub release means the npm channel did not ship (verify in Phase 5/7).\n\n## Phase 4 — Production draft\n\n! **Last human gate before npm (#1972, #2002).** Immediately before invoking `task release`, re-state that the tag push in this step will irrevocably publish all four `@deftai/directive*` packages to npm via `.github/workflows/npm-publish.yml`. There is no undo on npm; only forward recovery (deprecate / dist-tag / patch). Proceed only when the operator explicitly confirms.\n\n! Invoke `task release -- <version>` (NO `--dry-run`, NO `--skip-tag`, NO `--skip-release`, NO `--skip-ci`). If Phase 1 collected an operator summary, pass `--summary \"<text>\"` so the production cut writes the same blockquote the dry-run previewed.\n\n⊗ Use `--skip-ci` on a production cut except under explicit operator incident review — it skips Step 5 vitest coverage and ships untested npm builds (#2652). When unavoidable, pass `--allow-skip-ci=#N` citing the tracked issue; Step 5 emits a loud WARN. See [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Vitest coverage hang recovery. The next patch after the hang fix must cut without `--skip-ci`.\n\n```\ntask release -- <version> --summary \"<text>\"\n```\n\nPer #716 default-draft hardening, this lands the release as a `--draft` on the real repo. Binaries upload via release.yml CI, but the artifact is NOT yet visible to consumers. The operator-authored summary becomes part of the promoted `CHANGELOG.md [<version>]` section AND the GitHub release body (auto-pickup via `_section_for_version`). The same wording is the canonical source for the Phase 8 Slack `*Summary*:` slot.\n\n! **Maintainer-mode release notes auto-lead with an \"Upgrading from an older version?\" banner (#1413).** When the cut targets the canonical framework repo (`deftai/directive`), `scripts/release.py` Step 12 prepends the banner from the editable template at `.github/release-notes/upgrade-banner.md` to the notes passed to `gh release create` (via `_prepend_upgrade_banner`). The banner points consumers at the canonical `deft-install --yes --upgrade --repo-root . --json` upgrade command and #1411. This is **GitHub-release-body-only** -- it is NEVER injected into `CHANGELOG.md`, so the CHANGELOG section and the release body intentionally differ by this leading block. To change the wording, edit the template file; do not hand-edit the published release body. **Consumer-mode releases (any non-`deftai/directive` repo) are unaffected** -- a downstream project that vendors the release pipeline never inherits deft's upgrade guidance. A missing/unreadable template degrades gracefully (notes ship without the banner; the cut is never blocked).\n\n! **Verify isDraft within 5 seconds; flip immediately if not (#724).** Immediately after `gh release create --draft` returns success, `scripts/release.py` Step 11 polls `gh release view v<version> --json isDraft` up to 5 times at 1-second intervals. If the release exists with `isDraft=false`, the pipeline auto-flips it via `gh release edit v<version> --draft=true` and emits a `WARNING: release landed as public; flipping to draft (defense-in-depth, see #724)` line. This closes the ~90-second public-exposure window observed during the v0.21.0 cut where a manual recovery created a public release before the operator noticed and flipped it. The verify gate is defense in depth even when `--draft` was passed correctly: it catches the case where `gh release create` partially succeeded (release record written, error returned) AND the operator-error variant where an alternate code path sent the release without `--draft`. A release-not-found-within-budget result emits a WARN and does NOT fail the pipeline (release.yml CI may still be processing).\n\n! Wait for `task release` to exit 0 before continuing. A non-zero exit means the pipeline halted partway through; consult Phase 7's `task release:rollback` recovery before retrying.\n\n⊗ Pass `--no-draft` here unless the operator has explicitly opted into direct-publish (e.g. automated security patch). The default-draft contract is the foundation of the safety hardening surface.\n\n⊗ Skip the post-create verify-isDraft gate -- the gate is the only reliable safety net against \"create call exited 0 but the release somehow landed as public\" variants (#724). If `task release` is invoked manually outside the canonical `scripts/release.py` flow, the operator MUST run `gh release view v<version> --json isDraft` followed by `gh release edit --draft=true` on `isDraft=false` BEFORE handing off to Phase 5.\n\n## Phase 5 — GitHub draft QA (optional; NOT the npm authority gate)\n\n! After `task release` exits 0, QA the **GitHub draft release** only. npm packages typically **already shipped** when the tag push in Phase 4 fired `.github/workflows/npm-publish.yml` (#1972, #2002). Phase 5 is NOT a \"user-only authority before going live\" gate for the release as a whole -- it is optional draft QA for GitHub assets, notes, and binaries.\n\n1. ! **Verify npm publish status FIRST (in parallel with draft inspection).** Run `gh run list --workflow=npm-publish.yml --repo <owner>/<repo> --limit 5` and confirm the tag run for `v<version>` is `completed`/`success`. If npm failed, surface immediately -- the GitHub draft QA is secondary to a red npm channel.\n2. ! Run `gh release view v<version> --json url,name,body,assets,isDraft --repo <owner>/<repo>` and present the output to the user\n3. ! Surface the asset list (size + filename) so the user can verify binaries uploaded correctly\n4. ! Surface the auto-generated release notes (or the CHANGELOG section that was promoted into the release body)\n\n### Happy path (default when npm succeeded and draft assets look correct)\n\n! When the npm workflow succeeded AND draft assets/notes pass inspection, **auto-proceed to Phase 6 Publish branch** -- run `task release:publish -- <version>` without a redundant human publish prompt (#2002). npm already shipped at tag push; waiting for a separate `publish` confirmation does not protect the npm channel.\n\n? **Operator override:** if the operator wants to hold the GitHub release in draft (e.g. embargo, last-minute notes edit), they MAY say `defer` before auto-publish runs.\n\n### Exception paths (operator-initiated)\n\n- `rollback` → proceed to Phase 6 (Rollback branch). **Reminder:** rollback unwinds the GitHub release only; npm packages already published at tag push are NOT retracted (#1972).\n- `defer` → halt and exit. Surface the draft URL so the operator can return later with `task release:publish -- <version>` or `task release:rollback -- <version>`.\n\n⊗ Treat Phase 5 as the npm publish-authority gate -- npm ships at tag push (Phase 4), not at `task release:publish`. A human `publish` prompt here is redundant when npm already succeeded and only delays flipping the GitHub draft to public.\n⊗ Skip npm workflow verification in Phase 5 and defer it entirely to post-publish Phase 7 -- npm status MUST be checked before or in parallel with the GitHub publish flip.\n\n## Phase 6 — Publish or rollback\n\n! Branch on the Phase 5 outcome. The happy path auto-enters the Publish branch when npm succeeded and draft QA passed (#2002).\n\n### Publish branch (happy path auto-run, or resumed after `defer`)\n\n```\ntask release:publish -- <version>\n```\n\nThe companion script flips `--draft=false`, then re-reads the release to verify `isDraft == false` actually flipped. State machine:\n- `draft` found → flip to public; verify; exit 0\n- already `published` → exit 0 no-op (idempotent re-runs are safe)\n- `not-found` → exit 1 (cannot publish a missing release)\n- gh-error → exit 1 with diagnostic\n\n! Wait for `task release:publish` to exit 0 before continuing. On the happy path this runs immediately after Phase 5 draft QA without a separate human publish prompt.\n\n### Rollback branch (user said `rollback`)\n\n```\ntask release:rollback -- <version>\n```\n\nThe state-aware unwind detects the post-release state and applies the matching tiered recovery. Time-windowed download-count guard:\n- release age `< 5 min` → threshold = 0 (rollback safe; nobody noticed yet)\n- release age `5-30 min` → threshold = max(`--allow-low-downloads`, 10) (filters bot fetches)\n- release age `> 30 min` → refuse without `--allow-data-loss`\n\nThree escape hatches (escalating warnings):\n- `--allow-low-downloads N` -- accept up to N downloads\n- `--allow-data-loss` -- accept any count (consumer impact)\n- `--force-strict-0` -- require exactly 0 regardless of release age\n\nRace-condition mitigation: `download_count` is double-read with a 5s sleep between reads; rollback only proceeds if both reads agree below threshold.\n\n! When the guard refuses, surface the recommendation to the user: rollback is risky on a released artifact with non-zero downloads. Prefer the **hot-fix path** (cut the next patch with a withdrawal note in `[Unreleased]/Changed` rather than deleting the broken release).\n\n! **`task release:rollback` does NOT retract npm (#1972, #2002).** Rollback unwinds GitHub release state (draft/public, tag, assets) only. npm packages published at tag push remain on the registry irrevocably. Recovery is forward-only: deprecate the bad version, move a dist-tag, or ship a patch release.\n\n## Phase 7 — Post-publish verification\n\n! Only enter Phase 7 if Phase 6 took the Publish branch (rollback branch ends here with the unwind log).\n\n1. ! **Re-verify npm publish landed (#1910, #1909, #2002).** Phase 5 checked workflow status before the GitHub publish flip; Phase 7 confirms registry truth AFTER `task release:publish`. For each of `@deftai/directive-types`, `@deftai/directive-core`, `@deftai/directive-content`, and `@deftai/directive`, run `npm view <pkg>@<version> version` (expect `<version>`) and confirm provenance on the npm page. A green GitHub release with missing npm packages means consumers cannot `npm i -g @deftai/directive@<version>` -- escalate immediately. (Real-registry verification depends on #1909's credential; until then verify workflow-run status and flag credential gaps.)\n2. ! Verify GitHub auto-closed the discrete-task issue(s) referenced via `Closes #N` in the release notes (mirrors `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 2)\n3. ! Run `gh issue view <N> --json state --jq .state` for each closed issue. If any didn't auto-close, manually close with `gh issue close <N> --comment \"Closed by release v<version> (squash auto-close did not trigger)\"` (Layer 1, #167)\n4. ! Verify ROADMAP.md correctness via `task roadmap:render` (the release pipeline already invoked this; Phase 7 is the second-pass sanity check)\n5. ! Verify binaries are downloadable from the public release URL: `gh release view v<version> --json assets --jq '.assets[].url'` and curl one to confirm 200 OK\n6. ! For any umbrella / staying-OPEN issue (`Refs #N`) referenced in the release notes, run the Layer 3 reopen sweep from `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 1: any protected issue that auto-closed MUST be reopened with a comment citing #701\n\n⊗ Skip the post-publish verification. The closing-keyword false-positive (Layer 1 / Layer 2 / Layer 3) and the incremental-renderer-drift (#641, #614) are exactly the kind of issues that surface only AFTER a release is public.\n\n## Phase 8 — Slack announcement\n\n! Generate the canonical Slack release announcement and present it to the user for copy-paste, re-using the template from `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 5.\n\nThe announcement block MUST include:\n\n```\n:rocket: *deft v<version>* -- <release title>\n\n*Summary*: <one-sentence description of the release scope>\n\n*Key Changes*:\n- <bullet per significant change, 3-5 items max>\n\n*Stats*: 1 release | ~<duration> elapsed | <N> commits since v<previous>\n*Release*: <GitHub release URL>\n```\n\n! Populate version from the freshly-published `gh release view v<version>` output. Populate release title from the CHANGELOG section heading (or the GitHub release title). Summarize key changes from the promoted `[Unreleased]` -> `[<version>]` CHANGELOG section (NOT raw commit messages). Populate stats from `git log v<previous>..v<version> --oneline | wc -l`.\n\n! Populate the `*Summary*:` slot VERBATIM from the operator-authored blockquote at the top of the CHANGELOG `[<version>]` section (the line beginning with `> ` immediately after the `## [<version>] - <date>` heading). The Phase 1 prompt + Phase 4 `--summary` flag exist precisely so this populate step is mechanical -- one canonical narrative authored once at Phase 1, propagated through Phase 4 promotion, and copy-pasted here without re-authoring. If the CHANGELOG section has no blockquote (operator skipped the Phase 1 prompt), generate a one-sentence summary from the `### Added` / `### Changed` bullets and surface to the operator that this is a regenerated narrative (NOT canonical) so they can decide whether to amend the CHANGELOG before publishing.\n\n! Present the block as a code-fenced snippet the user can copy directly. Do NOT post to Slack from inside this skill -- the user owns the actual broadcast.\n\n## Skill Completion\n\n! When Phase 8 completes (or when Phase 5 took the `defer` / `quit` path, or when Phase 6 completed the rollback branch), explicitly confirm skill exit:\n\n```\ndeft-directive-release complete -- exiting skill.\nNext: <one-line guidance>\n```\n\nWhere `<one-line guidance>` is one of:\n- \"release v<version> live -- monitor consumer reports for ~24h before cutting v<next>\"\n- \"release v<version> rolled back -- the underlying defect needs a hot-fix in the next CHANGELOG entry\"\n- \"release deferred -- resume by running `task release:publish -- <version>` (GitHub only; npm already shipped at tag push) or `task release:rollback -- <version>` (GitHub unwind only; npm is forward-recovery) when ready\"\n\n⊗ Exit silently without confirming completion or providing next-step guidance.\n\n## Anti-Patterns\n\n- ⊗ Foreground-block the operator chat on Phase 1 long prep (`reconcile:issues`, cache refresh, `ci:local` / `check`) or Phase 3 `release:e2e` when background / subagent dispatch is available (#1880 Gap D / #2692) — the interactive channel must stay free for version confirmation, `--summary`, and the Phase 2 dry-run gate\n- ⊗ Wrap long release-prep task output in PowerShell `Select-Object -Last` — it buffers until exit and makes the session look hung (#2692)\n- ⊗ Run `task release` without a Phase 2 dry-run preview -- the dry-run is the only safe place to catch a bad version, malformed CHANGELOG, or wrong base branch\n- ⊗ Skip Phase 3 (e2e rehearsal) on the assumption that \"the dry-run is enough\" -- the e2e harness catches gh-CLI auth issues, repo permission gaps, and pipeline-shape regressions that the dry-run cannot detect\n- ⊗ Pass `--no-draft` to `task release` without explicit operator opt-in -- the default-draft contract is the foundation of the safety hardening surface\n- ⊗ Treat Phase 5 as the npm authority gate or require a redundant human `publish` prompt when npm already succeeded -- npm ships at tag push (#1972); Phase 5 is GitHub draft QA only\n- ⊗ Expect `task release:rollback` to retract npm packages -- rollback is GitHub-only; npm recovery is forward-only (deprecate / dist-tag / patch)\n- ⊗ Run `task release:rollback` against a release that has > 30 minutes of consumer-driven downloads without first weighing the hot-fix path -- a withdrawal note in the next patch is almost always less disruptive than deleting a public artifact\n- ⊗ Use `--allow-data-loss` without first reading the script docstring's hot-fix-path recommendation -- the flag is an explicit acknowledgment of consumer impact, not a default\n- ⊗ Skip the Phase 7 Layer 3 reopen sweep -- protected umbrellas can auto-close on a release-merge squash even when the release notes use `Refs #N` only\n- ⊗ Post the Phase 8 Slack announcement directly from this skill -- the user owns the broadcast; the skill only generates the template\n- ⊗ Hardcode `master` as the base branch -- delegate to the configured base branch from `task release --base-branch <branch>`\n- ⊗ Skip the post-create verify-isDraft gate (#724) -- a successful `gh release create` exit code does NOT prove the release actually landed in draft state; the 5-second poll-and-flip gate in `scripts/release.py` Step 11 is the only safety net against operator-error variants and partial-success races, and any manual recovery path that bypasses `scripts/release.py` MUST run `gh release view --json isDraft` followed by `gh release edit --draft=true` on `isDraft=false` before handing off to Phase 5\n- ⊗ Manually rewrite the Phase 8 Slack `*Summary*:` line to deviate from the CHANGELOG `[<version>]` blockquote -- the canonical narrative is authored ONCE at Phase 1 via `--summary` and propagates verbatim across all three audiences (CHANGELOG / GitHub release body / Slack). Per-audience hand-edits create documentation drift that the deterministic `--summary` flow is designed to prevent. If the operator wants Slack-specific tone, fold it into the canonical Phase 1 wording before passing `--summary`, OR amend the CHANGELOG blockquote BEFORE Phase 8 so all three surfaces stay aligned\n- ⊗ Export `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1` for the entire release session or wrap `task release` / `task ci:local` in it (#1553) -- the env var is process-wide and leaks into nested tests and temporary repos, producing false preflight failures. Prefer `task policy:allow-direct-commits -- --confirm` and restore with `task policy:enforce-branches` after the cut (closeout commit+push may use a **scoped** env prefix on those three git commands only — see Branch-Protection Policy Guard, #2623)\n- ⊗ Pass `--allow-coverage-debt=#N` unquoted on Windows PowerShell (#2621) -- `#` starts a comment and silently drops the issue number. Use `--allow-coverage-debt=N` or `--allow-coverage-debt=\"#N\"`\n- ⊗ Soft-pass coverage debt while an **open** coverage-debt issue from a prior hatch still exists (#2866 / #2573 / #3187) -- restore real branch coverage >= 85% and close the debt issue before reusing `--allow-coverage-debt` or expecting auto-hatch; the ledger is open GitHub issues, not prior CHANGELOG citations (#2618 superseded by open-issue ledger)\n- ⊗ Re-run the full Step 5 suite after a legal branch-only hairline when auto-hatch already filed `#N` and continued (`PASS_WITH_DEBT`) — that is the ceremony tax #3187 removes\n- ⊗ Trust `.deft/release-suite-stamp.json` in CI or after HEAD/tree drift (#3187)\n",
+      "body": "# Deft Directive Release\n\nStructured 8-phase workflow for cutting a v0.X.Y release of the deft framework. Operationalizes the `task release` / `task release:publish` / `task release:rollback` / `task release:e2e` surface introduced in #716 (safety hardening of #74).\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n**See also**: [deft-directive-swarm](../deft-directive-swarm/SKILL.md) Phase 6 Step 5 (Slack announcement template re-used by Phase 8 below) | [deft-directive-review-cycle](../deft-directive-review-cycle/SKILL.md) (user-gate pattern) | [deft-directive-refinement](../deft-directive-refinement/SKILL.md) (conversational phased flow).\n\n## Platform Requirements\n\n! GitHub as the SCM platform; the **GitHub CLI (`gh`)** must be installed and authenticated. The full pipeline plus the rehearsal target (`task release:e2e`) all dispatch through `gh`.\n\n## Branch-Protection Policy Guard\n\n! Before any Phase 1 state mutation, run the skill-level branch-policy guard documented in `scripts/policy.py` / `scripts/preflight_branch.py` (#746 / #747). Releases run on the configured base branch (default `master`), so the operator MUST be on the explicit-opt-in side of the policy before the pipeline starts writing files.\n\n**Preferred path — typed direct-commit policy opt-out (#1553).** For a release session on the default branch, prefer the audited typed flag over the emergency env-var bypass:\n\n```\ntask policy:allow-direct-commits -- --confirm\n```\n\nThis writes `plan.policy.allowDirectCommitsToMaster = true` on `xbrief/PROJECT-DEFINITION.xbrief.json` with a capability-cost disclosure. After the release completes (or if the session aborts), restore enforcement **and commit the restore in the same closeout** (#2623):\n\n```\ntask policy:enforce-branches\n# enforce flips the typed flag to false locally — the commit that lands that\n# flip cannot use the typed opt-in anymore. Scope the emergency env bypass to\n# ONLY this closeout commit+push (do NOT export it for the whole session):\nDEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1 git add xbrief/PROJECT-DEFINITION.xbrief.json meta/policy-changes.log\nDEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1 git commit -m \"chore(policy): restore branch protection after vX.Y.Z\"\nDEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1 git push origin HEAD\n```\n\n⊗ Leave `allowDirectCommitsToMaster=true` on origin after publish. ⊗ Run `policy:enforce-branches` and leave the dirty restore under protection ON without committing (forces a follow-up PR — the v0.79.0 / #2619 failure mode).\n\n**Branch-guard probe (either path).** Regardless of which opt-out path you chose, confirm the guard passes before Phase 1 mutates state:\n\n```\nuv run python scripts/preflight_branch.py --project-root . --quiet || exit 1\n```\n\nor invoke `task verify:branch`. This is the canonical surface that surfaces the policy state to the operator before the pipeline starts writing files. The release pipeline's other safety surfaces (the dirty-tree guard, base-branch check, `task ci:local` gate) remain independent of this check.\n\n**Emergency env-var bypass — narrow scope only (#1553).** `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1` is process-wide: every child process, nested test, and temporary repository spawned from the same shell inherits it. During the v0.43.0 release attempt, wrapping the entire `task release` invocation in this env var let the bypass leak into the Step 5 `task ci:local` preflight, which caused `TestWriteConsumerGitHooks_VendoredCommitBlocked_RealGit` to fail because the vendored test repo allowed a direct `master` commit the test expected the hook to block.\n\n- ! Prefer `task policy:allow-direct-commits -- --confirm` for release sessions instead of exporting `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1` for the whole shell.\n- ⊗ Wrap `task release`, `task ci:local`, or `task check` in `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1` -- the env var is inherited by every subprocess and can produce false preflight failures before any release mutation.\n- ? If the env-var path is unavoidable, scope it to a **single** branch-guard probe only (e.g. `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1 task verify:branch`) and do NOT export it for the release session. The release pipeline itself passes the bypass only in scoped subprocess `env=` for its authorised commit/tag/push mutations (#867); operators MUST NOT mirror that pattern at the shell level.\n\nThe release pipeline's Step 9/10/11 git mutations carry the bypass in subprocess `env=` only (`scripts/release.py::_release_subprocess_env`, #867) so the parent shell stays clean. Operator-side env-var exports defeat that isolation.\n\n## Deterministic Questions Contract\n\n! Every numbered-menu prompt rendered in this skill (Phase 1 version-bump magnitude check, Phase 2 dry-run review `yes`/`back`/`quit`, Phase 5 optional `defer`/`rollback`/`Discuss` (happy path auto-publishes after draft QA)) MUST follow [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md): the final two numbered options MUST be `Discuss` and `Back`, in that order. Existing `back`/`quit` options remain valid; this contract simply adds `Discuss` as a peer alongside `Back`. The Discuss-pause semantic is documented verbatim in the contract -- implicit resumption is forbidden.\n\n## When to Use\n\n- User says \"release\", \"cut release\", \"v0.X.Y\", \"publish release\", \"ship a release\"\n- The framework's `[Unreleased]` CHANGELOG section is non-empty and the operator wants to cut a tagged release\n- A previous release rehearsal succeeded and the operator is ready for the production cut\n\n## Phase 1 — Pre-flight\n\n! Validate the local + remote state before any irreversible action.\n\n\n### Parallel prep — #1880 Gap D (#2692)\n\n! Phase 1 long steps (`task reconcile:issues -- --apply-lifecycle-fixes`, cache refresh when ritual-stale, `task ci:local` / `task check`) and Phase 3 `task release:e2e` MUST be backgrounded or subagent-dispatched when the host supports it (Cursor: Task tool `run_in_background: true`), with progress surfaced via DONE/heartbeat — same ownership as review-cycle / merge-ready workers (#1880 Gap D). The operator conversation MUST stay interactive for version magnitude confirmation, `--summary`, and the Phase 2 dry-run `yes`/`back`/`quit` gate while prep runs.\n\n! **Checklist:** Phase 1 prep parallelized — long prep started in background before (or while) collecting version magnitude / summary / npm irrevocability disclosure.\n\n! On Windows PowerShell, do NOT wrap long task output in `Select-Object -Last` (it buffers until the process exits); stream to the terminal or log to a file and read incrementally. See `scm/github.md` § #2646 / Windows encoding guidance for related PS pitfalls.\n\n⊗ Foreground-block the operator chat on reconcile / `ci:local` / `release:e2e` when background dispatch is available (#1880 Gap D / #2692).\n\n### Fixable check failure — file-and-merge before resume (#2859)\n\n! When Step 4 (`task ci:local` or `task check`) fails on a **fixable product or test defect** (hang, failing test, validation bug — not operator env misconfiguration), the release cut MUST pause and route the blocker through normal issue → xBRIEF → feature branch → PR → merge before resuming Phase 1.\n\n? **Step 5 branch-coverage threshold misses** during `task release` (Vitest branch coverage below 85% with no other failure mode) are carved out to § Step 5 branch-coverage threshold — open-issue ledger hatch (#2866) below — not this file-and-merge path.\n\n**Required path:**\n1. File a GitHub issue with root cause, recurrence signature, and acceptance criteria.\n2. Ingest / promote / activate scope xBRIEF; implement on a feature branch with `drive-to: merge-ready`.\n3. Merge; confirm `task check` / `ci:local` is green for the failure mode.\n4. Resume the release cut from Phase 1 (re-run Step 4).\n\n⊗ Lead with an inline-only hotfix on the release branch / default branch without a tracked issue and merged PR.\n⊗ Suggest untracked `--skip-ci` or `--allow-skip-ci` without a **tracked issue number** as the first recovery when the failure is a clear, shippable bug.\n⊗ Continue the cut with \"raise timeouts,\" \"fix it here,\" or other shortcut theater before file-and-merge completes.\n\n? **`--skip-ci` / `--allow-skip-ci=#N` remains valid** only under explicit operator incident review with a **tracked issue** cited on the flag (Phase 4 contract). It is NOT a substitute for filing and merging a fixable defect discovered in Phase 1.\n\n**AGENTS.md bulk rejected (#2859):** Expanding `AGENTS.md` / `content/templates/agents-entry.md` with an always-on pin for this release-phase reminder was considered and **rejected**. This rule lives in the release skill (and optional lesson); do NOT add AGENTS.md / agents-entry bulk for it.\n\nSee [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Fixable check failure during release for the operator runbook and the existing `--allow-skip-ci=#N` incident contract.\n\n### Step 5 branch-coverage threshold — open-issue ledger hatch (#2866 / #3187)\n\n! When **`task release` Step 5** fails on Vitest coverage below the 85% goal, apply this hatch **only** when **branches** is the **sole** metric below 85% (hairline branch miss — lines, functions, and statements all ≥ 85%). Confirm via the Step 5 failure output, `coverage/coverage-final.json`, or `task coverage:hotspots` before hatching. If **any other metric** is also below 85%, or the failure is a hang / failing test / non-coverage defect, STOP — use § Fixable check failure — file-and-merge before resume (#2859) instead.\n\n**Runtime disclosure (#2573):** `--allow-coverage-debt=#N` sets vitest coverage thresholds to zero for the release Step 5 run (`vitest.config.ts`). The hatch is justified only for branch-only hairlines; the filed debt issue MUST require restoring **all four metrics** (lines, functions, branches, statements) to ≥ 85% before close.\n\n**Auto-hatch in `task release` Step 5 (#3187):** the pipeline classifies a non-zero Step 5 as `REAL_FAILURE` | `BRANCH_HAIRLINE` | `OTHER_COVERAGE` | `UNKNOWN` after **one** suite run.\n\n1. `REAL_FAILURE` | `OTHER_COVERAGE` | `UNKNOWN` → **fail closed** (no auto-issue). Route product defects via #2859.\n2. `BRANCH_HAIRLINE` + **any open** coverage-debt ledger entry → **fail closed** (\"restore coverage; close `#N` first\") — consecutive soft-pass ban (#2866).\n3. `BRANCH_HAIRLINE` + **empty** open debt ledger → **auto-file** `#N` with markers `coverage-debt` and `--allow-coverage-debt`, measured metrics, cut version, and acceptance (all four metrics ≥ 85%); mark Step 5 `PASS_WITH_DEBT(#N)`; **continue the cut without re-running vitest**. Loud stderr banner + cite `#N` in CHANGELOG / release notes.\n\n! **File before continue** — never soft-pass without a durable issue number.\n\n? Operators MAY still pass `--allow-coverage-debt=#N` manually (PowerShell-safe: `--allow-coverage-debt=N` or `--allow-coverage-debt=\"#N\"` — #2621) when re-running after a pre-filed debt issue.\n\n**SHA suite stamp (#3187, coordinates with #3188 check ordering):** after suite **green** or `PASS_WITH_DEBT`, write a local SHA-bound stamp under `.deft/release-suite-stamp.json` (gitignored). Re-entry at the **same clean HEAD** skips the suite; dirty tree or different HEAD invalidates the stamp. ⊗ CI never trusts the stamp (GHA has no committed stamp; `CI`/`GITHUB_ACTIONS` force miss).\n\n**Open-issue ledger (release-scoped only):**\n\n1. Check for an **open coverage-debt tracking issue** (unpaid hatch from a prior cut) — union all three probes and dedupe by issue number:\n   - **Marker search** (new-format debt issues):\n     ```\n     gh issue list --repo <owner>/<repo> --state open --search \"coverage-debt in:title,body\" --limit 20\n     gh issue list --repo <owner>/<repo> --state open --search \"allow-coverage-debt in:body\" --limit 20\n     ```\n   - **CHANGELOG citation scan** (legacy hatch issues filed before markers were mandatory): parse `CHANGELOG.md` `[Unreleased]` plus the last three `## [version]` sections for `--allow-coverage-debt=#N` / `allow-coverage-debt=#N` citations; for each `#N`, probe issue state via REST — `OPEN` (or unknown) counts as unpaid debt even when title/body lack the new markers (#2866).\n2. If **no open coverage-debt issue exists** → auto-hatch files `#N` (or operator files manually) with title prefix `coverage-debt:` and body containing both markers. The open `#N` remains WIP until coverage is restored and the issue is closed.\n3. If an **open coverage-debt issue from a prior hatch still exists** → ⊗ soft-pass again; restore real coverage (all four metrics ≥ 85%) and close the debt issue before the cut proceeds.\n\n**Framework-release-first (#3187):** auto-hatch applies to framework `task release` Step 5 (e.g. deftai/directive). Consumer expansion of auto-hatch via `plan.policy.coverageDebt` is reserved; consumer expansion is not implemented (#3314). Refuse when unset or off. Live hatch is `--allow-coverage-debt=#N` (#2866). Do not auto-file debt on the framework repo from consumer trees; consumer ledger is always the consumer repo.\n\n⊗ Auto-pass on a near-miss band without `#N` (#2573).\n⊗ Silent soft-pass with no tracked issue.\n⊗ File a debt issue without `coverage-debt` / `allow-coverage-debt` markers in title or body — the ledger query will miss it and permit a consecutive soft-pass (#2866).\n⊗ Use this carve-out when lines, functions, or statements are also below 85%, or for hangs, failing tests, or non-coverage Step 5 failures — those stay under #2859 file-and-merge.\n⊗ Treat file-debt-then-hatch as the default for ordinary PR / `task check` work outside a release cut — this hatch is release-scoped only.\n⊗ Trust a laptop suite stamp in CI or after HEAD/tree drift (#3187).\n\nSee [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Coverage debt hatch during release.\n\n### Routine vs hard cut for Step 5 (#2953)\n\n! Treat **hard cut** as the default: full Step 5 (`task check` + Vitest coverage) with no `--skip-ci`.\n\n~ Treat **routine cut** as the same full Step 5, sped up by default-excluding `.deft-scratch/` (and legacy `swarm-worktrees/`) from content/link/path/build-dist walks, plus pre-cut hygiene (green required checks on the tip SHA; prune stale `.deft-scratch/worktrees`).\n\n! Confirm required CI is green on the tip you will tag when aiming for a calm routine cut — green tip CI is a precondition, not a replacement for Step 5.\n\n⊗ Invent a silent lighter Step 5 that skips or soft-passes coverage without an explicit hatch (`--allow-coverage-debt=#N` for branch-only hairlines, or `--skip-ci` + `--allow-skip-ci=#N` for incidents). Silent soft-pass is forbidden in every mode.\n\n~ Prefer pruning abandoned worktrees / cutting from a clean clone over re-scanning scratch noise.\n\nSee [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Routine vs hard cut for Step 5 (#2953).\n\n\n~ **Frozen Go-installer bridge (#1912 / #1972 / #1987):** by default a release tag *above* the frozen line (the `LAST_GO_INSTALLER` constant in `packages/core/src/legacy-bridge/sot.ts`) will NOT rebuild the 6 Go binaries -- the CI `freeze-gate` job in `.github/workflows/release.yml` skips the build (the run stays green; npm still ships from the separate `npm-publish.yml`). If this release must rebuild the Go installer, follow the runbook in [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Frozen Go-installer bridge: roll `LAST_GO_INSTALLER` forward to the cut tag BEFORE tagging (pinning to the exact cut tag both releases the gate AND re-freezes at the new line), then see that section's \"After the release\" step for the re-pin.\n\n1. ! Verify the operator is on the configured base branch (default `master`) and the working tree is clean\n2. ! Confirm the next version number (`X.Y.Z`) with the user. Major / minor / patch decision flows from the `[Unreleased]` content (breaking change → major; new feature → minor; fix-only → patch)\n3. ! Inspect `[Unreleased]` content vs the proposed version bump. If a breaking change appears in `### Changed` / `### Removed` but only a patch is proposed, surface the mismatch and ask the user to choose\n4. ! Verify `task ci:local` passes locally (or `task check` as the graceful-degradation fallback per `tasks/release.yml` line 9-10). The `task release` script will refuse to proceed otherwise -- but Phase 1 catches it earlier — **on failure from a fixable defect, STOP and follow § Fixable check failure below (#2859); do NOT proceed to step 5**\n5. ! Verify `gh auth status` reports authenticated (`task release` will refuse otherwise)\n6. ! **Run `task reconcile:issues -- --apply-lifecycle-fixes` to clear any closed-issue / non-completed-folder xBRIEFs before invoking `task release`** (#734). The release pipeline carries the deterministic gate at Step 3 (`scripts/release.py::check_vbrief_lifecycle_sync`, refuses with `EXIT_VIOLATION` on any Section (c) mismatch), but Phase 1 is the operator's first-line defence -- running the apply-mode flag here is the canonical clean path; `--allow-vbrief-drift` on the pipeline exists only as the explicit-acknowledgment escape hatch (analogous to `--allow-dirty`). The recurrence record is the v0.21.0 cut, which surfaced 13 stranded xBRIEFs (8 cycle-relevant + 5 historical residue) post-publish; the gate now blocks that drift before any irreversible action\n7. ! **Verify the proposed `v<version>` tag is not already in use locally, on origin, or as a published GitHub release** (#784). The release pipeline carries the deterministic gate at Step 4 (`scripts/release.py::check_tag_available`, refuses with `EXIT_VIOLATION` before any state mutation -- CHANGELOG promotion, ROADMAP refresh, build, commit), but Phase 1 is the operator's first-line defence. Quickly probe with `git tag -l v<version>` (local), `git ls-remote --tags origin refs/tags/v<version>` (remote), and `gh release view v<version> --repo <owner>/<repo>` (release-only, where `gh release view` exits 0 only when the release exists). The recurrence record is the v0.22.0 → v0.23.0 release attempt on 2026-05-01: the operator typed `0.22.0` (the prior release from 12 hours earlier) and the legacy pipeline ran 8 steps before failing at `git tag` -- leaving a wrong-version local commit + `dist/deft-0.22.0.zip` orphan + manual `git reset --hard` recovery. The new pre-flight gate blocks that mode before any irreversible action\n8. ! **Verify the npm credential path is configured before cutting the tag** (#1910, #1909). A `v*` tag now auto-triggers `.github/workflows/npm-publish.yml`, which publishes the four `@deftai/directive*` packages with `npm publish --provenance`. Confirm the publish path can authenticate: either the `NPM_TOKEN` repo secret is present (`gh secret list --repo <owner>/<repo>` shows `NPM_TOKEN`) OR an npm OIDC trusted publisher is configured for the `@deftai/directive*` packages. If neither is in place, WARN loudly that the tag will fire a publish job that fails (red X on the tag, no packages) -- the operator may still proceed for a GitHub-only release, but the npm channel will not land until #1909's credential is provisioned. Cross-reference #1909.\n9. ! **Disclose npm irrevocability before any tag push (#1972, #2002, #3527).** A `v<version>` tag push is the **real npm publish gate** -- NOT Phase 5 or `task release:publish`. Tag push fires `.github/workflows/npm-publish.yml` in a separate workflow that is NOT draft-gated; npm packages ship immediately and **cannot be retracted** (`npm unpublish` is forbidden). Recovery is forward-only: deprecate, dist-tag, or ship a patch. The last human gates before npm goes live are: (a) Phase 2 dry-run `yes`, (b) a human-origin closed-verb grant (`deft authz:grant -- --template release-publish --target <version>` or `DEFT_ALLOW_RELEASE_PUBLISH=1`). `task release` fails closed at the Step 10–11 tag-push boundary without that grant. Phase 5 only controls GitHub release visibility (draft → public); it does NOT gate npm. The draft-flip `release:publish` closed-verb check remains (#1095).\n10. ~ Ask the operator for an optional one-line release **summary** (recommended 80-160 chars; can be skipped). The summary is the canonical narrative for THIS release across three audiences: (a) injected as a Markdown blockquote at the top of the promoted `CHANGELOG.md [<version>]` section, (b) auto-flowed into the GitHub release body via the existing `_section_for_version` pickup, and (c) populated VERBATIM into the Phase 8 Slack `*Summary*:` slot. Capture the wording once here; do NOT regenerate per-audience downstream\n\n⊗ Skip the version-bump magnitude check -- a patch release that ships breaking changes is the kind of regression that Repair Authority [AXIOM] (#709) is designed to prevent.\n\n⊗ Skip the xBRIEF-lifecycle-sync check (#734); the gate exists because operators consistently forget the manual `task scope:complete` move step. The v0.21.0 cut surfaced 13 stranded xBRIEFs (8 cycle-relevant + 5 historical residue) post-publish as the recurrence record this gate prevents. If `task release` reports `[3/13] Pre-flight xBRIEF lifecycle sync... FAIL (<count> mismatches; run task reconcile:issues -- --apply-lifecycle-fixes to fix)`, the canonical recovery is the apply-mode invocation -- `--allow-vbrief-drift` is reserved for cases where the operator has explicitly reviewed the drift and chosen to defer the lifecycle reconcile to the next refinement pass (e.g. an emergency hot-fix release).\n\n⊗ Skip the tag-availability check (#784); the gate exists because the legacy 12-step pipeline only invoked `git tag` at Step 9, after Steps 1-8 had already mutated state (CHANGELOG promoted, ROADMAP refreshed, dist built, release commit made locally). A duplicate-tag failure at Step 9 stranded the operator with an unpushed wrong-version commit + orphaned `dist/deft-<wrong>.zip` artifact + manual `git reset --hard` recovery (forbidden by AGENTS.md SCM rules without explicit permission). The recurrence record is the v0.22.0 → v0.23.0 release attempt on 2026-05-01. If `task release` reports `[4/13] Pre-flight tag availability... FAIL (<surface> tag v<version> already exists ...)`, the canonical recovery is to choose a different version (the most likely cause is operator typo of a prior release).\n\n⊗ Hand-write a different one-line narrative for each of the three downstream surfaces (CHANGELOG / GitHub release / Slack) -- that drift is exactly the gap the `--summary` flag is designed to close. If the operator insists on per-audience tone, populate the canonical `--summary` ONCE here and document the deviation in the Phase 8 anti-pattern.\n\n## Phase 2 — Dry-run review\n\n! Invoke `task release -- <version> --dry-run --skip-tag --skip-release` and present the plan to the user. If Phase 1 collected an operator summary, also pass `--summary \"<text>\"` so the dry-run preview reflects the canonical narrative the operator just authored.\n\n```\ntask release -- <version> --dry-run --skip-tag --skip-release --summary \"<text>\"\n```\n\nThe dry-run prints `[N/13] <step>... DRYRUN (would <action>)` for every pipeline step (Step 13 is the post-create verify-isDraft gate added by #724; Step 4 is the tag-availability pre-flight gate added by #784). Step 6 (CHANGELOG promotion) surfaces whether a summary was supplied (truncated to ~60 chars in the preview) so the operator can validate the wording before any file is written. Capture the output and present it to the user, then wait for explicit confirmation before continuing.\n\n! Wait for explicit user confirmation: `yes` / `back` / `quit`. Remind the operator that Phase 4's tag push will irrevocably publish npm (#1972) and requires a `release-publish` grant (or `DEFT_ALLOW_RELEASE_PUBLISH=1`) -- this `yes` is the last safe abort before that channel opens (#3527).\n- `yes` (or `confirmed` / `approve`) → proceed to Phase 3\n- `back` → return to Phase 1 for re-validation (e.g. user wants to amend the version or `[Unreleased]` content)\n- `quit` → abort the workflow cleanly; no state changes\n\n⊗ Skip the dry-run preview. The dry-run is the operator's last opportunity to catch a bad version number, malformed CHANGELOG, or wrong base branch before the pipeline starts writing files.\n\n## Phase 3 — E2E sanity\n\n! Invoke `task release:e2e` against an auto-created temp repo to verify the full pipeline shape works end-to-end before touching the real repo.\n\n! **#1880 Gap D (#2692):** `task release:e2e` is a long-running step — MUST background / subagent-dispatch it when the host supports it so Phase 2 confirmation and other human gates stay interactive. Do not wrap its output in PowerShell `Select-Object -Last`.\n\n```\ntask release:e2e\n```\n\nThe harness provisions `deftai/deftai-release-test-<ts>-<uuid6>`, runs the smoke-test rehearsal, and **by default keeps** the temp repo (#2572). Stderr always includes the full `owner/slug` and a copy-pasteable manual-cleanup command (`gh repo delete <owner>/<slug> --yes`). Privileged environments (CI or an operator with `delete_repo`) MAY pass `task release:e2e -- --destroy-repo` to attempt auto-delete; destroy failure emits a WARN and does **not** block Phase 4 when the rehearsal succeeded.\n\n! After Phase 3, the agent MUST NOT retry or escalate temp-repo deletion. Include any leftover temp repo(s) in the phase summary for the operator to clean up manually.\n\n! Treat a non-zero exit from `task release:e2e` as a hard refusal to proceed to Phase 4. Surface the diagnostic and ask whether to debug (return to Phase 1) or abort (`quit`).\n\n? **Skip allowed** when the operator has just run `task release:e2e` successfully against the same branch in the past 30 minutes. Note the prior run timestamp in the user-facing summary.\n\n! **`task release:e2e` now also rehearses the npm publish (#1910).** Unless `--skip-npm` is passed (or `npm` is absent from PATH, which soft-skips), the rehearsal runs `npm publish --dry-run --access public` for all four `@deftai/directive*` packages against the throwaway clone in dependency order (types -> core -> content -> cli), after `pnpm install` + `pnpm -w run build` and a version-alignment pass. This catches a broken `files` allowlist, a version-drift bug, or a dependency-order error BEFORE the real `v*` tag fires the publish workflow -- without touching the real registry. The install+build exceeds the <90s fast budget, so pass `task release:e2e -- --skip-npm` when you only need the GitHub-pipeline shape check.\n\n! **Tag -> npm coupling + irrevocability (#1910, #1972, #2002).** A `v<version>` tag is a TWO-channel action: the GitHub release (this skill's pipeline) AND `.github/workflows/npm-publish.yml`, which runs in a SEPARATE workflow that does NOT block the GitHub release and is NOT draft-gated. The npm workflow derives the published version from the tag (`${GITHUB_REF_NAME#v}`); this skill owns the version chosen in Phase 1. These MUST stay consistent -- the tag you cut IS the npm version that ships; there is no separate npm version bump. **npm publish is irrevocable** (#1972): once the tag fires, packages are live on npm and cannot be unpulled; `task release:rollback` does NOT retract npm (forward-only recovery). A red npm job on a green GitHub release means the npm channel did not ship (verify in Phase 5/7).\n\n## Phase 4 — Production draft\n\n! **Last human gate before npm (#1972, #2002, #3527).** Immediately before invoking `task release`, re-state that the tag push in this step will irrevocably publish all four `@deftai/directive*` packages to npm via `.github/workflows/npm-publish.yml`. There is no undo on npm; only forward recovery (deprecate / dist-tag / patch). Proceed only when the operator explicitly confirms **and** a human-origin grant covers `release-publish` for this version (`deft authz:grant -- --template release-publish --target <version>` or `DEFT_ALLOW_RELEASE_PUBLISH=1`). The pipeline fails closed at Step 10–11 without that grant -- that is the npm-distributing boundary. ⊗ Rely on Phase 5 `release:publish` as the npm gate; it only flips the GitHub draft. ⊗ Delete the draft-flip check as a substitute for the tag-push gate.\n\n! Invoke `task release -- <version>` (NO `--dry-run`, NO `--skip-tag`, NO `--skip-release`, NO `--skip-ci`). If Phase 1 collected an operator summary, pass `--summary \"<text>\"` so the production cut writes the same blockquote the dry-run previewed.\n\n⊗ Use `--skip-ci` on a production cut except under explicit operator incident review — it skips Step 5 vitest coverage and ships untested npm builds (#2652). When unavoidable, pass `--allow-skip-ci=#N` citing the tracked issue; Step 5 emits a loud WARN. See [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Vitest coverage hang recovery. The next patch after the hang fix must cut without `--skip-ci`.\n\n```\ntask release -- <version> --summary \"<text>\"\n```\n\nPer #716 default-draft hardening, this lands the release as a `--draft` on the real repo. Binaries upload via release.yml CI, but the artifact is NOT yet visible to consumers. The operator-authored summary becomes part of the promoted `CHANGELOG.md [<version>]` section AND the GitHub release body (auto-pickup via `_section_for_version`). The same wording is the canonical source for the Phase 8 Slack `*Summary*:` slot.\n\n! **Maintainer-mode release notes auto-lead with an \"Upgrading from an older version?\" banner (#1413).** When the cut targets the canonical framework repo (`deftai/directive`), `scripts/release.py` Step 12 prepends the banner from the editable template at `.github/release-notes/upgrade-banner.md` to the notes passed to `gh release create` (via `_prepend_upgrade_banner`). The banner points consumers at the canonical `deft-install --yes --upgrade --repo-root . --json` upgrade command and #1411. This is **GitHub-release-body-only** -- it is NEVER injected into `CHANGELOG.md`, so the CHANGELOG section and the release body intentionally differ by this leading block. To change the wording, edit the template file; do not hand-edit the published release body. **Consumer-mode releases (any non-`deftai/directive` repo) are unaffected** -- a downstream project that vendors the release pipeline never inherits deft's upgrade guidance. A missing/unreadable template degrades gracefully (notes ship without the banner; the cut is never blocked).\n\n! **Verify isDraft within 5 seconds; flip immediately if not (#724).** Immediately after `gh release create --draft` returns success, `scripts/release.py` Step 11 polls `gh release view v<version> --json isDraft` up to 5 times at 1-second intervals. If the release exists with `isDraft=false`, the pipeline auto-flips it via `gh release edit v<version> --draft=true` and emits a `WARNING: release landed as public; flipping to draft (defense-in-depth, see #724)` line. This closes the ~90-second public-exposure window observed during the v0.21.0 cut where a manual recovery created a public release before the operator noticed and flipped it. The verify gate is defense in depth even when `--draft` was passed correctly: it catches the case where `gh release create` partially succeeded (release record written, error returned) AND the operator-error variant where an alternate code path sent the release without `--draft`. A release-not-found-within-budget result emits a WARN and does NOT fail the pipeline (release.yml CI may still be processing).\n\n! Wait for `task release` to exit 0 before continuing. A non-zero exit means the pipeline halted partway through; consult Phase 7's `task release:rollback` recovery before retrying.\n\n⊗ Pass `--no-draft` here unless the operator has explicitly opted into direct-publish (e.g. automated security patch). The default-draft contract is the foundation of the safety hardening surface.\n\n⊗ Skip the post-create verify-isDraft gate -- the gate is the only reliable safety net against \"create call exited 0 but the release somehow landed as public\" variants (#724). If `task release` is invoked manually outside the canonical `scripts/release.py` flow, the operator MUST run `gh release view v<version> --json isDraft` followed by `gh release edit --draft=true` on `isDraft=false` BEFORE handing off to Phase 5.\n\n## Phase 5 — GitHub draft QA (optional; NOT the npm authority gate)\n\n! After `task release` exits 0, QA the **GitHub draft release** only. npm packages typically **already shipped** when the tag push in Phase 4 fired `.github/workflows/npm-publish.yml` (#1972, #2002). Phase 5 is NOT a \"user-only authority before going live\" gate for the release as a whole -- it is optional draft QA for GitHub assets, notes, and binaries.\n\n1. ! **Verify npm publish status FIRST (in parallel with draft inspection).** Run `gh run list --workflow=npm-publish.yml --repo <owner>/<repo> --limit 5` and confirm the tag run for `v<version>` is `completed`/`success`. If npm failed, surface immediately -- the GitHub draft QA is secondary to a red npm channel.\n2. ! Run `gh release view v<version> --json url,name,body,assets,isDraft --repo <owner>/<repo>` and present the output to the user\n3. ! Surface the asset list (size + filename) so the user can verify binaries uploaded correctly\n4. ! Surface the auto-generated release notes (or the CHANGELOG section that was promoted into the release body)\n\n### Happy path (default when npm succeeded and draft assets look correct)\n\n! When the npm workflow succeeded AND draft assets/notes pass inspection, **auto-proceed to Phase 6 Publish branch** -- run `task release:publish -- <version>` without a redundant human publish prompt (#2002). npm already shipped at tag push; waiting for a separate `publish` confirmation does not protect the npm channel.\n\n? **Operator override:** if the operator wants to hold the GitHub release in draft (e.g. embargo, last-minute notes edit), they MAY say `defer` before auto-publish runs.\n\n### Exception paths (operator-initiated)\n\n- `rollback` → proceed to Phase 6 (Rollback branch). **Reminder:** rollback unwinds the GitHub release only; npm packages already published at tag push are NOT retracted (#1972).\n- `defer` → halt and exit. Surface the draft URL so the operator can return later with `task release:publish -- <version>` or `task release:rollback -- <version>`.\n\n⊗ Treat Phase 5 as the npm publish-authority gate -- npm ships at tag push (Phase 4), not at `task release:publish`. A human `publish` prompt here is redundant when npm already succeeded and only delays flipping the GitHub draft to public.\n⊗ Skip npm workflow verification in Phase 5 and defer it entirely to post-publish Phase 7 -- npm status MUST be checked before or in parallel with the GitHub publish flip.\n\n## Phase 6 — Publish or rollback\n\n! Branch on the Phase 5 outcome. The happy path auto-enters the Publish branch when npm succeeded and draft QA passed (#2002).\n\n### Publish branch (happy path auto-run, or resumed after `defer`)\n\n```\ntask release:publish -- <version>\n```\n\nThe companion script flips `--draft=false`, then re-reads the release to verify `isDraft == false` actually flipped. State machine:\n- `draft` found → flip to public; verify; exit 0\n- already `published` → exit 0 no-op (idempotent re-runs are safe)\n- `not-found` → exit 1 (cannot publish a missing release)\n- gh-error → exit 1 with diagnostic\n\n! Wait for `task release:publish` to exit 0 before continuing. On the happy path this runs immediately after Phase 5 draft QA without a separate human publish prompt.\n\n### Rollback branch (user said `rollback`)\n\n```\ntask release:rollback -- <version>\n```\n\nThe state-aware unwind detects the post-release state and applies the matching tiered recovery. Time-windowed download-count guard:\n- release age `< 5 min` → threshold = 0 (rollback safe; nobody noticed yet)\n- release age `5-30 min` → threshold = max(`--allow-low-downloads`, 10) (filters bot fetches)\n- release age `> 30 min` → refuse without `--allow-data-loss`\n\nThree escape hatches (escalating warnings):\n- `--allow-low-downloads N` -- accept up to N downloads\n- `--allow-data-loss` -- accept any count (consumer impact)\n- `--force-strict-0` -- require exactly 0 regardless of release age\n\nRace-condition mitigation: `download_count` is double-read with a 5s sleep between reads; rollback only proceeds if both reads agree below threshold.\n\n! When the guard refuses, surface the recommendation to the user: rollback is risky on a released artifact with non-zero downloads. Prefer the **hot-fix path** (cut the next patch with a withdrawal note in `[Unreleased]/Changed` rather than deleting the broken release).\n\n! **`task release:rollback` does NOT retract npm (#1972, #2002).** Rollback unwinds GitHub release state (draft/public, tag, assets) only. npm packages published at tag push remain on the registry irrevocably. Recovery is forward-only: deprecate the bad version, move a dist-tag, or ship a patch release.\n\n## Phase 7 — Post-publish verification\n\n! Only enter Phase 7 if Phase 6 took the Publish branch (rollback branch ends here with the unwind log).\n\n1. ! **Re-verify npm publish landed (#1910, #1909, #2002).** Phase 5 checked workflow status before the GitHub publish flip; Phase 7 confirms registry truth AFTER `task release:publish`. For each of `@deftai/directive-types`, `@deftai/directive-core`, `@deftai/directive-content`, and `@deftai/directive`, run `npm view <pkg>@<version> version` (expect `<version>`) and confirm provenance on the npm page. A green GitHub release with missing npm packages means consumers cannot `npm i -g @deftai/directive@<version>` -- escalate immediately. (Real-registry verification depends on #1909's credential; until then verify workflow-run status and flag credential gaps.)\n2. ! Verify GitHub auto-closed the discrete-task issue(s) referenced via `Closes #N` in the release notes (mirrors `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 2)\n3. ! Run `gh issue view <N> --json state --jq .state` for each closed issue. If any didn't auto-close, manually close with `gh issue close <N> --comment \"Closed by release v<version> (squash auto-close did not trigger)\"` (Layer 1, #167)\n4. ! Verify ROADMAP.md correctness via `task roadmap:render` (the release pipeline already invoked this; Phase 7 is the second-pass sanity check)\n5. ! Verify binaries are downloadable from the public release URL: `gh release view v<version> --json assets --jq '.assets[].url'` and curl one to confirm 200 OK\n6. ! For any umbrella / staying-OPEN issue (`Refs #N`) referenced in the release notes, run the Layer 3 reopen sweep from `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 1: any protected issue that auto-closed MUST be reopened with a comment citing #701\n\n⊗ Skip the post-publish verification. The closing-keyword false-positive (Layer 1 / Layer 2 / Layer 3) and the incremental-renderer-drift (#641, #614) are exactly the kind of issues that surface only AFTER a release is public.\n\n## Phase 8 — Slack announcement\n\n! Generate the canonical Slack release announcement and present it to the user for copy-paste, re-using the template from `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 5.\n\nThe announcement block MUST include:\n\n```\n:rocket: *deft v<version>* -- <release title>\n\n*Summary*: <one-sentence description of the release scope>\n\n*Key Changes*:\n- <bullet per significant change, 3-5 items max>\n\n*Stats*: 1 release | ~<duration> elapsed | <N> commits since v<previous>\n*Release*: <GitHub release URL>\n```\n\n! Populate version from the freshly-published `gh release view v<version>` output. Populate release title from the CHANGELOG section heading (or the GitHub release title). Summarize key changes from the promoted `[Unreleased]` -> `[<version>]` CHANGELOG section (NOT raw commit messages). Populate stats from `git log v<previous>..v<version> --oneline | wc -l`.\n\n! Populate the `*Summary*:` slot VERBATIM from the operator-authored blockquote at the top of the CHANGELOG `[<version>]` section (the line beginning with `> ` immediately after the `## [<version>] - <date>` heading). The Phase 1 prompt + Phase 4 `--summary` flag exist precisely so this populate step is mechanical -- one canonical narrative authored once at Phase 1, propagated through Phase 4 promotion, and copy-pasted here without re-authoring. If the CHANGELOG section has no blockquote (operator skipped the Phase 1 prompt), generate a one-sentence summary from the `### Added` / `### Changed` bullets and surface to the operator that this is a regenerated narrative (NOT canonical) so they can decide whether to amend the CHANGELOG before publishing.\n\n! Present the block as a code-fenced snippet the user can copy directly. Do NOT post to Slack from inside this skill -- the user owns the actual broadcast.\n\n## Skill Completion\n\n! When Phase 8 completes (or when Phase 5 took the `defer` / `quit` path, or when Phase 6 completed the rollback branch), explicitly confirm skill exit:\n\n```\ndeft-directive-release complete -- exiting skill.\nNext: <one-line guidance>\n```\n\nWhere `<one-line guidance>` is one of:\n- \"release v<version> live -- monitor consumer reports for ~24h before cutting v<next>\"\n- \"release v<version> rolled back -- the underlying defect needs a hot-fix in the next CHANGELOG entry\"\n- \"release deferred -- resume by running `task release:publish -- <version>` (GitHub only; npm already shipped at tag push) or `task release:rollback -- <version>` (GitHub unwind only; npm is forward-recovery) when ready\"\n\n⊗ Exit silently without confirming completion or providing next-step guidance.\n\n## Anti-Patterns\n\n- ⊗ Foreground-block the operator chat on Phase 1 long prep (`reconcile:issues`, cache refresh, `ci:local` / `check`) or Phase 3 `release:e2e` when background / subagent dispatch is available (#1880 Gap D / #2692) — the interactive channel must stay free for version confirmation, `--summary`, and the Phase 2 dry-run gate\n- ⊗ Wrap long release-prep task output in PowerShell `Select-Object -Last` — it buffers until exit and makes the session look hung (#2692)\n- ⊗ Run `task release` without a Phase 2 dry-run preview -- the dry-run is the only safe place to catch a bad version, malformed CHANGELOG, or wrong base branch\n- ⊗ Skip Phase 3 (e2e rehearsal) on the assumption that \"the dry-run is enough\" -- the e2e harness catches gh-CLI auth issues, repo permission gaps, and pipeline-shape regressions that the dry-run cannot detect\n- ⊗ Pass `--no-draft` to `task release` without explicit operator opt-in -- the default-draft contract is the foundation of the safety hardening surface\n- ⊗ Invoke `task release` without `--skip-tag` when no `release-publish` grant or `DEFT_ALLOW_RELEASE_PUBLISH` is present -- the v0.105.0 cut published npm with no authz because the closed-verb check sat only on the later draft flip (#3527)\n- ⊗ Delete the `release:publish` draft-flip closed-verb check as a substitute for the tag-push gate -- placement, not strength; both stay (#3527 / #1095)\n- ⊗ Treat Phase 5 as the npm authority gate or require a redundant human `publish` prompt when npm already succeeded -- npm ships at tag push (#1972); Phase 5 is GitHub draft QA only\n- ⊗ Expect `task release:rollback` to retract npm packages -- rollback is GitHub-only; npm recovery is forward-only (deprecate / dist-tag / patch)\n- ⊗ Run `task release:rollback` against a release that has > 30 minutes of consumer-driven downloads without first weighing the hot-fix path -- a withdrawal note in the next patch is almost always less disruptive than deleting a public artifact\n- ⊗ Use `--allow-data-loss` without first reading the script docstring's hot-fix-path recommendation -- the flag is an explicit acknowledgment of consumer impact, not a default\n- ⊗ Skip the Phase 7 Layer 3 reopen sweep -- protected umbrellas can auto-close on a release-merge squash even when the release notes use `Refs #N` only\n- ⊗ Post the Phase 8 Slack announcement directly from this skill -- the user owns the broadcast; the skill only generates the template\n- ⊗ Hardcode `master` as the base branch -- delegate to the configured base branch from `task release --base-branch <branch>`\n- ⊗ Skip the post-create verify-isDraft gate (#724) -- a successful `gh release create` exit code does NOT prove the release actually landed in draft state; the 5-second poll-and-flip gate in `scripts/release.py` Step 11 is the only safety net against operator-error variants and partial-success races, and any manual recovery path that bypasses `scripts/release.py` MUST run `gh release view --json isDraft` followed by `gh release edit --draft=true` on `isDraft=false` before handing off to Phase 5\n- ⊗ Manually rewrite the Phase 8 Slack `*Summary*:` line to deviate from the CHANGELOG `[<version>]` blockquote -- the canonical narrative is authored ONCE at Phase 1 via `--summary` and propagates verbatim across all three audiences (CHANGELOG / GitHub release body / Slack). Per-audience hand-edits create documentation drift that the deterministic `--summary` flow is designed to prevent. If the operator wants Slack-specific tone, fold it into the canonical Phase 1 wording before passing `--summary`, OR amend the CHANGELOG blockquote BEFORE Phase 8 so all three surfaces stay aligned\n- ⊗ Export `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1` for the entire release session or wrap `task release` / `task ci:local` in it (#1553) -- the env var is process-wide and leaks into nested tests and temporary repos, producing false preflight failures. Prefer `task policy:allow-direct-commits -- --confirm` and restore with `task policy:enforce-branches` after the cut (closeout commit+push may use a **scoped** env prefix on those three git commands only — see Branch-Protection Policy Guard, #2623)\n- ⊗ Pass `--allow-coverage-debt=#N` unquoted on Windows PowerShell (#2621) -- `#` starts a comment and silently drops the issue number. Use `--allow-coverage-debt=N` or `--allow-coverage-debt=\"#N\"`\n- ⊗ Soft-pass coverage debt while an **open** coverage-debt issue from a prior hatch still exists (#2866 / #2573 / #3187) -- restore real branch coverage >= 85% and close the debt issue before reusing `--allow-coverage-debt` or expecting auto-hatch; the ledger is open GitHub issues, not prior CHANGELOG citations (#2618 superseded by open-issue ledger)\n- ⊗ Re-run the full Step 5 suite after a legal branch-only hairline when auto-hatch already filed `#N` and continued (`PASS_WITH_DEBT`) — that is the ceremony tax #3187 removes\n- ⊗ Trust `.deft/release-suite-stamp.json` in CI or after HEAD/tree drift (#3187)\n",
       "frontmatter_extra": null
     },
     {
@@ -272,7 +300,7 @@
       ],
       "path": "skills/deft-directive-review-cycle/SKILL.md",
       "version": "0.1",
-      "body": "# Deft Directive Review Cycle\n\nStructured workflow for responding to bot reviewer (Greptile) findings on a PR.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n## Principle Authority (#1471 / #212)\n\n! Universal review-cycle principles live in [`coding/review.md`](../../coding/review.md) (RFC2119): read-all-findings, severity P0/P1/P2 + merge-blocking semantics, single batch commit, cross-file grep of changed terms, local structured-data validation (SHOULD), no push mid-review, exit when no P0/P1 remain (P2 non-blocking), and post-merge closing-keyword verification.\n\n! This skill is the **Greptile + GitHub adapter** only: polling cadence, confidence-score thresholds, check-run detection, dual-source fetch (`gh` + MCP) for Comments Outside Diff, fail-closed Step 6 `ReviewerStatus`, review-monitor lease, and merge gates. Apply `coding/review.md` for the process; do not restate that principle list inline.\n\n~ Future adapters (CodeRabbit, Codacy, host babysit) SHOULD implement the same `coding/review.md` principles with their own mechanics.\n\n## Platform Requirements\n\n! This skill requires **GitHub** as the SCM platform and the **GitHub CLI (`gh`)** to be installed and authenticated. PR comment fetching, check-run queries, and review submission all depend on `gh`.\n\n\n## Ordered-plan exit / advance (#2402)\n\n! When the review-cycle exit condition is met (no P0/P1 remaining / CLEAN verdict):\n\n1. Return control to the caller — do **not** discover adjacent backlog work.\n2. If an ordered-plan sequence is active and this PR matched the current entry, run `task plan-sequence:advance`.\n3. If another entry remains, the caller may continue **only** to that entry (one unit).\n4. If the sequence is exhausted, stop and ask. Do not open another PR from queue intuition or chaining text.\n\n⊗ Exit the review cycle into `task triage:queue` or an unrelated PR without fresh operator approval.\n\n## When to Use\n\n- User says \"review cycle\", \"check reviews\", or \"run review cycle\" on a PR\n- Operator asks to **babysit**, **shepherd**, or **watch** a PR -- including the Cursor product action **babysit-pull-request-in-cloud** (#2261 / #1862 intent-routing class)\n- A bot reviewer (Greptile) has posted findings on an open PR\n- Dispatching a cloud or background agent to monitor and resolve PR review findings until merge-ready\n- Operator re-authorizes after conf-hold / dual-stop residual: **pursue residual**, **follow-up hard-stop**, **same as conf-hold**, **continue dual-stopped PR**, or **re-babysit residual** — route to § Operator follow-up after dual-stop / hard stop (#3273) **one-shot** path\n- Operator issues a **standing residual order**: **until floor or loop**, **until greptile meets policy**, or **pursue residuals until told otherwise** — route to the same § **standing** path (#3448); applies to open cohort / ordered-plan units, not only the last halted PR\n\n## Cursor global babysit supersession (#2261)\n\nOn repos with `.deft/core/` installed, **PR shepherding intent** routes here -- not the Cursor-global `babysit` skill (`~/.cursor/skills-cursor/babysit/SKILL.md`). The product action **babysit-pull-request-in-cloud** shares the babysit name but MUST chain into this review-cycle surface on Deft-managed projects.\n\n- ! Orchestrators dispatching cloud/background workers for PR shepherding MUST include `templates/agent-prompt-preamble.md` (or reference it) and mandate reading this skill as the first workflow step.\n- ! Cloud babysit workers use `worker_role: review-monitor` (or `drive-to: merge-ready` implementation workers that own the review cycle) -- not a generic babysit loop without Phase 1 audit or Step 6 exit predicate (#1259).\n- ⊗ Route **babysit-pull-request-in-cloud** to Cursor global babysit when `.deft/core/` is present -- that bypasses xBRIEF preflight, `task check`, Greptile fail-closed exit, and CHANGELOG discipline (#2261 recurrence).\n\n### OpenClaw babysit supersession (#2876 / #2261)\n\nOn OpenClaw hosts with Directive installed (`.deft/core/` or equivalent content deposit), **babysit / shepherd / watch** intent likewise routes here -- not host-local freestyle poll loops and not OpenClaw `cron` alone.\n\n- ! When the OpenClaw tool surface exposes `sessions_spawn`, Approach 1 is the **default** babysit path: spawn a background review-monitor via `sessions_spawn` (register with `--platform-primitive sessions_spawn` or the alias `openclaw-sessions-spawn`).\n- ! Prefer a **visible** Control UI subagent (`visible:true` when the tool surface allows) when OpenClaw Control UI is the operator control plane so humans can inspect the monitor (#3044; invisible empty settles are higher FC04 residual risk).\n- ! Long review-monitor ownership (>~3 min) MUST NOT block the parent OpenClaw session — background `sessions_spawn` + parent yield; same Gap D rule as Cursor/Grok Build (#1880).\n- ! Prefer deep-think gates inside the monitor via the dual-invoke probe order (#2893): `deft pr:watch` / `deft pr:merge-ready` first, then `task deft:pr:watch` when the Taskfile include is present, then the #2878 gh-only fallback — bare `task pr:watch` is not the consumer form.\n- ⊗ Treat OpenClaw `cron` (or any host scheduler alone) as Approach 1. Cron/timer re-invocation is Approach 2 only when `sessions_spawn` is unavailable.\n- ⊗ Freestyle main-session `gh pr view` / `sleep` poll + ad-hoc cron when `sessions_spawn` is available — that is the statusreport#153 / #2876 process-routing failure mode.\n\n## Branch-Protection Policy Guard\n\n! Before entering the review/fix loop, run the skill-level branch-policy guard (#746 / #747). Halt before any state mutation if the project's `plan.policy.allowDirectCommitsToMaster` is unresolvable AND the operator has not set `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1`. Concretely:\n\n```\ntask verify:branch || exit 1\n```\n\nThe skill MUST NOT modify files, push, or comment on the PR until the guard passes -- this catches the case where a malformed PROJECT-DEFINITION quietly disabled the policy and the agent would have committed directly to master mid-review.\n\n## Deterministic Questions Contract\n\n! Every numbered-menu prompt rendered in this skill (Phase 1 audit gates, Phase 2 Step 4 monitoring approach selection, Phase 5->6 ready-to-merge gate, Step 6 exit-condition prompts) MUST follow [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md): the final two numbered options MUST be `Discuss` and `Back`, in that order. The Discuss-pause semantic is documented verbatim there -- on `Discuss` selection the agent MUST halt the in-progress sequence immediately, prompt `What would you like to discuss?`, and resume only on an explicit user signal (re-asking the original question, saying `resume`/`continue`, or re-issuing the prior selection). Implicit resumption is forbidden.\n\n## Pre-Flight Check\n\n! Before entering the review/fix loop, verify the Greptile configuration supports it:\n\n1. ! `triggerOnUpdates` must be enabled (via Greptile dashboard or `.greptile/config.json`) — without this, Greptile only reviews the initial PR and never re-reviews after fix pushes, so the loop cannot reach the exit condition\n2. ~ `statusCheck` should be enabled so Greptile posts a `\"Greptile Review\"` check run on each commit — this is the signal the org ruleset uses to gate merges\n3. ? If Greptile does not re-review after a push despite `triggerOnUpdates` being enabled, comment `@greptileai` on the PR as a manual re-trigger fallback\n\n! Greptile posts **check runs** (GitHub Checks API), not **commit statuses** (Statuses API). To verify the check run is present on a commit:\n\n```\ngh api repos/<owner>/<repo>/commits/<sha>/check-runs --jq '.check_runs[] | select(.name == \"Greptile Review\")'\n```\n\n⊗ Use `commits/<sha>/statuses` to check for Greptile — that endpoint will always be empty.\n\n~ See `tools/greptile.md` for recommended dashboard and per-repo settings.\n\n## Phase 1 — Deft Process Audit\n\n! Before touching code, verify ALL prerequisites are satisfied. Fix any gaps first:\n\n1. ! Verify `skills/deft-directive-pre-pr/SKILL.md` was run before PR creation -- the PR branch should have passed at least one full pre-PR cycle (Read-Write-Lint-Diff). If not, run it now before proceeding.\n2. ! `PROJECT-DEFINITION.xbrief.json` and `xbrief/` lifecycle folders have scope xBRIEF coverage for all changes in the PR\n3. ! `CHANGELOG.md` has entries under `[Unreleased]` for the PR's changes\n4. ! `task check` passes fully (fmt + lint + typecheck + tests + coverage ≥75%)\n5. ! `.github/PULL_REQUEST_TEMPLATE.md` checklist is satisfied in the PR description\n6. ! If the PR touches 3+ files: verify a `/deft:change` `proposal.xbrief.json` exists in `history/changes/` for this branch and was explicitly confirmed by the user (affirmative response, not a broad 'proceed'), or document N/A with reason in the PR checklist\n7. ! Verify the PR is on a feature branch -- work MUST NOT have been committed directly to the default branch (master/main)\n\n~ **PR scope gate:** If the PR spans 3+ unrelated surfaces (e.g. a skill, a tool doc, and a strategy -- with no shared issue or scope xBRIEF linking them), warn the user that broad PRs increase review churn and Greptile noise. Recommend splitting into focused PRs unless all changes trace to the same scope xBRIEF or issue bundle.\n\n! Phase 1 audit gaps must be resolved before merging — but hold the fixes (do NOT commit or push them independently). Proceed to Phase 2 analysis to gather bot findings, then batch all Phase 1 + Phase 2 fixes into a single commit.\n⊗ Commit or push Phase 1 audit fixes independently before gathering Phase 2 findings.\n\n## Phase 2 — Review/Fix Loop\n\n### Step 1: Fetch ALL bot comments\n\n! Retrieve findings using BOTH methods — each catches different comment categories:\n\n```\ngh pr view <number> --comments\n```\n\n! Use `do_not_summarize_output: true` — summarizers silently drop the \"Comments Outside Diff\" section from large bot comments.\n\n~ **Oversized output fallback:** If `do_not_summarize_output: true` produces output too large to process, extract the relevant section with:\n\n- **PowerShell (Windows):** `gh pr view <number> --comments | Select-String \"Outside Diff\" -Context 50`\n- **Unix/macOS:** `gh pr view <number> --comments | grep -A 50 \"Outside Diff\"`\n\nBoth commands extract the \"Comments Outside Diff\" section with surrounding context, avoiding the need to process the full output.\n\n~ **Windows + Grok Build (#1353):** Avoid `|`, `>`, or `2>&1` in `run_terminal_command` strings -- use Python `pathlib`/`subprocess` or plain task commands instead.\n\n! **MCP capability probe** (mirrors deft-directive-swarm Phase 3 pattern): Before attempting MCP `get_review_comments`, probe whether MCP GitHub tools are available in the current session. Detection: attempt a lightweight MCP call (e.g. list available tools or a no-op query) -- if it succeeds, MCP is available; if it errors or the tool is not in the available set, MCP is unavailable.\n\n- **MCP available**: ! Use MCP `get_review_comments` as the second source to catch Comments Outside Diff.\n- **MCP unavailable** (e.g. non-MCP agents including `start_agent` / `spawn_subagent` (\"grok-build\") dispatch, cloud agents, `oz agent run`): ! Use `gh api repos/<owner>/<repo>/pulls/<number>/comments` as the explicit fallback for the second review source. Document in the commit message or PR comment why MCP was skipped (e.g. \"MCP unavailable in this session -- used gh api fallback for review comments\"). The platform descriptor from runtime detection determines MCP availability independently of the dispatch primitive.\n\n⊗ Report \"all comments resolved\" without verifying both sources.\n⊗ Skip the second review source without probing for MCP capability and documenting the fallback used.\n\n~ **Late-arriving bot review re-check:** If the initial dual-source fetch returns no bot review on the current HEAD SHA, wait ~60s and re-fetch before evaluating the Step 6 exit condition. Bot reviewers (Greptile) typically land within 3-7 min of PR creation/push; an empty first pass is more likely \"review pending\" than \"review clean\".\n\n⊗ Declare the exit condition met based on a single fetch that returned no bot review — re-fetch at least once after a ~60s delay first.\n\n~ This codifies a user-rule precedent on late-arriving bot reviews into the deft-internal deterministic tier. The [`templates/swarm-greptile-poller-prompt.md`](../../templates/swarm-greptile-poller-prompt.md) loop body already handles the same case for push-driven cycles via its per-poll fetch -- the rule above closes the orthogonal cold-start path where the one-shot review-cycle entry runs on a freshly-opened PR before any fix push has triggered the Step 4 polling loop.\n\n### Step 2: Analyze ALL findings before changing anything\n\n! Apply [`coding/review.md`](../../coding/review.md) before any code change: read **all** findings, classify P0/P1/P2, and plan **one** batch. Do not start per-finding fixes mid-read.\n\nGreptile adapter analysis extras:\n\n- Identify cross-file dependencies (a term, value, or field mentioned in multiple files)\n- ! **Scope-check each finding against the active story xBRIEF** (`plan.items[].narrative.Acceptance`) before coding — see Out-of-AC gate (#2881) below\n\n### Out-of-AC findings / active-story scope gate (#2881)\n\nBabysit and review-cycle are **not** a second unbounded implementation mandate. When Greptile (or another reviewer) raises design-adjacent work outside the active story's acceptance criteria, default to follow-up — not silent redesign mid-babysit (PR #2871 / #2869 → #2880 recurrence).\n\n! Given an active story xBRIEF with fixed `plan.items`, when a finding is **outside** those Acceptance criteria:\n\n1. ! File or propose a **follow-up** GitHub issue / scope xBRIEF for the out-of-AC work, **or**\n2. ! Amend the active brief's `plan.items` (and narratives) **with explicit operator consent** before implementing a new subsystem,\n3. ! Then continue babysit only for in-AC and carve-out findings.\n\n! **P0 carve-out vs new-subsystem-needs-story:**\n\n- ! P0 security / correctness defects on files **already touched** by the PR MAY land in the same PR without a new story.\n- ! New ledgers, idempotency protocols, cross-cutting reliability contracts, or multi-commit redesigns that expand story meaning **require** a separate story or an amended brief before code.\n\n**Leftover classes (A/B/C, #3448):**\n\n| Class | What it is | Auto-continue? |\n|-------|------------|----------------|\n| **class A** — named leftover on already-touched files | Wrong remediation, dropped field, fixture, same-module hole on files this PR already owns | **in-AC residual.** Continue until the resolved `#3095` floor or same-fingerprint loop |\n| **class B** — new subsystem / AC fight | New ledger, protocol, cross-cutting contract, or work that expands story meaning | Park or file follow-up. Do not expand mid-babysit |\n| **class C** — score-only, no concrete finding | Confidence below the resolved floor, 0 P0/P1, no named leftover | Document / same-as-conf-hold / operator floor this-PR-only. Not unbounded redesign |\n\n! **Already-touched leftover is class A (#2881 / #3448):** a leftover on files **already in the PR** is class A (in-AC residual) unless it needs a new ledger, protocol, or story.\n\n! **Confidence-only holds (0 P0/P1):** when confidence is below the **resolved `#3095` floor** (`plan.policy.review.minGreptileConfidence`: typed project policy > framework dogfood **5** > consumer default **4**; inspect `task policy:show --field=minGreptileConfidence` / `deft policy:show --field=minGreptileConfidence`) with zero P0 and zero P1 findings, the skill does **not** mandate unbounded redesign to raise confidence. That is class C unless a named leftover on already-touched files makes it class A. Offer one of:\n\n1. Follow-up issue / residual-risk note in the PR,\n2. Operator override path (document in PR comment),\n3. Minimal in-AC polish only — then re-evaluate Step 6.\n\n! **`issue:emit` related-ref footgun:** `task issue:emit` treats any `plan.references[]` entry whose type matches `github-issue` / `x-xbrief/github-issue` / `x-vbrief/github-issue` as **already tracked** and SKIPs creating a new issue. When linking **related** (non-primary) work:\n\n- ! Use a non-emit-tracking type for related issues (e.g. keep related links in narratives / PR body / `Refs #N` prose), **or** designate a single primary origin github-issue ref that emit should honor.\n- ⊗ Add related-issue `x-*/github-issue` refs to a brief that still needs `issue:emit` for its primary origin — emit will SKIP as already tracked.\n\n⊗ Expand active story scope past xBRIEF AC mid-babysit without follow-up or consented amend (#2881).\n⊗ Treat confidence-only holds as authorization to invent new subsystems in-tree.\n\n\n### Dual stop — review fix loops (#2442)\n\nReview fix cycles are multi-iteration work and MUST carry dual stop (`main.md` `## Dual Stop Rule (#2442)`). Single-turn re-checks are exempt.\n\n**Defaults for this skill (override only with an explicit operator envelope):**\n\n| Loop class | Success stop | Default failure stop |\n|------------|--------------|----------------------|\n| Greptile / bot fix batch (Step 3 → re-review) | No P0/P1 on current HEAD; confidence meets `minGreptileConfidence` | **max 3** fix-batch iterations across the whole review ownership (do **not** reset the counter on push when the same primary fingerprint remains) **or** the **Same-fingerprint stop** (below) |\n| Confidence-only hold (0 P0/P1, score below floor) | Confidence meets floor, or operator chooses document/accept path | **max 1** optional polish pass, then stop (do not redesign unbounded — see confidence-only holds above) |\n\n**On failure stop:**\n\n- ! Halt automatic re-fix. Prefer `BLOCKED:` with PR number, HEAD SHA, blocker class (`review_cycle_cap` / `greptile_p0_p1` / `conf_floor` / `no_progress`), what was tried, and human decision needed (preamble §11 / #2843).\n- ! **Halt-report resume line (MUST, #3273 / #3448):** End the terminal halt with leftover class (A/B/C) + residual class + conf (if any) + resolved `#3095` floor + standing vs one-shot + PR URL. Example: `RESUME: residual=<class> leftover=<A|B|C> conf=<n/5|n/a> floor=<resolved min|n/a> standing=<yes|one-shot> PR=<url>`. One-shot phrases: **pursue residual** | **follow-up hard-stop** | **same as conf-hold** | **continue dual-stopped PR**. Standing phrases: **until floor or loop** | **until greptile meets policy** | **pursue residuals until told otherwise**. Skill pointer to § Operator follow-up after dual-stop / hard stop (#3273). Same affordance shape as swarm `references/core-phase-4.md`.\n- ⊗ Continue silent fix rounds after the envelope is exhausted.\n- ⊗ Reset the fix-batch counter solely by re-pushing, empty-committing, or swapping workers when the same primary finding fingerprint remains (poll-wait timer MAY reset for a new HEAD; the dual-stop fix-batch counter MUST NOT).\n\n**Enforcement note:** skill defaults are behavioral. Durable delivery/acceptance circuit breaker: **#3143** `packages/core/src/delivery-attempt/` (`evaluatePreDispatch`). Docs: `docs/delivery-attempt.md`.\n\n### Operator follow-up after dual-stop / hard stop (#3273)\n\nOperator-initiated resume after conf-hold, residual dual-stop, or hard-stop exit — **not** automatic re-thrash. Composes Greptile floor (#3095) and advisory should-not-merge (#3225). Portable consumer + maintainer (`task` / `deft` dual-invoke). Continue-until target is the **resolved `#3095` floor** (`plan.policy.review.minGreptileConfidence`: typed project policy > framework dogfood **5** > consumer default **4**; inspect `task policy:show --field=minGreptileConfidence` / `deft policy:show --field=minGreptileConfidence`). ⊗ Hard-code 5/5. ⊗ Lower project policy to clear one PR.\n\n**One-shot vs standing (#3448):**\n- **One-shot** triggers: pursue residual · follow-up hard-stop · same as conf-hold · continue dual-stopped PR · re-babysit residual — **one** pass on the unit that just halted, then re-stop. Do not silently widen.\n- **Standing** triggers: **until floor or loop** · **until greptile meets policy** · **pursue residuals until told otherwise** — class A leftovers on **every open unit in the active cohort / ordered plan** keep moving until the resolved floor or the **Same-fingerprint stop** (this skill, Dual stop). Class B/C stay parked unless the operator names them.\n\n**One residual pass under operator consent (one-shot, or one standing batch):**\n1. Ground-truth: dual-invoke `pr:merge-ready` / `pr:watch --one-shot` (#2893). Classify leftover A/B/C (#2881 table above).\n2. Apply **one** residual fix batch **or** one re-review wait — not both as an unbounded loop.\n3. If operator authorized a conf floor for **this PR only** (e.g. ≥4/5): post a PR audit comment (floor, HEAD SHA, authorizer). That is the human-merge / documented-override trail — it does **not** rewrite policy or make `pr:merge-ready` / `pr:watch` CLEAN below `minGreptileConfidence`. ⊗ Silent policy edit for one residual.\n4. Re-evaluate Step 6; merge when **policy** floor + gates met, or human-merge after the documented PR-local floor is met in the bot body; else halt again with a fresh resume line (leftover class + resolved floor + standing vs one-shot).\n5. Post-merge `scope:complete` when this owner holds lifecycle (#2321 / #3264).\n\n! **Same-fingerprint stop (normative, #3448 / #2442):** **2 consecutive re-review observations**, **same primary fingerprint**, **no material fix between**. **Blocked handoffs count as observations.** After a real fix, a *new* leftover MAY take another batch. `#2442` batch cap (max 3 fix-batches) still applies.\n⊗ Restate a competing 2-vs-3 same-fingerprint threshold, or treat a `BLOCKED` handoff as not counting toward the stop.\n\n! Dual-stop re-entry: one residual pass then re-stop without new consent **unless** a standing order is active **and** the leftover is class A with a **new** fingerprint under the `#2442` cap. Fresh operator consent required for another one-shot pass, or after same-fingerprint / cap halt.\n\n⊗ Unlimited auto-retry after dual-stop without new operator consent (#3273 / #2442).\n⊗ Treat conf-only holds as authorization for unbounded redesign (#2881).\n⊗ Lower project-wide `minGreptileConfidence` for one residual.\n⊗ Treat one-shot `pursue residual` as a standing order, or park a class A leftover on already-touched files because the score is below 5.\n\n### Step 3: Fix all findings in ONE batch commit\n\n! Apply [`coding/review.md`](../../coding/review.md) single-batch, cross-file grep, and local structured-data validation rules. Land **all** in-scope fixes in one commit (or one intentional batch), never per-finding pushes.\n\nGreptile adapter pre-commit gate:\n\n- ! Before committing any Greptile fix, re-read the FULL current Greptile review and confirm all P0/P1 issues are addressed in the staged changes — this is the pre-commit gate that prevents per-finding fix commits\n- ! Run `task check` before committing\n- ! **Fail-loud completion claim (#1006)**: when reporting fix-batch completion (to the user, in the commit message, in a PR comment, or in a status message to a parent agent), MUST surface the OUTCOMES not the intent -- name the P0/P1 finding count addressed (\"addressed 3/3 P0 findings, 2/2 P1 findings, 0 deferred\" -- NOT \"all findings addressed\"), report the `task check` result with the test-collection counts (\"task check: 412 collected, 412 passed, 0 skipped, 0 xfailed\" -- NOT \"task check passed\"), and explicitly call out any finding intentionally deferred with the reason. Apply `coding/coding.md` `## Fail Loud: Completion Claims Require Outcome Verification (#1006)` to every claim emitted during the review cycle\n- ⊗ Claim \"all Greptile findings addressed\" without verifying that the staged fix actually closes every P0/P1 currently surfaced in the review body -- a fix that addresses 3 out of 4 P1 findings and reports completion is the exact failure mode #1006 forbids\n- ⊗ Claim \"task check passes\" when any test was skipped, xfailed, or run with errors suppressed -- report the full collection counts instead (#1006)\n- ? **Pre-existing failure carve-out**: If `task check` fails due to a pre-existing issue unrelated to the PR's changes, a partial test suite run is acceptable ONLY if BOTH conditions are met: (a) the `task check` failure is pre-existing with an open GitHub issue number tracking it, AND (b) the PR description explicitly notes the failure and includes the issue reference (e.g. \"task check: test_foo fails due to #NNN (pre-existing)\"). Without both conditions, the full `task check` pass remains mandatory.\n- ~ Commit message: `fix: address Greptile review findings (batch)`\n\n### Step 3b: Proactive test coverage scan\n\n! After committing the fix batch but before pushing, scan the changed lines for untested code paths:\n\n1. ! Run `git --no-pager diff HEAD~1 HEAD --name-only` to identify files touched in the fix batch\n2. ! For each changed file that has a corresponding test file, review whether the fix introduced or modified logic that lacks test coverage\n3. ! If untested code paths are found, write tests and amend them into the fix batch commit (or add as a second commit in the same push)\n4. ! Run `task check` again after adding tests to verify they pass\n\n~ This eliminates one CI round-trip per fix cycle — catching coverage gaps before CI does.\n\n⊗ Push fix commits without scanning for untested code paths in changed files.\n\n### Step 4: Push and wait\n\n! Push the batch commit, then wait for the bot to review the latest commit.\n\n! After pushing, the agent MUST autonomously poll for review updates and continue the review cycle without stopping to ask the user. Do not pause for confirmation, do not ask \"should I continue?\", do not wait for user input between push and review completion. The review/fix loop is designed to run to the exit condition without human intervention.\n\n! Mid-review push rule: see [`coding/review.md`](../../coding/review.md) (no push while review in progress). Adapter rationale: every push re-triggers Greptile and resets the review clock.\n\n⊗ Push any additional commits — including unrelated fixes, doc updates, or lessons — while waiting for the bot to finish reviewing the current head. If you discover additional work while waiting, stage it locally but do NOT push until the current review completes.\n\n\n\n### Greptile CLEAN vs CI holdout (`pr:watch` / #2688)\n\n! When waiting on a Greptile verdict for a `drive-to: merge-ready` worker (or any review-cycle owner), prefer the dual-invoke probe order below over ad-hoc sleep loops (#1056 / #2893). Parse `clean_gate_holdout` on every probe.\n\n### Gates-surface dual invoke order (#2893 / #2878)\n\nDeep-think gates (`pr:watch`, `pr:merge-ready`, `review-monitor:*`) have **three ordered invoke paths**. Agents MUST probe in this order; bare `task pr:watch` is **not** the sole (or first) consumer form.\n\n! **Probe order (MUST):**\n\n1. **`deft` / `directive` CLI first** — attempt `deft pr:watch --help` (or `directive pr:watch --help`). Primary for npm/package-manager installs; works without a root Taskfile. CLI forms take flags **without** go-task's bare `--` separator (e.g. `deft pr:watch <N> --json`, `deft verify:review-monitor --pr <N>`).\n2. **`task deft:<verb>` second** — when a root Taskfile includes `.deft/core/Taskfile.yml` under key `deft:`, go-task exposes **namespaced** tasks (`task deft:pr:watch`, `task deft:verify:review-monitor`, `task deft:review-monitor:register`). Probe `task --list` / `task deft:pr:watch -- --help`. Task forms **require** the bare `--` separator before verb flags (e.g. `task deft:pr:watch -- <N>`, `task deft:verify:review-monitor -- --pr <N>`).\n3. **#2878 gh-only fallback last** — only when both CLI and namespaced task probes fail, classify **missing-task: pr:watch** (or **missing-task: review-monitor**) and use the official gh-only subset below.\n\n⊗ Treat bare `task pr:watch` / `task review-monitor:register` as the only prescribed consumer form — under include key `deft:` those un-namespaced names are absent; that probe failure is not proof the gate is unavailable if `deft` or `task deft:` works (#2893).\n⊗ Pass go-task's bare `--` separator into `deft`/`directive` CLI forms (e.g. `deft pr:watch -- --help`) — CLI parsers reject the standalone `--` and the probe fails falsely (#2893).\n\n### Missing gate surface / consumer gh-only fallback (#2878)\n\nSome consumer repos (e.g. sister product deposits) ship Directive skills but have **no working invoke path** for `pr:watch` / `review-monitor:*` (no `deft` CLI on PATH, no Taskfile include → no `task deft:…`). Agents MUST NOT invent a non-skill poll loop when every probe fails.\n\n! **After dual-invoke probe fails (#2893):** classify the session as **missing-task: pr:watch** (or the specific verb) and fail-loud:\n\n```\nBLOCKED: missing-task pr:watch on this consumer\nRemediation:\n  1. Prefer `deft pr:watch` / install `@deftai/directive` so the CLI surface works, OR\n  2. Add the root Taskfile include (doctor gates-surface snippet) so `task deft:pr:watch` works, OR\n  3. Use the official gh-only fallback subset below (still this skill — not freestyle).\n```\n\n! **Official gh-only fallback** (when both `deft`/`directive` and `task deft:<verb>` probes fail for pr:watch / review-monitor):\n\n1. Still select Approach 1 when a sub-agent primitive exists (OpenClaw `sessions_spawn`, Cursor `Task`, Claude Code `Agent`, `spawn_subagent`, `start_agent`) — spawn a review-monitor that runs the gh-only loop; do not block the parent.\n2. **Do not call** gate verbs via any surface the probe showed absent — those invocations cannot succeed and must not gate the spawn.\n3. Ownership claim without the tasks: post/update the sticky `<!-- deft:review-owner -->` PR comment via `gh api` (same field shape as the task-written lease) **or** keep ownership in the parent and document `missing-task: review-monitor` in the PR/parent handback. Never invent `.deft/review-monitor.json`.\n4. Poll with adaptive cadence (20-30s / 60s / 90s) using:\n   - `gh pr view <N> --comments` (dual-source + Step 1 rules still apply)\n   - `gh pr checks <N>`\n   - `gh api repos/<owner>/<repo>/pulls/<N> -q .head.sha` for HEAD pin\n   - `gh api repos/<owner>/<repo>/commits/<sha>/check-runs` for Greptile terminal check-run\n5. Evaluate the same Step 6 fail-closed all-of (terminal check-run + HEAD SHA + Last reviewed commit + confidence meets resolved min (policy/dogfood/default; see Step 6 #3095) + no P0/P1).\n6. Surface missing-task once to the operator/parent on first detection; do not silently rebrand freestyle sleep as `pr:watch`.\n\n⊗ Fake a successful `pr:watch` or `review-monitor:*` gate when every dual-invoke probe failed.\n⊗ Block Approach 1 / parent yield on missing `review-monitor:*` after the dual-invoke probe — use the gh lease claim or parent-owned gh-only poll instead (#2878).\n⊗ Invent ad-hoc `sleep` / main-session poll / OpenClaw cron loops outside Approach 1–3 when the skill already names this fallback (#2878 / statusreport#153 recurrence).\n⊗ Skip Step 6 fail-closed fields because deterministic tasks are missing — the gh surfaces above remain mandatory.\n\n! When `clean_gate_holdout=ci_failures` and Greptile otherwise satisfies the probe-side Step 6 fields (SHA match on HEAD, confidence meets resolved min (policy/dogfood/default; see Step 6 #3095), no P0/P1, not errored): **MUST NOT** idle-poll hoping CI heals. Treat Greptile CLEAN + CI red with the **same ownership** as a Greptile P0 for a merge-ready worker — one fix batch, re-push, re-probe.\n\n! On persistent `ci_failures` holdout: exit the Greptile wait immediately, fetch failing check annotations (`gh pr checks <N>`, CodeQL / required-check details, or `ci_failed_checks` from `pr:watch --json`), fix or escalate with evidence, then re-enter the review loop after CI is green.\n\n! PR body \"Test plan\" checkboxes being `[x]` do **not** authorize idle wait — merge-ready is `pr:watch` CLEAN / the merge path only.\n\n⊗ Treat `pr:watch` TIMEOUT or long PENDING with `clean_gate_holdout=ci_failures` as \"Greptile still reviewing\" — it means **CI blocked the clean gate**.\n\n~ Surface the holdout to the user/parent on the first stable `ci_failures` probe (fail-loud), not after burning `max-wait-minutes`. See also [`templates/swarm-greptile-poller-prompt.md`](../../templates/swarm-greptile-poller-prompt.md) CLEAN gate evaluation (#1039).\n\n\n### Runner capacity stall (`runner_capacity_stall` / #2672)\n\n! Framework CI prefers Blacksmith with a timed GH-hosted failover (~20 minute stall budget). When `task pr:watch --json` / `task pr:merge-ready` reports `ci_ready_state=runner_capacity_stall` (or verdict `RUNNER_CAPACITY_STALL`, exit 2): **wait for auto-failover** to the ubuntu-latest lane and the authoritative aggregator check. Do **not** invent `--skip-ci` or merge with pending required checks.\n\n! `runner_capacity_stall` is distinct from ordinary `not_ready_yet` (under budget / `in_progress`) and from execution hangs (#2652). Capacity stall means required checks stayed `queued` with no runner claimed past the budget.\n\n⊗ Use `--skip-ci` / merge-with-pending because CI is capacity-stalled — the failover path is the unblock; skip-ci is an incident-only release escape hatch (#2652), not a runner-capacity remedy.\n\n### CI weather reason codes + thrash caps (#3167)\n\n`pr:watch` / `pr:merge-ready` expose machine-distinguishable `ci_ready_state` values (also `--json`) so agents stop conflating Actions weather with product test failure:\n\n| `ci_ready_state` / verdict | Meaning | Agent action |\n|----------------------------|---------|--------------|\n| `ci_never_scheduled` / `CI_NEVER_SCHEDULED` | No CI workflow check-run for HEAD (empty or bots-only: Greptile/SLizard) | Cap re-triggers; then **BLOCKED** — do not multi-hour empty-commit thrash |\n| `runner_capacity_stall` / `RUNNER_CAPACITY_STALL` | Required still `queued`, no runner past budget (#2672) | Wait auto-failover; ⊗ `--skip-ci` |\n| `ci_failures` / `CI_BLOCKED` | Completed `failure` / `timed_out` with product evidence (#2688) | Own like Greptile P0 — fix or escalate |\n| `ci_cancelled_no_failover` / `CI_CANCELLED_NO_FAILOVER` | Primary `cancelled` and no green required sibling (failover skipped/not armed; workflow sibling **#3168**) | Cap re-triggers; then **BLOCKED** |\n| Greptile CLEAN fields / `greptile_pending` | Existing Step 6 / SHA / confidence | Unchanged |\n\n! **Thrash caps (MUST):** Under stable `ci_never_scheduled`, `ci_cancelled_no_failover`, or repeated capacity stall after failover wait budget, limit **CI re-trigger attempts** (empty-commit push, close/reopen, rebase-for-enqueue) to **at most 2** total across the ownership span. On the **2nd** failed re-trigger (or immediately when the weather code is stable and Greptile Step 6 is already clean), stop automatic re-push and emit a structured **BLOCKED** handoff.\n\n### Platform status probe + outage attribution (#3180)\n\n! When `ci_ready_state` is weather-class (`ci_never_scheduled`, `runner_capacity_stall`, `ci_cancelled_no_failover`, `ci_failures`), CI never starts for HEAD, or many PRs share an empty-check pattern: **MUST probe public status pages** before workflow thrash or drive-by edits. Gates surface static URLs in `pr:watch` / `pr:merge-ready` JSON and human output (v1: no network fetch required).\n\n1. ! **GitHub Status** (Actions, Webhooks): https://www.githubstatus.com/\n2. ! **Blacksmith Status**: https://status.blacksmith.sh/\n\n**Attribution table:**\n\n| Observation | `attribution` | Agent action |\n|-------------|---------------|--------------|\n| GH Actions and/or Webhooks major/partial outage | `platform` | Platform incident; ⊗ workflow drive-by edits; ⊗ empty-commit thrash past thrash caps; wait + re-check HEAD runs + local `task check` |\n| Blacksmith red while GH Actions green | `capacity` | Runner-provider incident; failover doctrine (#2672 / #3168) |\n| Both green + still `ci_never_scheduled` on this PR only | `repo_config` | Workflow paths, branch filters, required-check names, Actions disabled / org policy |\n| Unclear / mixed | `unknown` | Cap thrash; BLOCKED with both status URLs; operator decision |\n\n! **Anti-thrash during attributed platform outage:** After thrash caps, stop automatic re-push loops. Remediation is wait + re-probe HEAD check-runs, not inventing workflow edits for a global outage.\n\n### Forge-outage drop-back (#3422)\n\n! On attributed platform outage (`attribution: platform`) or repeated REST 429/502/503: **drop back** GitHub I/O (empty-commit, close/reopen, tight polls, new poller children), **report once** to the human in chat (what is down, attribution/incident, parked work, next probe time), and **re-probe once per** `plan.policy.forgeOutageRetryMinutes` (default **30**; USER.md Personal wins; min 5; inspect `task policy:show --field=forgeOutageRetryMinutes`). Local work that does not need the forge MAY continue. Depth: [`scm/github.md`](../../scm/github.md) § #3180 / #3422. Complements #3167 (weather codes) and #3180 (status attribution) — does not replace them.\n\n⊗ Tight retry, empty-commit thrash, or sending the human to github.com as the only remediation.\n⊗ Auto-merge / `--skip-ci` because a status page is red.\n\n⊗ Merge or `--skip-ci` solely because a status page is red — status is attribution for wait/thrash policy, not a second branch-protection oracle.\n⊗ Blame Blacksmith when GH Actions/Webhooks are the red components and Blacksmith runners are operational.\n⊗ Edit workflows / empty-commit thrash to \"fix\" a documented global Actions/webhook outage without a status-page probe.\n\nCross-links: #3167 (weather codes), #3168 (failover arms), #2672 (capacity stall), #2688 (Greptile CLEAN + CI holdout).\n\n! **BLOCKED handoff template (CI weather):**\n\n```text\nBLOCKED: ci_weather\nPR: <N>\nHEAD: <sha>\nREASON: ci_never_scheduled|ci_cancelled_no_failover|runner_capacity_stall\nGREPTILE: CLEAN|P0/P1|pending (Step 6 fields)\nCI: <ci_ready_state from pr:watch --json>\nplatform_status_github: https://www.githubstatus.com/\nplatform_status_blacksmith: https://status.blacksmith.sh/\nincident_url: <optional status-page incident URL or n/a>\nattribution: platform|capacity|repo_config|unknown\nATTEMPTS: empty-commit=<0-2> close-reopen=<0-2>\nREMEDIATION: wait for platform recovery | capacity failover (#3168) | repo config fix | human admin-merge playbook below | operator decision\nREDISPATCH_OK: yes|no\n```\n\n! Ownership of Greptile CLEAN + CI holdout is still real (#2688) — **ownership ≠ infinite wait**. After thrash caps, hand off; do not burn multi-hour `gh run watch` / empty-commit loops when Greptile is already CLEAN.\n\n! **Envelope selection under CI weather (#3153):** Prefer deliberate `stop-at: pr-open` implement + this skill as the partner merge-path babysit when known capacity/outage weather dominates; see swarm Envelope selection SLA and partner merge-path section above. Cross-link only — do not re-spec the tree here.\n\n⊗ Multi-hour empty-commit / close-reopen / rebase thrash after thrash caps when `ci_ready_state` is `ci_never_scheduled` or `ci_cancelled_no_failover`.\n⊗ Treat `ci_never_scheduled` as ordinary Greptile latency (`sha_match` / `terminal_check_run` only).\n⊗ Silent `--skip-ci` / admin merge without the outage playbook audit trail below.\n\n### SLizard advisory-only for merge-ready wait (#3167)\n\n! Required bot for **merge-ready wait** / Step 6 exit ownership is **Greptile**. SLizard (Gemini Verify) is **advisory only**: timeouts, retries, missing check, or flaky SLizard conclusions MUST NOT gate the review-cycle wait loop or authorize unbounded re-push.\n\n! `task pr:merge-ready` may still surface SLizard structure when present (#2189); agents MUST NOT idle-poll or thrash solely for SLizard when Greptile Step 6 is clean. Prefer continue / BLOCKED on CI weather / human decision.\n\n⊗ Block merge-ready babysit on SLizard alone when Greptile Step 6 all-of is satisfied on HEAD.\n\n### Outage admin-merge playbook (opt-in / human, #3167)\n\nWhen GitHub Actions is in a **documented major outage** (or multi-hour `ci_never_scheduled` / `ci_cancelled_no_failover` after thrash caps) and product + Greptile are ready:\n\n! Admin / human merge is **opt-in**, never the autonomous agent default. Preconditions:\n\n1. ! Greptile Step 6 fail-closed all-of on current HEAD (dogfood conf floor / `minGreptileConfidence`).\n2. ! Evidence of local or prior green `task check` / merge-gate when available.\n3. ! PR comment **audit note** naming the weather code, HEAD SHA, and who authorized override.\n4. ? Optional explicit env/policy for bot merge (`DEFT_ALLOW_BOT_MERGE` / `task policy:allow-bot-merge`) — **opt-in**, never silent default skip-ci.\n\n⊗ Autonomous `--skip-ci` / `--admin` merge as the default under ordinary CI weather.\n⊗ Replace branch protection with Greptile-only merge on normal days.\n\nWorkflow failover arming (Blacksmith cancelled → GH-hosted lane) is sibling issue **#3168** — this skill owns agent thrash caps and reason codes only.\n\n### Stall Detection Rubric (#564)\n\n! Track per poll: `startedAt` (timestamp of the first observation of the IN_PROGRESS check run for the current commit) and `commit.oid` (head SHA being reviewed). Both fields MUST be re-recorded every time the head SHA changes -- the rubric measures elapsed time on a single commit, not across the whole review cycle.\n\n! Expected duration baseline -- Greptile reviews typically complete in 2-5 minutes, with 7 minutes as the upper bound of normal. The escalation threshold is **3x expected = ~10 minutes** of continuous IN_PROGRESS on the same `commit.oid`. The 21-minute stall observed during the rc4 swarm cascade on PR #561 is the recurrence record; see [`../../meta/lessons.md`](../../../meta/lessons.md) `## Greptile Review Stall Detection (2026-04)`.\n\n! When elapsed time on the current `commit.oid` exceeds 10 minutes (3x expected) without the IN_PROGRESS check transitioning to a terminal state, the agent MUST escalate to the user. The escalation message MUST include: (1) the PR number; (2) the head SHA being reviewed; (3) the elapsed time since `startedAt`; (4) the four canonical user-decision options.\n\n! User-decision options at escalation -- render as a deterministic numbered menu per [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md) (final two options `Discuss` + `Back`):\n\n  1. Wait another N minutes (user picks N).\n  2. Manually re-trigger Greptile by commenting `@greptileai` on the PR (logs the override in a PR comment for auditability per the next rule).\n  3. Skip the bot review for this cycle and exit the loop with a documented reason.\n  4. Cancel the review cycle entirely.\n  5. Discuss.\n  6. Back.\n\n! Auto-restart detection -- when the polling loop observes a NEW `startedAt` (Greptile dropped its prior check run and started a fresh one without any push from the agent, e.g. service-side restart), the agent MUST reset its elapsed-time clock to the new `startedAt` AND notify the user that an auto-restart was detected. Resetting the clock without notifying is forbidden -- the user needs to know the cycle effectively re-started.\n\n! **`INCOMPLETE_BUT_RATED` stall signature (#1259):** when a poll observes a parsed `Confidence Score: X/5` number BUT no terminal check-run (no `completed` status with a `{success, neutral}` conclusion) AND/OR no HEAD-matching `Last reviewed commit:` completion marker, classify the state as **`INCOMPLETE_BUT_RATED`** — Greptile has emitted a confidence rating against a review that has NOT terminally landed on the current HEAD. This is NOT an exit condition (the Step 6 fail-closed all-of resolves the missing fields to `unknown`); treat it as a stall signature and keep polling, escalating per the 10-minute threshold above if it persists. A confidence number is the single most common false-positive for a premature exit — `INCOMPLETE_BUT_RATED` names the trap so the agent does not mistake a rating for a verdict.\n\n⊗ Auto-retrigger Greptile (empty commits, force-pushes, agent-posted `@greptileai` comments, status-check rebuilds) without explicit user approval. The escalation menu's option 2 is the ONLY supported re-trigger path, and even that requires the user to pick it.\n\n! Document any user-approved override in a brief PR comment for auditability -- e.g. `Note: review-cycle stall detected at <SHA> after <N> min; user approved manual re-trigger via @greptileai per skills/deft-directive-review-cycle Stall Detection Rubric (#564).` This makes the override visible to humans reviewing the PR history and to future agents that resume the cycle.\n\n⊗ Treat a stall as silent -- if the elapsed clock crosses the 10-minute threshold the agent MUST surface the menu, even if the agent is mid-poll. Continuing to poll past the threshold without user input is forbidden.\n\n### Owner Continuity Gate (#3090)\n\n! After any claim of `drive-to: merge-ready`, babysit, shepherd, or \"driving review-cycle / merge\" on an **open PR**, the **same turn** MUST end in exactly one of:\n\n- **A.** Approach 1 monitor live + sticky `<!-- deft:review-owner -->` lease registered (or #2878 gh-only lease equivalent). Parent yields with an **active** child / monitor and emits `review_cycle: in_progress:<pr>#<monitor_or_lease_ref>`.\n- **B.** Parent-retained ownership: parent does **not** mark the work complete; the next concrete action is an explicit dual-source poll/fix (Step 1 + Step 6). Emit `review_cycle: in_progress:<pr>#parent-retained` (or lease id when a sticky lease exists).\n- **C.** Explicit finish to caller/principal: `BLOCKED` / needs decision / `FAILED` with PR URL + HEAD SHA + why. Emit `review_cycle: skipped:<reason>` or keep `in_progress` only when a live owner remains; never freeform `started`.\n\n! **`review_cycle` evidence enum (portable — all consumers / handoffs / preamble §11 / swarm finish messages):** **only**\n  - `done` — Step 6 fail-closed all-of met on current HEAD (terminal check + HEAD pin + confidence bar + **0 P0/P1** via **dual-source**)\n  - `in_progress:<pr>#<monitor_or_lease_ref>` — verifiable sticky lease, registered monitor id, or documented `parent-retained` ownership\n  - `skipped:<reason>` — intentional skip (e.g. no-pr, operator cancel)\n  - `n/a` — work never entered review-cycle\n\n! Layer **L4** `status: pass` (or equivalent process-green handoff) is **illegal** unless `review_cycle: done` **or** `review_cycle: in_progress:…` with **verifiable** sticky lease / parent-retained ownership documented on that turn.\n\n! Opening a PR may use `in_progress` + lease; the **merge path** requires `done` (stricter product merge bars remain out of scope).\n\n! When dual-source fetch shows open P0/P1 under Step 6 / CLEAN evaluation: continue the fix loop **or** exit **BLOCKED** to the parent — never idle.\n\n! Optional machine gate: `deft verify:l4-owner --pr <N>` (or `task verify:l4-owner -- --pr <N>`; dual-invoke same order as other gates). Exit **0** only when a sticky lease is fresh on the PR **or** the caller asserts `--review-cycle done` after Step 6 (lease-or-done machine gate). `skipped` / `n/a` / parent-retained are process evidence only and do **not** satisfy this machine gate. Exit **1** on silent hold (no lease, no done). Pair with existing monitor-without-lease regression (#2797).\n\n⊗ End an owning turn with **0 children**, **no sticky lease**, and **no finish signal** after a drive-to-merge / babysit / shepherd claim (**silent hold**).\n⊗ Treat check-run **SUCCESS alone** as CLEAN or merge-ready while dual-source P0/P1 remain open.\n⊗ Emit freeform `review_cycle: started` / `pending` / `initiated` or L4 `status: pass` without **A** (or parent-retained **B** with explicit next action) or full Step 6 `done`.\n⊗ Solve Owner Continuity via host cron-as-Approach-1 or always-block-parent-until-merge — use A/B/C above (#2876 / #3090).\n\n~ **Eval / regression (#3090):** Given PR open + check SUCCESS + open inline P1s + agent text claims driving merge + turn ends with 0 subagents and no lease → **FAIL** (Owner Continuity Gate), not PASS.\n\n### Review Monitoring\n! **Background / independent dispatch (#1880 Gap D):** Long-running review-cycle owners and pollers (>~3 min) MUST be dispatched independently / in the background so the parent conversation stays interactive. On Cursor, use the Task tool background path (`run_in_background: true`) when the current agent is the top-level owner of that primitive (not a nested leaf — see Cursor leaf boundary). On Claude Code, top-level parents/orchestrators use the `Agent` tool with `run_in_background: true` (register primitive `claude-agent`, #3134); implementation leaves follow the Claude Code leaf boundary (blocking `pr:watch` or `stop-at: pr-open` sibling), not nested Agent. This generalizes the Approach-1 sub-agent monitor rule to implementation and fix workers as well — foreground dispatch is reserved for short tasks. The parent receives completion via `DONE` / `BLOCKED` / `FAILED` per `templates/agent-prompt-preamble.md` §11.\n\n! **Worker-owns-lifecycle (#1880 Gap C):** When this skill runs as part of an implementation worker scoped `drive-to: merge-ready`, the worker owns the full review/fix loop through merge-ready in its own tool loop — do NOT exit at PR-open expecting the orchestrator to spawn a separate review leaf.\n\n! **Swarm monitor must not self-implement (#2843 / Gap C):** When a cohort monitor receives `BLOCKED` or DONE-with-blockers from a `drive-to: merge-ready` implementation leaf, the monitor MUST NOT enter the review/fix loop inline on Tier 1 — background-dispatch ONE continuation leaf scoped `drive-to: merge-ready` on the same worktree. Monitor-inline review-cycle is permitted only on Tier 3 or with explicit operator consent (see `skills/deft-directive-swarm/SKILL.md` Phase 5 completion-notification decision tree).\n\n### Partner merge-path when implement stops at PR-open (#3153)\n\n! This skill is the **required partner** for the swarm **Envelope selection SLA** (`skills/deft-directive-swarm/references/core-phase-0.md` / Phase 3). When an implement leaf was deliberately scoped **`stop-at: pr-open`** (or a merge-ready leaf failed thin DONE and recovery chose babysit ownership), the parent/monitor MUST **not** leave the open PR without a merge-path owner.\n\n! **First-class merge-path ownership (MUST, same turn as PR ground-truth):**\n\n1. ! Spawn **or** retain **exactly one** review-cycle owner for the open PR:\n   - **Approach 1** review-monitor (`worker_role: review-monitor`) with sticky `<!-- deft:review-owner -->` lease (#3090 / #3044 / dual-invoke `review-monitor:register` when available), **or**\n   - A continuation leaf scoped **`drive-to: merge-ready`** on that PR/worktree that owns babysit → merge-ready in its tool loop, **or**\n   - Documented **parent-retained** ownership (`review_cycle: in_progress:<pr>#parent-retained`) with an explicit next poll/fix action — never silent hold.\n2. ! Route through **this skill** — ⊗ Cursor global babysit (`#2261`), freestyle main-session poll, or dual parallel monitors (`#3044`).\n3. ! Apply Owner Continuity Gate (#3090) and Single review-monitor lease (#3044) without exception: one sticky lease; force-takeover only when the prior owner is dead.\n4. ! **Post-merge `scope:complete` (#2321 / Gap C):** When the implement leaf stopped at pr-open, it MUST NOT have run `task scope:complete`. After the PR **merges**, the merge-path owner (or swarm Phase 6 `task swarm:finalize-cohort` / `task swarm:complete-cohort` / monitor) MUST run `task scope:complete` or `task scope:cancel`. `task verify:orphan-active` fails closed on stranded active briefs.\n5. ! **Human-merge / CLEAN-before-merge ownership (#3153 / #1193 / #2321):** When `plan.policy.requireHumanMerge` (or missing bot-merge authority) means the review owner reaches Greptile CLEAN / merge-ready but **cannot** squash-merge, lifecycle ownership is **not** complete. Prefer **durable** ownership (not a prose-only promise):\n   - **Preferred:** Parent/monitor **retains** ownership (`review_cycle: in_progress:<pr>#parent-retained` or sticky lease held by the long-lived monitor) until human merge lands, then runs `scope:complete` (or Phase 6 `task swarm:finalize-cohort` / `task swarm:complete-cohort`).\n   - **Allowed handoff:** Only to a **long-lived** parent/monitor / Phase 6 closer — same turn: (1) re-claim sticky `<!-- deft:review-owner -->` lease for the **recipient** (register/force as needed), (2) structured handback with PR, HEAD, `awaiting-human-merge`, and explicit post-merge `scope:complete` duty, (3) recipient acknowledges with `review_cycle: in_progress:<pr>#…` before the giving agent exits.\n   - ! Cohort through-merge: the **swarm monitor** is the default durable post-merge `scope:complete` owner for every `stop-at: pr-open` story (#2321) — do not rely on a review leaf that exits at CLEAN.\n   - ! **Post-CLEAN wake path (MUST):** After CLEAN under human-merge, the durable owner MUST keep a **reachable observe path** until the PR is `MERGED` (or closed without merge → `scope:cancel` / operator decision). Concrete options (pick one, same ownership):\n     1. **Background poller** (Approach 1 preferred when Tier 1): spawn/retain a review-monitor or short poll loop that probes `gh api repos/<owner>/<repo>/pulls/<N>` for `merged` / `state` on adaptive cadence (or host merge webhook when available), then runs post-merge verification + `scope:complete`.\n     2. **Parent-retained yield-with-wake:** parent keeps `review_cycle: in_progress:<pr>#parent-retained` and re-enters on the next operator message / scheduled re-invocation (Approach 2) with an explicit first action of \"check merge state → if merged, `scope:complete`\".\n     3. **Phase 6 cohort closer:** for swarm, record the PR as `awaiting-human-merge` in the monitor checkpoint and **require** the Phase 6 pre-sweep merge re-poll (`skills/deft-directive-swarm/references/core-phase-5-6.md` § Human-merge observe path / Step 1.5) before `task swarm:complete-cohort` / finalize — never skip `scope:complete` solely because Greptile was CLEAN earlier.\n   ⊗ Keep only a sticky lease with no poller, no parent re-entry plan, and no Phase 6 re-poll checklist — that is ownership-in-name-only and still strands `scope:complete`.\n   ⊗ Handoff to a short-lived leaf that exits at CLEAN without lease transfer.\n   ⊗ Emit terminal `DONE` / stand down at CLEAN when merge authority is human-only and no **reachable** durable owner (sticky lease + live parent/monitor/cohort closer **with an observe path above**) remains for post-merge `scope:complete`.\n6. ! **Thin DONE recovery (#2943 / #3153):** A failed `drive-to: merge-ready` leaf that only opened a PR is **not** success. After ground truth, hand merge path to **one** of the owners above — never improvise a second lease or re-dispatch implement + babysit in parallel without releasing the first.\n\n! **Cohort through-merge intent is unchanged:** stories still land on master. Envelope selection only assigns **who owns implement vs who owns Greptile/CI/merge** under capacity stall, conf floors, wall-clock budgets, or large multi-gate stories. Happy-path single `drive-to: merge-ready` leaves remain the default and do not use this partner handoff.\n\n! **Does not authorize:** lowering `minGreptileConfidence`, `--skip-ci` for capacity stalls, or unbounded redesign on conf-only holds (#2881 / #2672 / #3095).\n\nCross-links: swarm decision tree `skills/deft-directive-swarm/references/core-phase-0.md` § Envelope selection SLA; Phase 3 Gap C `skills/deft-directive-swarm/references/core-phase-3.md`; thin SKILL pointer `skills/deft-directive-swarm/SKILL.md` § Envelope selection SLA.\n\n\n\n! Select the monitoring approach based on runtime capability detection (the matrix in `skills/deft-directive-swarm/SKILL.md` Phase 3 Step 1, extended per #1342 slices 1-2 for `spawn_subagent` / \"grok-build\", per #1877 for Cursor as first-class Tier-1 tiers, per #2876 for OpenClaw `sessions_spawn`, and per #3134 for Claude Code `claude-code` / `claude-agent`). Probe the environment (tool set + env vars) to obtain the stable platform descriptor (`grok-build`, `warp-orchestrated`, `warp-manual`, `cursor-composer`, `cursor-cloud-agent`, `claude-code`, `openclaw`, etc.) from the launch adapter / `get_platform_capabilities` and map the descriptor to the appropriate tier + dispatch primitive (`start_agent`, `spawn_subagent`, the Cursor `Task` tool, Claude Code `Agent` / `claude-agent`, or OpenClaw `sessions_spawn`). The descriptor (not hard-coded tool presence) is the single source of truth for both launch and review monitoring.\n\n- **Tier 1 (orchestrated sub-agent)** → Approach 1 (spawn review-monitor sub-agent via the primitive matching the descriptor: `start_agent`, `spawn_subagent`, the Cursor `Task` tool with `run_in_background: true`, Claude Code `Agent` with `run_in_background: true` / register `claude-agent`, or OpenClaw `sessions_spawn`)\n- **Tier 2 (no sub-agent primitive, but scheduler/timer/auto-reinvocation)** → Approach 2 (yield-between-polls) — includes OpenClaw `cron` / host scheduler **only when** `sessions_spawn` is unavailable (#2876)\n- **Tier 3 (interactive session, nothing else)** → Approach 3 (blocking sleep loop as last resort)\n\n! Detection: use the full runtime capability matrix (swarm Phase 3 + launch adapter from #1342 slice 2). The old single-probe for `start_agent` is superseded; the returned platform descriptor determines both the orchestration path and the MCP surface (see MCP probe below). If the descriptor is `grok-build` (spawn_subagent present, start_agent + WARP_* absent), treat as Tier 1 with the spawn_subagent poller path. If the descriptor is `cursor-composer` / `cursor-cloud-agent` (Cursor `Task` tool present, start_agent + WARP_* + spawn_subagent absent), treat as **Tier 1 with the backgrounded Cursor `Task` poller path** (#1877) — NOT Tier 3. Cursor's `Task` tool is a first-class sub-agent primitive; degrading a Cursor session to the Approach-3 blocking poll is the misclassification #1877 closes. If the descriptor is `claude-code` (Claude-unique `Agent` / `CLAUDECODE` / `DEFT_PROBE_CLAUDE_CODE` signals), treat as **Tier 1 with the backgrounded Claude Code `Agent` poller path** (#3134) — NOT Tier 3 and NOT `cursor-composer` (bare `Task` is not a Claude-unique signal). If the descriptor is `openclaw` (`sessions_spawn` present), treat as **Tier 1 with the backgrounded `sessions_spawn` poller path** (#2876) — NOT Approach 2 cron and NOT main-session gh poll.\n\n! Swarm agents (whether launched via `start_agent`, `spawn_subagent`, or OpenClaw `sessions_spawn` per the platform descriptor) SHOULD prefer Approach 1 for their own review-monitor sub-agent. Approach 2's yield-between-polls is not self-sustaining for swarm agents (see warning below). Always include the canonical `templates/agent-prompt-preamble.md` (AGENTS.md read mandate, #810 xBRIEF gate, #798 PowerShell UTF-8, pre-PR + review-cycle mandates) when spawning a poller sub-agent.\n\n! **Deterministic review-monitor gate (#2655 / #2814 / #2876 / #2893):** When Tier 1 is available **and** a dual-invoke probe succeeds for review-monitor verbs (`deft verify:review-monitor` / `deft review-monitor:register`, or `task deft:verify:review-monitor` / `task deft:review-monitor:register`), run that verify form before yielding, entering Approach 3, or claiming review monitoring started — CLI: `deft verify:review-monitor --pr <N> [--call-site solo]`; task: `task deft:verify:review-monitor -- --pr <N> [--call-site solo]`. After spawning Approach 1, claim the PR-anchored lease with the matching register form (CLI: `deft review-monitor:register --pr <N> --monitor-agent-id <id> --platform-primitive ...`; task: `task deft:review-monitor:register -- --pr <N> --monitor-agent-id <id> --platform-primitive start_agent|spawn_subagent|cursor-task|claude-agent|sessions_spawn|openclaw-sessions-spawn`). Release with the matching release form (CLI: `deft review-monitor:release --pr <N>`; task: `task deft:review-monitor:release -- --pr <N>`) when done. Exit `0` ready / `1` not ready or held-by-other / `2` config. The sole source of truth is the sticky GitHub PR comment (`<!-- deft:review-owner -->`); legacy `.deft/review-monitor.json` is obsolete and ignored. On register conflict, attach to the existing owner or stop — do not parallel-fix.\n\n! **Missing review-monitor surface carve-out (#2878 / #2893):** When dual-invoke probes fail for `pr:watch` **and** `review-monitor:*` (no `deft` CLI, no `task deft:` include), do **not** invoke those gates and do **not** block Approach 1 on them. Fail-loud once with `missing-task: review-monitor` / `missing-task: pr:watch`, then:\n1. Still spawn Approach 1 with the official gh-only fallback when a sub-agent primitive exists.\n2. Post (or update) the sticky lease comment via raw `gh api` using the same `<!-- deft:review-owner -->` field shape the tasks would write — parent may yield after that claim succeeds — **or**, if the agent cannot write issue comments, keep ownership in the parent with the gh-only poll and document that lease tasks were unavailable.\n3. Never invent a local `.deft/review-monitor.json` as a substitute gate.\n⊗ Require successful review-monitor register/verify on a consumer where dual-invoke probes failed — that is the conf=3 / #2878 inconsistency Greptile flagged.\n\n! **Regression trigger (#2797 / #2878):** A leaf that claims a monitor is active without a preceding successful **GitHub sticky lease claim** MUST fail the review-monitor checklist/eval; a backgrounded `pr:watch` shell is insufficient. When a dual-invoke probe finds `review-monitor:register`, that form is the required claim path. When the missing-task carve-out applies (#2878), a raw `gh api` post/update of the same `<!-- deft:review-owner -->` sticky comment satisfies the claim (or the parent keeps ownership and does not claim a separate monitor). The regression fails only on a claim with **no** sticky lease evidence — not on consumers that legitimately lack the gate surface.\n\n\n\n! **CI-holdout carve-out (#2688):** When `task pr:watch --one-shot --json` reports `clean_gate_holdout=ci_failures` with Greptile fields otherwise satisfied on current HEAD, do **not** freeze on `verify:review-monitor` / spawn-monitor as if Greptile latency were the blocker. Fix CI first (same ownership as Greptile P0). Keep or register a review-monitor only while still waiting on Greptile latency; a `BLOCKED: ci_failures` DONE handback to the implementation owner is correct.\n\n\n! **Cursor leaf boundary (#2797 / #2893):** A Cursor `Task` leaf cannot reliably spawn another Cursor `Task`; nested Task (leaf spawning leaf) is unsupported for an Approach 1 review-monitor. A Cursor `drive-to: merge-ready` leaf MUST either keep ownership in the same agent by blocking on `deft pr:watch <N>` (or `task deft:pr:watch -- <N>` when include-present), or its envelope MUST instead be `stop-at: pr-open` so the orchestrator can spawn and register a sibling review-monitor. A background shell `pr:watch` is not a monitor and MUST NOT be claimed as one.\n\n! **Claude Code leaf boundary (#3134 / #2797 analogue):** Nested `Agent` (implementation leaf spawning a second-level review-monitor Agent) is unsupported/unreliable on some Claude Code surfaces. A Claude Code `drive-to: merge-ready` leaf MUST either keep ownership in the same agent by blocking on `deft pr:watch <N>` (or `task deft:pr:watch -- <N>` when include-present), or its envelope MUST instead be `stop-at: pr-open` so the orchestrator can spawn and register a sibling review-monitor with `--platform-primitive claude-agent`. ⊗ Background a nested Agent poller from an implementation leaf and exit claiming monitoring is active. Top-level parents/orchestrators that own the `Agent` primitive MAY still Approach-1 background a review-monitor Agent.\n\n**Approach 1 (preferred -- sub-agent orchestration available per platform descriptor):**\n\n! **Background dispatch (#1880 / #2876 / #3134):** Spawn the review-monitor sub-agent via the matching primitive IN THE BACKGROUND (Cursor: Task `run_in_background: true`; Claude Code: `Agent` `run_in_background: true`; Grok Build: `spawn_subagent` with parent yielding; OpenClaw: `sessions_spawn` with parent yielding). The parent MUST remain interactive while the poller runs — never block the parent OpenClaw/Cursor/Claude Code/Grok session for >~3 min of monitor ownership.\n\n! **Heartbeat contract for Cursor pollers (#1877 / #1166 / #2876 / #3134):** Claude Code `Agent` and OpenClaw `sessions_spawn` pollers share this contract. A Cursor `Task`, Claude Code `Agent`, or OpenClaw `sessions_spawn` review-monitor poller whose loop runs > ~3 min MUST honour the sub-agent heartbeat contract (`docs/subagent-heartbeat.md`), same as the `spawn_subagent` path — emit periodic progress so the parent can distinguish a live poller from a hung one.\n\n~ **Visible Control UI (OpenClaw / #3044):** When OpenClaw Control UI is the operator control plane, SHOULD spawn the review-monitor with `visible:true` when the tool surface allows so humans can inspect progress without attaching to the parent session; invisible empty settles are higher FC04 residual risk.\n\n! When the platform descriptor indicates Tier 1 (sub-agent support), spawn a review-monitor sub-agent using the primitive matching the descriptor:\n\n1. ! Launch via the matching primitive: `start_agent` (Warp), `spawn_subagent` (grok-build / TUI / non-Warp), the Cursor `Task` tool with `run_in_background: true` (`cursor-composer` / `cursor-cloud-agent`, #1877), the Claude Code `Agent` tool with `run_in_background: true` (`claude-code` / register `claude-agent`, #3134), **or OpenClaw `sessions_spawn` (`openclaw`, #2876)** with a prompt that instructs it to poll for Greptile completion. For `spawn_subagent`, Cursor `Task`, Claude Code `Agent`, and OpenClaw `sessions_spawn` the prompt MUST reference the canonical poller template `templates/swarm-greptile-poller-prompt.md` (with placeholders filled) plus the agent preamble; the working directory / context must be the PR branch (worktree or equivalent for hybrid).\n2. ! The sub-agent polls using the mechanism for its primitive: for `spawn_subagent` use `get_command_or_subagent_output` (adaptive cadence: ~20-30s first check after push, ~60s second, ~90s thereafter; Greptile typically lands in 3-7 min); for `start_agent` the native messaging path; for the Cursor `Task` tool the backgrounded-task completion-notification path; for Claude Code `Agent` the backgrounded-agent completion-notification path; for OpenClaw `sessions_spawn` the host session completion / messaging channel (prefer `task pr:watch` inside the child when available). Front-load the first check to catch fast reviews.\n3. ! When the exit condition is met (Greptile review current on the HEAD commit SHA, confidence meets resolved min (policy/dogfood/default; see Step 6 #3095), no P0/P1 remaining), the sub-agent reports completion back to the parent (via `send_message_to_agent`, the spawn_subagent result channel, or the OpenClaw sessions completion channel).\n4. ! The main conversation pane stays fully interactive during monitoring -- the user (or parent monitor) can continue other work.\n5. ! On receiving the completion message / result, the parent re-fetches findings (both gh pr view --comments and the secondary source) and proceeds to Step 5.\n\n⊗ Use OpenClaw `cron` alone as Approach 1 when `sessions_spawn` is available — cron is Approach 2 scheduler fallback only (#2876).\n\n### Empty announce ≠ done (parent DoD) (#3044 / FC04 residual)\n\n! When a review-monitor settle arrives with **empty body**, **missing `STATUS:` line**, or **status unknown** (including host `(no output)` / empty `subagent_announce`):\n\n1. ! The parent MUST run **same-turn ground truth** before any DONE / CLEAN / merge-ready claim: at least `gh pr view <N>` (or REST `pulls/<N>`), `gh pr checks <N>`, and current HEAD SHA (`gh api repos/<owner>/<repo>/pulls/<N> -q .head.sha`).\n2. ! Classify the settle as **FC04 residual** (empty babysit ≠ done) until ground truth shows a terminal merge/close outcome **or** an explicit structured `BLOCKED` / `FAILED` handback.\n3. ⊗ Treat empty / unknown settle as `DONE`, `CLEAN`, merge-ready, or batch-complete.\n4. ⊗ Spawn a second review-monitor solely because the first settle was empty/unknown without completing the ground-truth batch first (#3044 dual-lease recurrence).\n\n~ Recurrence: enterprize PR #43 (2026-08-02) — first monitor polled live, host settled empty/unknown; parent spawned a second same-`taskName` monitor; dual lease collision while PR stayed open. See also `meta/lessons.md` and FC04 / growth friction R1 + R10.\n\n\n### Completion latch on settle replay (#3092)\n\n! **Empty settle** is not a latch hit — use Empty announce ≠ done (#3044) above. When the parent has already emitted **one** consolidate for a monitor/leaf `runId` and the harness re-delivers an **identical or equivalent** non-empty settle for the same key, stay **silent** (no re-QC, no second final; host silent token when defined). Re-open only on new runId, principal reopen, or material new evidence. Full MUST: `templates/agent-prompt-preamble.md` §11.5.\n\n### Single review-monitor lease (#3044 / #2814)\n\n! **One sticky lease per PR:** ownership is the single sticky GitHub PR comment `<!-- deft:review-owner -->` (or the dual-invoke `review-monitor:register` form that writes it). Parallel ownership is forbidden.\n\n! **Pre-spawn check:** before launching another Approach 1 review-monitor (`sessions_spawn`, `spawn_subagent`, Cursor `Task`, Claude Code `Agent`, `start_agent`):\n\n1. ! Read the sticky lease (dual-invoke `verify:review-monitor` when available, else `gh api` issues comments for `<!-- deft:review-owner -->`).\n2. ! List active same-PR / same-`taskName` subagents when the host exposes that surface (OpenClaw `subagents list` or equivalent).\n3. ⊗ Spawn a second monitor while a prior owner is **running**.\n4. ⊗ Spawn a second monitor when the last settle was **empty/unknown** and ground truth has **not** shown a terminal merge/close (or explicit structured handback that releases ownership).\n5. ! If the prior owner is **dead** (liveness fail / `REDISPATCH_OK` / `verify:subagent-alive` exit 1) and the PR is still open: spawn **one** replacement monitor and re-claim the lease with **`--force`** (CLI: `deft review-monitor:register --pr <N> --monitor-agent-id <id> --force` / task: `task review-monitor:register -- --pr <N> --monitor-agent-id <id> --force`, or host equivalent force takeover) so a non-expired foreign lease does not block replacement — then **update** the sticky lease comment to the new owner. Never silent dual ownership.\n6. ! On register conflict when the prior owner is **still alive**: attach to the existing owner or stop — do not parallel-fix.\n7. ⊗ Refuse replacement of a dead owner solely because the 30-minute lease has not expired without attempting force takeover (#3044).\n\n### Required non-empty monitor handback (#3044)\n\n! Approach 1 review-monitor prompts (including `templates/swarm-greptile-poller-prompt.md` and any host-filled spawn prompt) MUST require a **non-empty** final handback with these fields:\n\n```text\nSTATUS: DONE|BLOCKED|FAILED\nHEAD: <sha>\nCHECKS: <summary>\nMERGE: <url|error|n/a>\nISSUE: <closed|open|n/a>\nNOTES: <short>\n```\n\n⊗ Empty final assistant message from a review-monitor.\n⊗ Parent treating a settle that lacks `STATUS:` as success.\n\n~ **Visible Control UI risk (#3044):** When OpenClaw Control UI is the operator plane, prefer `visible:true` on the review-monitor spawn; invisible empty settles are higher risk for FC04 misclassification. Cross-link: `skills/deft-directive-swarm/references/host-openclaw.md` Babysit / review-monitor residual.\n\n\n\n**Approach 2 (fallback -- no sub-agent primitive for the descriptor):**\n\n! When the platform descriptor indicates no sub-agent orchestration (or the primitive is unavailable), use discrete tool calls with a yield between checks. For `grok-build` / spawn_subagent descriptor this path is normally avoided in favor of Approach 1; it exists for pure interactive or limited runtimes.\n\n1. ! Use the current shell execution tool (`run_terminal_command` or equivalent in the runtime) in wait mode to run `gh pr view <number> --comments` and `gh pr checks <number>`.\n2. ! After each check, yield control (end all tool calls) -- the agent runtime will re-invoke after its interval or on next interaction.\n3. ! Target adaptive cadence (20-30s / 60s / 90s) where the runtime permits. The full cadence is easiest in Approach 1 (sub-agent) or 3 (blocking); pure yield is runtime-controlled.\n4. ! No blocking shell pane lock -- the conversation remains interactive between checks.\n5. ~ Approach 2 requires a periodic re-invocation trigger (timer, scheduler, user nudge, or external orchestrator for hybrid/worktree cases). Without it the poller stops after the first yield.\n6. ! When the exit condition is met, proceed to Step 5.\n\n⚠️ **Swarm / hybrid limitation**: Approach 2 is NOT autonomous for swarm agents or manual worktree setups. Yielding ends the turn with no self-wake; the parent monitor (or external scheduler) must detect idle and re-trigger or send a message. For true `grok-build` / spawn_subagent hybrids, prefer Approach 1 (spawn_subagent + get_command_or_subagent_output poller) exactly as the swarm launch adapter does.\n\n⊗ Use blocking `Start-Sleep` shell loops or `time.sleep()` loops EXCEPT as Approach 3 (see below) -- these lock the conversation and prevent user interaction.\n⊗ Poll more frequently than every 20 seconds -- use a real delay between checks, not back-to-back calls. Adaptive cadence (20-30s / 60s / 90s) replaces the fixed 60s minimum.\n\n**Approach 3 (last resort -- interactive session, no `start_agent`, no timer/scheduler):**\n\n! Approach 3 is a blocking sleep-poll loop used ONLY when both Approach 1 and Approach 2 are unavailable (interactive session with no `start_agent` and no auto-reinvocation mechanism). Uses PowerShell `sleep` / Unix `sleep` commands between polls.\n\n! **User warning gate:** Before activating Approach 3, the agent MUST warn the user that the conversation pane will be locked during polling and ask for explicit confirmation. Example: \"No sub-agent or auto-reinvocation available. I will poll in a blocking loop (~20-30s / 60s / 90s cadence). The conversation will be locked during polling. Proceed? (yes/no)\"\n\n⊗ Activate Approach 3 without first warning the user that it will lock the conversation pane.\n\n1. ! After receiving user confirmation, use a blocking shell loop with adaptive cadence:\n   - First check: wait ~25 seconds (e.g. `sleep 25`), then poll\n   - Second check: wait ~60 seconds, then poll\n   - Subsequent checks: wait ~90 seconds, then poll\n2. ! Poll using `gh pr view <number> --comments` and `gh pr checks <number>` in the same shell session\n3. ! When the exit condition is met (Greptile review current, confidence meets resolved min (policy/dogfood/default; see Step 6 #3095), no P0/P1), exit the loop and proceed to Step 5\n4. ! If the user interrupts (Ctrl+C or equivalent), exit gracefully and report current review status\n\n! Greptile may advance its review by **editing an existing PR issue comment** rather than creating a new PR review object. Do NOT rely solely on `pulls/{number}/reviews` — that endpoint may remain stale at an older commit SHA even after Greptile has reviewed the latest commit.\n\n! To confirm the review is current, check **both** surfaces:\n\n1. **PR issue comments** (primary signal) — Greptile edits its existing summary comment in place:\n   - `gh pr view <number> --comments` (with `do_not_summarize_output: true`)\n   - Or `gh api repos/<owner>/<repo>/issues/<number>/comments`\n   - Parse the comment body for `Last reviewed commit` and compare to the pushed commit SHA\n   - Check the comment's `updated_at` timestamp to confirm it was refreshed after your push\n2. **PR review objects** (secondary signal) — may or may not be updated:\n   - `gh api repos/<owner>/<repo>/pulls/<number>/reviews`\n   - Check `commit_id` on the latest review object\n\n! Treat an edited Greptile issue comment as a valid new review pass even if no new PR review object was created.\n\n! Fetch the full untruncated comment body or use MCP `get_comments` to get the actual commit URL containing the full SHA — do NOT rely on grepping truncated link text.\n\n⊗ Re-fetch or re-trigger while the bot's last review still targets an older commit on **both** surfaces.\n\n### Step 5: Re-fetch and analyze\n\n! Fetch the new review using both methods from Step 1.\n\n! Analyze all new findings before planning any changes.\n\n### Step 6: Exit condition check — fail-closed ReviewerStatus all-of (#1259)\n\n! The loop MAY exit clean ONLY when a SINGLE fresh fetch (not cached state, not a verdict assembled across earlier polls) satisfies ALL of the `ReviewerStatus` fields below. This is a **fail-closed all-of**: any field that is missing, unparsed, or ambiguous resolves to **`unknown`**, and `unknown` is NOT a pass — the agent stays in the loop and returns to Step 2. A PARTIAL or STALE Greptile review MUST NOT satisfy the exit predicate; the predicate is what prevents merging un-reviewed code while a P0/P1 finding is still in flight (#1259).\n\n1. ! **Terminal check-run** — the `Greptile Review` check run on the current HEAD has `status == \"completed\"` AND `conclusion` in `{success, neutral}`. The conclusions `null`, `cancelled`, `timed_out`, `stale`, `action_required`, and `failure` are explicitly NOT terminal-clean: any of them resolves to `unknown` and the loop continues. A check run still `queued` / `in_progress` is `unknown`.\n2. ! **HEAD-SHA pinned AT READ TIME** — read the current HEAD SHA in the SAME fetch used to evaluate this predicate (`gh api repos/<owner>/<repo>/pulls/<number> -q .head.sha`, read AT exit-evaluation time, NOT carried over from an earlier poll) and require `head_sha_reviewed == current HEAD`. A review whose reviewed SHA lags HEAD is `unknown`.\n3. ! **Completion marker present and matching** — the rolling-summary comment body carries `Last reviewed commit: <sha>` AND that `<sha>` matches the current HEAD. Extract the SHA with the markdown-link-aware NON-GREEDY regex below. Markdown link text can contain escaped brackets (e.g. a commit subject `add \\[Unreleased\\] entry`), so a greedy `[^\\]]*` stops at the first `]` and yields no match → false `unknown` on a clean review (#1326):\n\n    ```\n    Last reviewed commit:\\s*\\[.*?\\]\\(https?://github\\.com/[^/]+/[^/]+/commit/(?P<sha>[0-9a-f]{7,40})\n    ```\n\n   A missing or non-matching completion marker is `unknown`. See [`../../templates/swarm-greptile-poller-prompt.md`](../../templates/swarm-greptile-poller-prompt.md) `### Last reviewed commit:` for the canonical regex shared with the push-driven poller loop.\n4. ! **Confidence meets resolved min (#3095)** — the parsed `Confidence Score: X/5` is **>=** the resolved floor from `plan.policy.review.minGreptileConfidence` (inspect: `task policy:show --field=minGreptileConfidence`; `pr:watch` / `pr:merge-ready` share this SoT). Resolution order: typed project policy > framework dogfood detect (framework source → **5**) > consumer default (**4**, legacy confidence > 3 / 4/5+). A score below the floor, an unparsed confidence, or an absent confidence is `unknown`. Directive dogfood MUST NOT exit CLEAN on 4/5.\n5. ! **No P0/P1 findings** — the triple-tier (+ Tier 2.5) detector reports zero P0 and zero P1 findings (P2 issues are non-blocking style suggestions and do not gate the loop).\n\n! All five fields MUST hold on the SAME single fresh fetch. The agent MUST NOT assemble a \"pass\" by combining a terminal check-run observed on one poll with a confidence parsed on an earlier poll — the read is atomic per the SHA-pinned-AT-READ-TIME rule above.\n\n? If the bot says \"all prior issues resolved\" but lists new issues, treat it as one final batch — not the start of another loop. Go back to Step 2 one more time, re-evaluate this all-of, then stop.\n\n⊗ Exit the loop on a confidence number alone while the check run is non-terminal (`queued` / `in_progress` / `cancelled` / `timed_out` / `stale` / `action_required`) — a confidence score is NOT a verdict without a terminal check-run AND a HEAD-matching completion marker (#1259).\n⊗ Exit the loop against a reviewed SHA that lags the current HEAD — a partial or stale review MUST resolve to `unknown`, never to a pass (#1259).\n\nIf the exit predicate is not met (any field `unknown`), go back to Step 2.\n\n## Mechanical mergeability is necessary, never sufficient (#3225)\n\n! GitHub **Ready to merge**, green required checks, and formal review state without Changes-Requested are **necessary but never sufficient** clean signals. Reviewer bots on repos without enforced review wiring often express **should-not-merge** + sub-threshold confidence **only in comment body prose** (no formal `REQUEST_CHANGES`, no blocking CheckRun). A shepherd that merges on mechanical signals alone merges against explicit advisory verdicts.\n\n! **`task pr:merge-ready` / `task pr:watch` / Step 6 clean** MUST parse advisory bot verdict text and confidence from comment bodies (the #1282-style body extraction path; shared detector in `packages/core/src/content-contracts/skills/greptile-detector.ts`). Treat any of the following as **blocking** regardless of formal review state or the Ready-to-merge box:\n\n1. Advisory should-not-merge prose (`should-not-merge`, `Not safe to merge`, `Do not merge`, `Safe to merge once corrected`, `not ready to merge`, …)\n2. Confidence below the resolved `minGreptileConfidence` floor (#3095 — project policy > dogfood 5 > consumer default 4)\n3. P0/P1 findings (triple-tier + inline threads) or errored Greptile sentinel\n\n! When advisory prose blocks or confidence is sub-threshold: continue the fix/document loop or exit **BLOCKED** — ⊗ do not treat mechanical mergeability as CLEAN.\n\n~ Recommend repo-level review-gate wiring (required review / blocking Greptile CheckRun) for org repos that lack it, so formal state and prose verdict cannot diverge silently. Directive dogfood already enforces #3095; portable babysit paths on other org repos still need this prose gate.\n\n⊗ Merge because the merge box says Ready to merge while bot comment prose says should-not-merge or confidence is below the resolved floor (#3225 / #3095).\n⊗ Treat formal Comment (non-blocking) review state as sufficient when the rolling-summary body carries an advisory block.\n\n## Pre-Merge Re-Poll Gate (#1259)\n\n! Immediately before any `gh pr merge` invocation, the agent MUST re-fetch reviewer state ONE more time — a fresh `gh pr view <number> --comments`, a fresh `gh api repos/<owner>/<repo>/commits/<HEAD>/check-runs`, and a fresh HEAD-SHA read — and re-evaluate the Step 6 fail-closed all-of against that fresh fetch. The exit-condition pass recorded at the end of the review loop is NOT sufficient authorization to merge: review state can go stale between the loop's last poll and the merge call (a new push, a Greptile re-trigger, a service-side check-run reset).\n\n! Treat the re-poll and the `gh pr merge` as an atomic freshness window. If the re-poll shows ANY field `unknown`, ABORT the merge and return to Step 2.\n\n! Re-poll MUST also re-check advisory should-not-merge prose + confidence (#3225) — mechanical Ready-to-merge alone is never sufficient.\n\n⊗ Call `gh pr merge` on the strength of a review verdict observed earlier in the loop without an immediately-preceding re-poll that re-satisfies the Step 6 all-of — merging on cached review state is forbidden (#1259).\n⊗ Call `gh pr merge` on mechanical Ready-to-merge / green checks while advisory bot prose still records should-not-merge or sub-threshold confidence (#3225).\n\n### Informal-clean missing canonical fields (#1543)\n\nGreptile can post a **separate** informal clean reply that says prior issues are resolved and the current diff is clean while omitting the canonical rolling-summary fields Directive merge gates require: `Last reviewed commit:` and `Confidence Score: X/5`. `task pr:merge-ready` and `task swarm:verify-review-clean` correctly refuse merge-ready in this state -- prose alone cannot prove review currency or confidence.\n\n! When the latest Greptile bot comment is found, reports P0=0 and P1=0, but BOTH canonical fields are unparsed, classify the state as **`informal-clean missing-canonical-fields`** (see `task pr:merge-ready` diagnostic output) instead of treating it as \"review still writing\" or silently polling.\n\n! Recovery for informal-clean missing canonical fields -- route to ONE of these operator actions; do NOT keep polling:\n\n1. Comment `@greptileai review` on the PR to retrigger a canonical rolling summary on the current HEAD.\n2. Wait for Greptile to edit its primary rolling-summary comment with both canonical fields, then re-run `task pr:merge-ready -- <N>`.\n3. Document an explicit operator override per `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 1 (merge with rationale in the merge commit body).\n\n⊗ Treat informal clean Greptile prose (`current diff is clean`, `looks solid`, `no new issues`) as merge-ready without canonical `Last reviewed commit:` and `Confidence Score: X/5` evidence.\n\n⊗ Keep polling silently when `task pr:merge-ready` reports the informal-clean missing-canonical-fields diagnostic -- this is a blocked recovery state, not a late-arriving review.\n\n~ Swarm pollers MUST surface this state via the `### (6) INFORMAL-CLEAN` terminal exit in `templates/swarm-greptile-poller-prompt.md` instead of falling through to generic `(4) TIMEOUT` or `(5) STALL`.\n\n## Submitting GitHub Reviews\n\n! When submitting PR reviews via the GitHub MCP tool, always use `pull_request_review_write` with method `create` and the appropriate event:\n\n- `APPROVE` — formally approve the PR (shows green \"Approved\" status)\n- `REQUEST_CHANGES` — block the PR with requested changes\n- `COMMENT` — review feedback without approving or blocking\n\n⊗ Use `add_issue_comment` for review notes — that creates a regular comment, not a formal review. Review notes must always go in the review body via `pull_request_review_write`.\n\n## GitHub Interface Selection\n\n~ Use the most efficient interface for the task:\n\n- **MCP GitHub tool** — structured/programmatic operations (querying issues, creating PRs, bulk operations, filtering data)\n- **GitHub CLI (`gh`)** — quick ad-hoc commands and direct shell integration\n\nChoose whichever minimizes steps and maximizes clarity for the given task.\n\n~ When MCP is unavailable (agents without MCP tools in their dispatch environment, including `start_agent` / `spawn_subagent` (\"grok-build\") cases, cloud agents, `oz agent run`), `gh` CLI is sufficient as the sole interface. The dual-source requirement (MCP + `gh`) in Step 1 applies only when both are available -- agents without MCP access should use `gh pr view --comments` and `gh api` as their primary and only review detection surface. Runtime capability detection (swarm Phase 3 matrix) informs both orchestration tier and MCP surface choice.\n\n## Framework Events Emitted Here\n\n! When the user replies `yes` / `confirmed` / `approve` on a ready-to-merge PR thread (Phase 5 -> 6 gate per the canonical #642 workflow comment), emit a `plan:approved` framework event via `task lifecycle:event` so the approval is captured as a structural artifact rather than prose-only:\n\n```\ntask lifecycle:event -- emit plan:approved \\\n  --plan-ref https://github.com/<owner>/<repo>/pull/<N> \\\n  --approver <github-login> \\\n  --approval-phrase <yes|confirmed|approve> \\\n  --pr-number <N>\n```\n\n? Downstream consumers of `plan:approved` (auto-merge bots, status updates, audit reporting) are explicitly deferred to follow-up work; this event currently emits a record only (#635 events behavioral wiring).\n\n## Post-Merge Verification\n\n! Apply [`coding/review.md`](../../coding/review.md) post-merge closing-keyword verification. Adapter HOW for GitHub:\n\n! After a PR is squash-merged, verify that all referenced issues were actually closed. Squash merges can silently fail to process closing keywords (`Closes #N`, `Fixes #N`) from the PR body (#167).\n\n1. ! For each issue referenced with a closing keyword in the PR body, run:\n   ```\n   gh issue view <N> --json state --jq .state\n   ```\n2. ! If the issue state is not `CLOSED`, close it manually with a comment referencing the merged PR:\n   ```\n   gh issue close <N> --comment \"Closed by #<PR> (squash merge — auto-close did not trigger)\"\n   ```\n3. ~ This step mirrors `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 2 and applies to ALL PR merges, not just swarm runs.\n4. ! For PRs that referenced any umbrella / staying-OPEN issue (`Refs #N`), the INVERSE check applies: any protected issue that auto-closed MUST be reopened with a comment citing #701 and the merged PR. See `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 1 protected-issue reopen sweep and `meta/lessons.md` `## GitHub Closing-Keyword False-Positive Layer 3` for the persistent `closingIssuesReferences` link case (Layer 3, #701).\n\n\n## Probe-then-fill remote claims (#3120)\n\n! Before filling any **remote** handoff field (PR URL, PR number, commit/HEAD SHA, CI green/success, review score) or claiming `status: pass` / ship/gate done, MUST **probe then fill**:\n\n1. Run same-turn `git` + forge probes (examples: `git rev-parse HEAD`, `gh api repos/<owner>/<repo>/pulls/<N>`, `task pr:watch -- <N> --one-shot`, checks API).\n2. Copy IDs / URLs / SHAs / scores **only** from that probe JSON/text into the evidence block.\n3. Set `proof_status: bound` and attach short raw probe snippets (`command` + `snippet`) for each remote claim.\n\n! Handoff evidence axes: **work** (local) / **ship** (pushed branch or PR) / **gate** (CI/review on HEAD). `proof_status` is `bound` | `unbound` | `n/a-no-remote-claim`.\n! **Legal partial:** local work `done` + ship `not_started` / `blocked` **without** PR/SHA/CI/review fields and `proof_status: n/a-no-remote-claim` (or `status: partial`) is valid — do not invent ship state.\n! **Fail ranking:** **invented-done** (false/unbound remote artifacts under pass) is **stricter** than **empty-done**. Unbound remote claims → invalid evidence (fail), not pass-with-notes.\n! Machine check: `validateHandoffEvidence` in `packages/core/src/handoff-evidence/` (see `templates/agent-prompt-preamble.md` §11).\n⊗ Fill PR / SHA / CI / review fields from recollection, narration, or prior-turn memory.\n⊗ Claim `status: pass` with remote fields when `proof_status` is not `bound` or probes are missing (#3120).\n\n## Anti-Patterns\n\n- ⊗ Multi-hour empty-commit / close-reopen thrash after CI weather thrash caps when `ci_never_scheduled` or `ci_cancelled_no_failover` (#3167)\n- ⊗ Workflow thrash or empty-commit spam during attributed platform outage without status-page probe (#3180)\n- ⊗ Tight forge-outage retry / empty-commit thrash without a one-shot human report (#3422)\n- ⊗ Merge or `--skip-ci` solely because a status page is red without check-run evidence (#3180)\n- ⊗ Block merge-ready wait on SLizard alone when Greptile Step 6 is clean (#3167)\n- ⊗ Silent admin / `--skip-ci` merge under Actions outage without audit comment and opt-in authority (#3167)\n- ⊗ Leave a deliberate `stop-at: pr-open` (or thin-DONE recovery) open PR without spawning/retaining one review-cycle babysit owner + lease continuity and post-merge `scope:complete` plan (#3153)\n- ⊗ Stand down at CLEAN under human-merge policy without a durable owner (sticky lease + live parent/monitor/Phase 6 closer) **and** a post-CLEAN observe path (poller / parent wake / Phase 6 re-poll) for post-merge `scope:complete` (#3153 / #1193 / #2321)\n- ⊗ Handoff human-merge cleanup to a short-lived leaf that exits at CLEAN without re-claiming the sticky lease (#3153)\n- ⊗ Retain only a sticky lease after CLEAN with no poller, no parent re-entry, and no Phase 6 merge re-poll — ownership-in-name-only (#3153)\n- ⊗ Dual-lease or freestyle Cursor global babysit for the partner merge-path after implement stops at PR-open (#3153 / #2261 / #3044)\n- ⊗ End owning turn with 0 children, no sticky lease, and no finish after drive-to-merge / babysit / shepherd claim — silent hold (#3090)\n- ⊗ Emit freeform `review_cycle: started` / `pending` / `initiated` or L4 `status: pass` without `done` or verifiable `in_progress:<pr>#…` lease/parent-retained (#3090)\n- ⊗ Treat check-run SUCCESS alone as CLEAN / merge-ready while dual-source P0/P1 remain (#3090)\n- ⊗ Ignore [`coding/review.md`](../../coding/review.md) while running this adapter — universal batch/severity/exit/post-merge rules live there\n- ⊗ Route PR shepherding to Cursor global `babysit` on Deft-managed repos when `.deft/core/` is installed -- use this review-cycle skill instead (#2261)\n- ⊗ Route OpenClaw babysit/shepherd/watch to main-session gh poll + cron when `sessions_spawn` is available -- use Approach 1 with `sessions_spawn` (#2876 / #2261)\n- ⊗ Treat OpenClaw `cron` alone as Approach 1 — cron/timer is Approach 2 only if spawn is unavailable (#2876)\n- ⊗ Route Claude Code babysit/shepherd/watch to Approach 3 blocking poll when Claude `Agent` spawn is available — use Approach 1 with backgrounded `Agent` / `claude-agent` (#3134)\n- ⊗ Misclassify Claude Code as `cursor-composer` from bare `Task` alone (#3134)\n- ⊗ Expand active story scope past xBRIEF AC mid-babysit without follow-up issue or consented brief amend (#2881)\n- ⊗ Treat confidence-only holds (0 P0/P1) as a mandate for unbounded redesign (#2881)\n- ⊗ Dual-stop / conf-residual terminal halt without #3273 resume line (leftover class + residual class + resolved floor + standing vs one-shot + pursue residual / until floor or loop + skill section pointer) (#3273 / #3448)\n- ⊗ Unlimited residual auto-retry after dual-stop without new operator consent (#3273 / #2442)\n- ⊗ Hard-code 5/5 as the continue-until target, or treat one-shot `pursue residual` as standing, or park a class A already-touched leftover as a new story (#3448 / #2881 / #3095)\n- ⊗ Invent freestyle sleep/poll loops when dual-invoke probes fail for `pr:watch` — use the official gh-only fallback and fail-loud missing-task (#2878 / #2893)\n- ⊗ Treat bare `task pr:watch` as the only consumer gate form — probe `deft` then `task deft:` first (#2893)\n- ⊗ Treat a passing SLizard/Greptile check run, a non-blocking review comment, or an ad hoc fix commit as the review-cycle exit predicate -- Step 6 fail-closed all-of (#1259) and multi-reviewer registry triage (#769) still apply\n- ⊗ Push individual fix commits per finding\n- ⊗ Start fixing before analyzing ALL findings\n- ⊗ Rely on the bot to catch syntax errors in structured data files\n- ⊗ Re-trigger a bot review before the previous one has updated\n- ⊗ Report \"all comments resolved\" without checking both `gh pr view --comments` and a second source (`get_review_comments` via MCP, or `gh api` fallback when MCP is unavailable)\n- ⊗ Use `add_issue_comment` for formal review submission\n- ⊗ Commit or push Phase 1 audit fixes independently — always batch with Phase 2 fixes\n- ⊗ Proceed to Phase 2 while any Phase 1 prerequisite is unmet\n- ⊗ Rely solely on `pulls/{number}/reviews` to detect whether Greptile has reviewed the latest commit — Greptile may update via an edited issue comment instead of a new review object\n- ⊗ Push additional commits while Greptile is reviewing the current head — each push re-triggers Greptile and resets the review clock\n- ⊗ Use blocking `Start-Sleep` shell loops or `time.sleep()` loops to poll for review updates when Approach 1 or 2 is available -- Approach 3 (blocking loop) is permitted only as a last resort with user warning\n- ⊗ Poll more frequently than every 20 seconds -- use a real delay between checks, not back-to-back calls; adaptive cadence (20-30s / 60s / 90s) replaces the fixed 60s minimum\n- ⊗ Stop and ask the user whether to continue after pushing -- the review/fix loop MUST run autonomously to the exit condition\n- ⊗ Push fix commits without scanning changed lines for untested code paths — always check test coverage before pushing\n- ⊗ Push a fix commit that addresses fewer findings than the current Greptile review surfaces — if Greptile flags 3 issues, all 3 must be fixed in one commit before pushing\n- ⊗ Push after fixing a P1 without first checking whether the same Greptile review contains additional P0 or P1 findings\n- ⊗ Assume squash merge auto-closed referenced issues — always verify with `gh issue view` after merge (#167)\n- ⊗ Assume Approach 2 (yield-between-polls) produces a self-sustaining polling loop -- yielding ends the agent's turn with no self-wake; swarm agents will silently stop polling\n- ⊗ Skip the second review source (MCP or `gh api` fallback) without probing for MCP capability and documenting the fallback used\n- ⊗ Run a partial test suite instead of `task check` without documenting the pre-existing failure reason and open issue number in the PR body\n- ⊗ Create a PR without running `skills/deft-directive-pre-pr/SKILL.md` first -- the pre-PR quality loop catches issues before they reach the reviewer\n- ⊗ Activate Approach 3 (blocking `Start-Sleep` loop) without first warning the user that it will lock the conversation pane and receiving confirmation\n- ⊗ Exit the review loop on a Greptile confidence number alone while the check run is non-terminal -- a confidence score is NOT a verdict without a terminal check-run (`completed` + `{success, neutral}`) AND a HEAD-matching `Last reviewed commit:` completion marker (#1259)\n- ⊗ Call `gh pr merge` on cached/earlier review state without an immediately-preceding pre-merge re-poll that re-satisfies the Step 6 fail-closed all-of (#1259)\n- ⊗ Merge on mechanical Ready-to-merge / green checks while bot comment prose records should-not-merge or confidence below `minGreptileConfidence` (#3225 / #3095)\n- ⊗ Treat formal non-blocking review state as sufficient when rolling-summary body carries an advisory block (#3225)\n- ⊗ Treat empty/unknown review-monitor settle as DONE/CLEAN/merge-ready without same-turn ground truth (#3044 / FC04 residual)\n- ⊗ Spawn a second review-monitor while prior owner is running or last settle was empty/unknown without terminal ground truth (#3044)\n- ⊗ Accept empty review-monitor final message missing STATUS/HEAD/CHECKS/MERGE handback (#3044)\n- ⊗ Invent remote PR/SHA/CI/review claims in handoff evidence without same-turn probe binding — invented-done (#3120)\n- ⊗ Fill remote ship/gate fields from memory when only local work completed; legal partial omits PR fields (#3120)",
+      "body": "# Deft Directive Review Cycle\n\nStructured workflow for responding to bot reviewer (Greptile) findings on a PR.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n## Principle Authority (#1471 / #212)\n\n! Universal review-cycle principles live in [`coding/review.md`](../../coding/review.md) (RFC2119): read-all-findings, severity P0/P1/P2 + merge-blocking semantics, single batch commit, cross-file grep of changed terms, local structured-data validation (SHOULD), no push mid-review, exit when no P0/P1 remain (P2 non-blocking), and post-merge closing-keyword verification.\n\n! This skill is the **Greptile + GitHub adapter** only: polling cadence, confidence-score thresholds, check-run detection, dual-source fetch (`gh` + MCP) for Comments Outside Diff, fail-closed Step 6 `ReviewerStatus`, review-monitor lease, and merge gates. Apply `coding/review.md` for the process; do not restate that principle list inline.\n\n~ Future adapters (CodeRabbit, Codacy, host babysit) SHOULD implement the same `coding/review.md` principles with their own mechanics.\n\n## Platform Requirements\n\n! This skill requires **GitHub** as the SCM platform and the **GitHub CLI (`gh`)** to be installed and authenticated. PR comment fetching, check-run queries, and review submission all depend on `gh`.\n\n\n## Ordered-plan exit / advance (#2402)\n\n! When the review-cycle exit condition is met (no P0/P1 remaining / CLEAN verdict):\n\n1. Return control to the caller — do **not** discover adjacent backlog work.\n2. If an ordered-plan sequence is active and this PR matched the current entry, run `task plan-sequence:advance`.\n3. If another entry remains, the caller may continue **only** to that entry (one unit).\n4. If the sequence is exhausted, stop and ask. Do not open another PR from queue intuition or chaining text.\n\n⊗ Exit the review cycle into `task triage:queue` or an unrelated PR without fresh operator approval.\n\n## When to Use\n\n- User says \"review cycle\", \"check reviews\", or \"run review cycle\" on a PR\n- Operator asks to **babysit**, **shepherd**, or **watch** a PR -- including the Cursor product action **babysit-pull-request-in-cloud** (#2261 / #1862 intent-routing class)\n- A bot reviewer (Greptile) has posted findings on an open PR\n- Dispatching a cloud or background agent to monitor and resolve PR review findings until merge-ready\n- Operator re-authorizes after conf-hold / dual-stop residual: **pursue residual**, **follow-up hard-stop**, **same as conf-hold**, **continue dual-stopped PR**, or **re-babysit residual** — route to § Operator follow-up after dual-stop / hard stop (#3273) **one-shot** path\n- Operator issues a **standing residual order**: **until floor or loop**, **until greptile meets policy**, or **pursue residuals until told otherwise** — route to the same § **standing** path (#3448); applies to open cohort / ordered-plan units, not only the last halted PR\n\n## Cursor global babysit supersession (#2261)\n\nOn repos with `.deft/core/` installed, **PR shepherding intent** routes here -- not the Cursor-global `babysit` skill (`~/.cursor/skills-cursor/babysit/SKILL.md`). The product action **babysit-pull-request-in-cloud** shares the babysit name but MUST chain into this review-cycle surface on Deft-managed projects.\n\n- ! Orchestrators dispatching cloud/background workers for PR shepherding MUST include `templates/agent-prompt-preamble.md` (or reference it) and mandate reading this skill as the first workflow step.\n- ! Cloud babysit workers use `worker_role: review-monitor` (or `drive-to: merge-ready` implementation workers that own the review cycle) -- not a generic babysit loop without Phase 1 audit or Step 6 exit predicate (#1259).\n- ⊗ Route **babysit-pull-request-in-cloud** to Cursor global babysit when `.deft/core/` is present -- that bypasses xBRIEF preflight, `task check`, Greptile fail-closed exit, and CHANGELOG discipline (#2261 recurrence).\n\n### OpenClaw babysit supersession (#2876 / #2261)\n\nOn OpenClaw hosts with Directive installed (`.deft/core/` or equivalent content deposit), **babysit / shepherd / watch** intent likewise routes here -- not host-local freestyle poll loops and not OpenClaw `cron` alone.\n\n- ! When the OpenClaw tool surface exposes `sessions_spawn`, Approach 1 is the **default** babysit path: spawn a background review-monitor via `sessions_spawn` (register with `--platform-primitive sessions_spawn` or the alias `openclaw-sessions-spawn`).\n- ! Prefer a **visible** Control UI subagent (`visible:true` when the tool surface allows) when OpenClaw Control UI is the operator control plane so humans can inspect the monitor (#3044; invisible empty settles are higher FC04 residual risk).\n- ! Long review-monitor ownership (>~3 min) MUST NOT block the parent OpenClaw session — background `sessions_spawn` + parent yield; same Gap D rule as Cursor/Grok Build (#1880).\n- ! Prefer deep-think gates inside the monitor via the dual-invoke probe order (#2893): `deft pr:watch` / `deft pr:merge-ready` first, then `task deft:pr:watch` when the Taskfile include is present, then the #2878 gh-only fallback — bare `task pr:watch` is not the consumer form.\n- ⊗ Treat OpenClaw `cron` (or any host scheduler alone) as Approach 1. Cron/timer re-invocation is Approach 2 only when `sessions_spawn` is unavailable.\n- ⊗ Freestyle main-session `gh pr view` / `sleep` poll + ad-hoc cron when `sessions_spawn` is available — that is the statusreport#153 / #2876 process-routing failure mode.\n\n## Branch-Protection Policy Guard\n\n! Before entering the review/fix loop, run the skill-level branch-policy guard (#746 / #747). Halt before any state mutation if the project's `plan.policy.allowDirectCommitsToMaster` is unresolvable AND the operator has not set `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1`. Concretely:\n\n```\ndeft verify:branch || exit 1\n```\n\nThe skill MUST NOT modify files, push, or comment on the PR until the guard passes -- this catches the case where a malformed PROJECT-DEFINITION quietly disabled the policy and the agent would have committed directly to master mid-review.\n\n## Deterministic Questions Contract\n\n! Every numbered-menu prompt rendered in this skill (Phase 1 audit gates, Phase 2 Step 4 monitoring approach selection, Phase 5->6 ready-to-merge gate, Step 6 exit-condition prompts) MUST follow [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md): the final two numbered options MUST be `Discuss` and `Back`, in that order. The Discuss-pause semantic is documented verbatim there -- on `Discuss` selection the agent MUST halt the in-progress sequence immediately, prompt `What would you like to discuss?`, and resume only on an explicit user signal (re-asking the original question, saying `resume`/`continue`, or re-issuing the prior selection). Implicit resumption is forbidden.\n\n## Pre-Flight Check\n\n! Before entering the review/fix loop, verify the Greptile configuration supports it:\n\n1. ! `triggerOnUpdates` must be enabled (via Greptile dashboard or `.greptile/config.json`) — without this, Greptile only reviews the initial PR and never re-reviews after fix pushes, so the loop cannot reach the exit condition\n2. ~ `statusCheck` should be enabled so Greptile posts a `\"Greptile Review\"` check run on each commit — this is the signal the org ruleset uses to gate merges\n3. ? If Greptile does not re-review after a push despite `triggerOnUpdates` being enabled, comment `@greptileai` on the PR as a manual re-trigger fallback\n\n! Greptile posts **check runs** (GitHub Checks API), not **commit statuses** (Statuses API). To verify the check run is present on a commit:\n\n```\ngh api repos/<owner>/<repo>/commits/<sha>/check-runs --jq '.check_runs[] | select(.name == \"Greptile Review\")'\n```\n\n⊗ Use `commits/<sha>/statuses` to check for Greptile — that endpoint will always be empty.\n\n~ See `tools/greptile.md` for recommended dashboard and per-repo settings.\n\n## Phase 1 — Deft Process Audit\n\n! Before touching code, verify ALL prerequisites are satisfied. Fix any gaps first:\n\n1. ! Verify `skills/deft-directive-pre-pr/SKILL.md` was run before PR creation -- the PR branch should have passed at least one full pre-PR cycle (Read-Write-Lint-Diff). If not, run it now before proceeding.\n2. ! `PROJECT-DEFINITION.xbrief.json` and `xbrief/` lifecycle folders have scope xBRIEF coverage for all changes in the PR\n3. ! `CHANGELOG.md` has entries under `[Unreleased]` for the PR's changes\n4. ! `task check` passes fully (fmt + lint + typecheck + tests + coverage ≥75%)\n5. ! `.github/PULL_REQUEST_TEMPLATE.md` checklist is satisfied in the PR description\n6. ! If the PR touches 3+ files: verify a `/deft:change` `proposal.xbrief.json` exists in `history/changes/` for this branch and was explicitly confirmed by the user (affirmative response, not a broad 'proceed'), or document N/A with reason in the PR checklist\n7. ! Verify the PR is on a feature branch -- work MUST NOT have been committed directly to the default branch (master/main)\n\n~ **PR scope gate:** If the PR spans 3+ unrelated surfaces (e.g. a skill, a tool doc, and a strategy -- with no shared issue or scope xBRIEF linking them), warn the user that broad PRs increase review churn and Greptile noise. Recommend splitting into focused PRs unless all changes trace to the same scope xBRIEF or issue bundle.\n\n! Phase 1 audit gaps must be resolved before merging — but hold the fixes (do NOT commit or push them independently). Proceed to Phase 2 analysis to gather bot findings, then batch all Phase 1 + Phase 2 fixes into a single commit.\n⊗ Commit or push Phase 1 audit fixes independently before gathering Phase 2 findings.\n\n## Phase 2 — Review/Fix Loop\n\n### Step 1: Fetch ALL bot comments\n\n! Retrieve findings using BOTH methods — each catches different comment categories:\n\n```\ngh pr view <number> --comments\n```\n\n! Use `do_not_summarize_output: true` — summarizers silently drop the \"Comments Outside Diff\" section from large bot comments.\n\n~ **Oversized output fallback:** If `do_not_summarize_output: true` produces output too large to process, extract the relevant section with:\n\n- **PowerShell (Windows):** `gh pr view <number> --comments | Select-String \"Outside Diff\" -Context 50`\n- **Unix/macOS:** `gh pr view <number> --comments | grep -A 50 \"Outside Diff\"`\n\nBoth commands extract the \"Comments Outside Diff\" section with surrounding context, avoiding the need to process the full output.\n\n~ **Windows + Grok Build (#1353):** Avoid `|`, `>`, or `2>&1` in `run_terminal_command` strings -- use Python `pathlib`/`subprocess` or plain task commands instead.\n\n! **MCP capability probe** (mirrors deft-directive-swarm Phase 3 pattern): Before attempting MCP `get_review_comments`, probe whether MCP GitHub tools are available in the current session. Detection: attempt a lightweight MCP call (e.g. list available tools or a no-op query) -- if it succeeds, MCP is available; if it errors or the tool is not in the available set, MCP is unavailable.\n\n- **MCP available**: ! Use MCP `get_review_comments` as the second source to catch Comments Outside Diff.\n- **MCP unavailable** (e.g. non-MCP agents including `start_agent` / `spawn_subagent` (\"grok-build\") dispatch, cloud agents, `oz agent run`): ! Use `gh api repos/<owner>/<repo>/pulls/<number>/comments` as the explicit fallback for the second review source. Document in the commit message or PR comment why MCP was skipped (e.g. \"MCP unavailable in this session -- used gh api fallback for review comments\"). The platform descriptor from runtime detection determines MCP availability independently of the dispatch primitive.\n\n⊗ Report \"all comments resolved\" without verifying both sources.\n⊗ Skip the second review source without probing for MCP capability and documenting the fallback used.\n\n~ **Late-arriving bot review re-check:** If the initial dual-source fetch returns no bot review on the current HEAD SHA, wait ~60s and re-fetch before evaluating the Step 6 exit condition. Bot reviewers (Greptile) typically land within 3-7 min of PR creation/push; an empty first pass is more likely \"review pending\" than \"review clean\".\n\n⊗ Declare the exit condition met based on a single fetch that returned no bot review — re-fetch at least once after a ~60s delay first.\n\n~ This codifies a user-rule precedent on late-arriving bot reviews into the deft-internal deterministic tier. The [`templates/swarm-greptile-poller-prompt.md`](../../templates/swarm-greptile-poller-prompt.md) loop body already handles the same case for push-driven cycles via its per-poll fetch -- the rule above closes the orthogonal cold-start path where the one-shot review-cycle entry runs on a freshly-opened PR before any fix push has triggered the Step 4 polling loop.\n\n### Step 2: Analyze ALL findings before changing anything\n\n! Apply [`coding/review.md`](../../coding/review.md) before any code change: read **all** findings, classify P0/P1/P2, and plan **one** batch. Do not start per-finding fixes mid-read.\n\nGreptile adapter analysis extras:\n\n- Identify cross-file dependencies (a term, value, or field mentioned in multiple files)\n- ! **Scope-check each finding against the active story xBRIEF** (`plan.items[].narrative.Acceptance`) before coding — see Out-of-AC gate (#2881) below\n\n### Out-of-AC findings / active-story scope gate (#2881)\n\nBabysit and review-cycle are **not** a second unbounded implementation mandate. When Greptile (or another reviewer) raises design-adjacent work outside the active story's acceptance criteria, default to follow-up — not silent redesign mid-babysit (PR #2871 / #2869 → #2880 recurrence).\n\n! Given an active story xBRIEF with fixed `plan.items`, when a finding is **outside** those Acceptance criteria:\n\n1. ! File or propose a **follow-up** GitHub issue / scope xBRIEF for the out-of-AC work, **or**\n2. ! Amend the active brief's `plan.items` (and narratives) **with explicit operator consent** before implementing a new subsystem,\n3. ! Then continue babysit only for in-AC and carve-out findings.\n\n! **P0 carve-out vs new-subsystem-needs-story:**\n\n- ! P0 security / correctness defects on files **already touched** by the PR MAY land in the same PR without a new story.\n- ! New ledgers, idempotency protocols, cross-cutting reliability contracts, or multi-commit redesigns that expand story meaning **require** a separate story or an amended brief before code.\n\n**Leftover classes (A/B/C, #3448):**\n\n| Class | What it is | Auto-continue? |\n|-------|------------|----------------|\n| **class A** — named leftover on already-touched files | Wrong remediation, dropped field, fixture, same-module hole on files this PR already owns | **in-AC residual.** Continue until the resolved `#3095` floor or same-fingerprint loop |\n| **class B** — new subsystem / AC fight | New ledger, protocol, cross-cutting contract, or work that expands story meaning | Park or file follow-up. Do not expand mid-babysit |\n| **class C** — score-only, no concrete finding | Confidence below the resolved floor, 0 P0/P1, no named leftover | Document / same-as-conf-hold / operator floor this-PR-only. Not unbounded redesign |\n\n! **Already-touched leftover is class A (#2881 / #3448):** a leftover on files **already in the PR** is class A (in-AC residual) unless it needs a new ledger, protocol, or story.\n\n! **Confidence-only holds (0 P0/P1):** when confidence is below the **resolved `#3095` floor** (`plan.policy.review.minGreptileConfidence`: typed project policy > framework dogfood **5** > consumer default **4**; inspect `task policy:show --field=minGreptileConfidence` / `deft policy:show --field=minGreptileConfidence`) with zero P0 and zero P1 findings, the skill does **not** mandate unbounded redesign to raise confidence. That is class C unless a named leftover on already-touched files makes it class A. Offer one of:\n\n1. Follow-up issue / residual-risk note in the PR,\n2. Operator override path (document in PR comment),\n3. Minimal in-AC polish only — then re-evaluate Step 6.\n\n! **`issue:emit` related-ref footgun:** `task issue:emit` treats any `plan.references[]` entry whose type matches `github-issue` / `x-xbrief/github-issue` / `x-vbrief/github-issue` as **already tracked** and SKIPs creating a new issue. When linking **related** (non-primary) work:\n\n- ! Use a non-emit-tracking type for related issues (e.g. keep related links in narratives / PR body / `Refs #N` prose), **or** designate a single primary origin github-issue ref that emit should honor.\n- ⊗ Add related-issue `x-*/github-issue` refs to a brief that still needs `issue:emit` for its primary origin — emit will SKIP as already tracked.\n\n⊗ Expand active story scope past xBRIEF AC mid-babysit without follow-up or consented amend (#2881).\n⊗ Treat confidence-only holds as authorization to invent new subsystems in-tree.\n\n\n### Dual stop — review fix loops (#2442)\n\nReview fix cycles are multi-iteration work and MUST carry dual stop (`main.md` `## Dual Stop Rule (#2442)`). Single-turn re-checks are exempt.\n\n**Defaults for this skill (override only with an explicit operator envelope):**\n\n| Loop class | Success stop | Default failure stop |\n|------------|--------------|----------------------|\n| Greptile / bot fix batch (Step 3 → re-review) | No P0/P1 on current HEAD; confidence meets `minGreptileConfidence` | **max 3** fix-batch iterations across the whole review ownership (do **not** reset the counter on push when the same primary fingerprint remains) **or** the **Same-fingerprint stop** (below) |\n| Confidence-only hold (0 P0/P1, score below floor) | Confidence meets floor, or operator chooses document/accept path | **max 1** optional polish pass, then stop (do not redesign unbounded — see confidence-only holds above) |\n\n**On failure stop:**\n\n- ! Halt automatic re-fix. Prefer `BLOCKED:` with PR number, HEAD SHA, blocker class (`review_cycle_cap` / `greptile_p0_p1` / `conf_floor` / `no_progress`), what was tried, and human decision needed (preamble §11 / #2843).\n- ! **Halt-report resume line (MUST, #3273 / #3448):** End the terminal halt with leftover class (A/B/C) + residual class + conf (if any) + resolved `#3095` floor + standing vs one-shot + PR URL. Example: `RESUME: residual=<class> leftover=<A|B|C> conf=<n/5|n/a> floor=<resolved min|n/a> standing=<yes|one-shot> PR=<url>`. One-shot phrases: **pursue residual** | **follow-up hard-stop** | **same as conf-hold** | **continue dual-stopped PR**. Standing phrases: **until floor or loop** | **until greptile meets policy** | **pursue residuals until told otherwise**. Skill pointer to § Operator follow-up after dual-stop / hard stop (#3273). Same affordance shape as swarm `references/core-phase-4.md`.\n- ⊗ Continue silent fix rounds after the envelope is exhausted.\n- ⊗ Reset the fix-batch counter solely by re-pushing, empty-committing, or swapping workers when the same primary finding fingerprint remains (poll-wait timer MAY reset for a new HEAD; the dual-stop fix-batch counter MUST NOT).\n\n**Enforcement note:** skill defaults are behavioral. Durable delivery/acceptance circuit breaker: **#3143** `packages/core/src/delivery-attempt/` (`evaluatePreDispatch`). Docs: `docs/delivery-attempt.md`.\n\n### Operator follow-up after dual-stop / hard stop (#3273)\n\nOperator-initiated resume after conf-hold, residual dual-stop, or hard-stop exit — **not** automatic re-thrash. Composes Greptile floor (#3095) and advisory should-not-merge (#3225). Portable consumer + maintainer (`task` / `deft` dual-invoke). Continue-until target is the **resolved `#3095` floor** (`plan.policy.review.minGreptileConfidence`: typed project policy > framework dogfood **5** > consumer default **4**; inspect `task policy:show --field=minGreptileConfidence` / `deft policy:show --field=minGreptileConfidence`). ⊗ Hard-code 5/5. ⊗ Lower project policy to clear one PR.\n\n**One-shot vs standing (#3448):**\n- **One-shot** triggers: pursue residual · follow-up hard-stop · same as conf-hold · continue dual-stopped PR · re-babysit residual — **one** pass on the unit that just halted, then re-stop. Do not silently widen.\n- **Standing** triggers: **until floor or loop** · **until greptile meets policy** · **pursue residuals until told otherwise** — class A leftovers on **every open unit in the active cohort / ordered plan** keep moving until the resolved floor or the **Same-fingerprint stop** (this skill, Dual stop). Class B/C stay parked unless the operator names them.\n\n**One residual pass under operator consent (one-shot, or one standing batch):**\n1. Ground-truth: dual-invoke `pr:merge-ready` / `pr:watch --one-shot` (#2893). Classify leftover A/B/C (#2881 table above).\n2. Apply **one** residual fix batch **or** one re-review wait — not both as an unbounded loop.\n3. If operator authorized a conf floor for **this PR only** (e.g. ≥4/5): post a PR audit comment (floor, HEAD SHA, authorizer). That is the human-merge / documented-override trail — it does **not** rewrite policy or make `pr:merge-ready` / `pr:watch` CLEAN below `minGreptileConfidence`. ⊗ Silent policy edit for one residual.\n4. Re-evaluate Step 6; merge when **policy** floor + gates met, or human-merge after the documented PR-local floor is met in the bot body; else halt again with a fresh resume line (leftover class + resolved floor + standing vs one-shot).\n5. Post-merge `scope:complete` when this owner holds lifecycle (#2321 / #3264).\n\n! **Same-fingerprint stop (normative, #3448 / #2442):** **2 consecutive re-review observations**, **same primary fingerprint**, **no material fix between**. **Blocked handoffs count as observations.** After a real fix, a *new* leftover MAY take another batch. `#2442` batch cap (max 3 fix-batches) still applies.\n⊗ Restate a competing 2-vs-3 same-fingerprint threshold, or treat a `BLOCKED` handoff as not counting toward the stop.\n\n! Dual-stop re-entry: one residual pass then re-stop without new consent **unless** a standing order is active **and** the leftover is class A with a **new** fingerprint under the `#2442` cap. Fresh operator consent required for another one-shot pass, or after same-fingerprint / cap halt.\n\n⊗ Unlimited auto-retry after dual-stop without new operator consent (#3273 / #2442).\n⊗ Treat conf-only holds as authorization for unbounded redesign (#2881).\n⊗ Lower project-wide `minGreptileConfidence` for one residual.\n⊗ Treat one-shot `pursue residual` as a standing order, or park a class A leftover on already-touched files because the score is below 5.\n\n### Step 3: Fix all findings in ONE batch commit\n\n! Apply [`coding/review.md`](../../coding/review.md) single-batch, cross-file grep, and local structured-data validation rules. Land **all** in-scope fixes in one commit (or one intentional batch), never per-finding pushes.\n\nGreptile adapter pre-commit gate:\n\n- ! Before committing any Greptile fix, re-read the FULL current Greptile review and confirm all P0/P1 issues are addressed in the staged changes — this is the pre-commit gate that prevents per-finding fix commits\n- ! Run `task check` before committing\n- ! **Fail-loud completion claim (#1006)**: when reporting fix-batch completion (to the user, in the commit message, in a PR comment, or in a status message to a parent agent), MUST surface the OUTCOMES not the intent -- name the P0/P1 finding count addressed (\"addressed 3/3 P0 findings, 2/2 P1 findings, 0 deferred\" -- NOT \"all findings addressed\"), report the `task check` result with the test-collection counts (\"task check: 412 collected, 412 passed, 0 skipped, 0 xfailed\" -- NOT \"task check passed\"), and explicitly call out any finding intentionally deferred with the reason. Apply `coding/coding.md` `## Fail Loud: Completion Claims Require Outcome Verification (#1006)` to every claim emitted during the review cycle\n- ⊗ Claim \"all Greptile findings addressed\" without verifying that the staged fix actually closes every P0/P1 currently surfaced in the review body -- a fix that addresses 3 out of 4 P1 findings and reports completion is the exact failure mode #1006 forbids\n- ⊗ Claim \"task check passes\" when any test was skipped, xfailed, or run with errors suppressed -- report the full collection counts instead (#1006)\n- ? **Pre-existing failure carve-out**: If `task check` fails due to a pre-existing issue unrelated to the PR's changes, a partial test suite run is acceptable ONLY if BOTH conditions are met: (a) the `task check` failure is pre-existing with an open GitHub issue number tracking it, AND (b) the PR description explicitly notes the failure and includes the issue reference (e.g. \"task check: test_foo fails due to #NNN (pre-existing)\"). Without both conditions, the full `task check` pass remains mandatory.\n- ~ Commit message: `fix: address Greptile review findings (batch)`\n\n### Step 3b: Proactive test coverage scan\n\n! After committing the fix batch but before pushing, scan the changed lines for untested code paths:\n\n1. ! Run `git --no-pager diff HEAD~1 HEAD --name-only` to identify files touched in the fix batch\n2. ! For each changed file that has a corresponding test file, review whether the fix introduced or modified logic that lacks test coverage\n3. ! If untested code paths are found, write tests and amend them into the fix batch commit (or add as a second commit in the same push)\n4. ! Run `task check` again after adding tests to verify they pass\n\n~ This eliminates one CI round-trip per fix cycle — catching coverage gaps before CI does.\n\n⊗ Push fix commits without scanning for untested code paths in changed files.\n\n### Step 4: Push and wait\n\n! Push the batch commit, then wait for the bot to review the latest commit.\n\n! After pushing, the agent MUST autonomously poll for review updates and continue the review cycle without stopping to ask the user. Do not pause for confirmation, do not ask \"should I continue?\", do not wait for user input between push and review completion. The review/fix loop is designed to run to the exit condition without human intervention.\n\n! Mid-review push rule: see [`coding/review.md`](../../coding/review.md) (no push while review in progress). Adapter rationale: every push re-triggers Greptile and resets the review clock.\n\n⊗ Push any additional commits — including unrelated fixes, doc updates, or lessons — while waiting for the bot to finish reviewing the current head. If you discover additional work while waiting, stage it locally but do NOT push until the current review completes.\n\n\n\n### Greptile CLEAN vs CI holdout (`pr:watch` / #2688)\n\n! When waiting on a Greptile verdict for a `drive-to: merge-ready` worker (or any review-cycle owner), prefer the dual-invoke probe order below over ad-hoc sleep loops (#1056 / #2893). Parse `clean_gate_holdout` on every probe.\n\n### Gates-surface dual invoke order (#2893 / #2878)\n\nDeep-think gates (`pr:watch`, `pr:merge-ready`, `review-monitor:*`) have **three ordered invoke paths**. Agents MUST probe in this order; bare `task pr:watch` is **not** the sole (or first) consumer form.\n\n! **Probe order (MUST):**\n\n1. **`deft` / `directive` CLI first** — attempt `deft pr:watch --help` (or `directive pr:watch --help`). Primary for npm/package-manager installs; works without a root Taskfile. CLI forms take flags **without** go-task's bare `--` separator (e.g. `deft pr:watch <N> --json`, `deft verify:review-monitor --pr <N>`).\n2. **`task deft:<verb>` second** — when a root Taskfile includes `.deft/core/Taskfile.yml` under key `deft:`, go-task exposes **namespaced** tasks (`task deft:pr:watch`, `task deft:verify:review-monitor`, `task deft:review-monitor:register`). Probe `task --list` / `task deft:pr:watch -- --help`. Task forms **require** the bare `--` separator before verb flags (e.g. `task deft:pr:watch -- <N>`, `task deft:verify:review-monitor -- --pr <N>`).\n3. **#2878 gh-only fallback last** — only when both CLI and namespaced task probes fail, classify **missing-task: pr:watch** (or **missing-task: review-monitor**) and use the official gh-only subset below.\n\n⊗ Treat bare `task pr:watch` / `task review-monitor:register` as the only prescribed consumer form — under include key `deft:` those un-namespaced names are absent; that probe failure is not proof the gate is unavailable if `deft` or `task deft:` works (#2893).\n⊗ Pass go-task's bare `--` separator into `deft`/`directive` CLI forms (e.g. `deft pr:watch -- --help`) — CLI parsers reject the standalone `--` and the probe fails falsely (#2893).\n\n### Missing gate surface / consumer gh-only fallback (#2878)\n\nSome consumer repos (e.g. sister product deposits) ship Directive skills but have **no working invoke path** for `pr:watch` / `review-monitor:*` (no `deft` CLI on PATH, no Taskfile include → no `task deft:…`). Agents MUST NOT invent a non-skill poll loop when every probe fails.\n\n! **After dual-invoke probe fails (#2893):** classify the session as **missing-task: pr:watch** (or the specific verb) and fail-loud:\n\n```\nBLOCKED: missing-task pr:watch on this consumer\nRemediation:\n  1. Prefer `deft pr:watch` / install `@deftai/directive` so the CLI surface works, OR\n  2. Add the root Taskfile include (doctor gates-surface snippet) so `task deft:pr:watch` works, OR\n  3. Use the official gh-only fallback subset below (still this skill — not freestyle).\n```\n\n! **Official gh-only fallback** (when both `deft`/`directive` and `task deft:<verb>` probes fail for pr:watch / review-monitor):\n\n1. Still select Approach 1 when a sub-agent primitive exists (OpenClaw `sessions_spawn`, Cursor `Task`, Claude Code `Agent`, `spawn_subagent`, `start_agent`) — spawn a review-monitor that runs the gh-only loop; do not block the parent.\n2. **Do not call** gate verbs via any surface the probe showed absent — those invocations cannot succeed and must not gate the spawn.\n3. Ownership claim without the tasks: post/update the sticky `<!-- deft:review-owner -->` PR comment via `gh api` (same field shape as the task-written lease) **or** keep ownership in the parent and document `missing-task: review-monitor` in the PR/parent handback. Never invent `.deft/review-monitor.json`.\n4. Poll with adaptive cadence (20-30s / 60s / 90s) using:\n   - `gh pr view <N> --comments` (dual-source + Step 1 rules still apply)\n   - `gh pr checks <N>`\n   - `gh api repos/<owner>/<repo>/pulls/<N> -q .head.sha` for HEAD pin\n   - `gh api repos/<owner>/<repo>/commits/<sha>/check-runs` for Greptile terminal check-run\n5. Evaluate the same Step 6 fail-closed all-of (terminal check-run + HEAD SHA + Last reviewed commit + confidence meets resolved min (policy/dogfood/default; see Step 6 #3095) + no P0/P1).\n6. Surface missing-task once to the operator/parent on first detection; do not silently rebrand freestyle sleep as `pr:watch`.\n\n⊗ Fake a successful `pr:watch` or `review-monitor:*` gate when every dual-invoke probe failed.\n⊗ Block Approach 1 / parent yield on missing `review-monitor:*` after the dual-invoke probe — use the gh lease claim or parent-owned gh-only poll instead (#2878).\n⊗ Invent ad-hoc `sleep` / main-session poll / OpenClaw cron loops outside Approach 1–3 when the skill already names this fallback (#2878 / statusreport#153 recurrence).\n⊗ Skip Step 6 fail-closed fields because deterministic tasks are missing — the gh surfaces above remain mandatory.\n\n! When `clean_gate_holdout=ci_failures` and Greptile otherwise satisfies the probe-side Step 6 fields (SHA match on HEAD, confidence meets resolved min (policy/dogfood/default; see Step 6 #3095), no P0/P1, not errored): **MUST NOT** idle-poll hoping CI heals. Treat Greptile CLEAN + CI red with the **same ownership** as a Greptile P0 for a merge-ready worker — one fix batch, re-push, re-probe.\n\n! On persistent `ci_failures` holdout: exit the Greptile wait immediately, fetch failing check annotations (`gh pr checks <N>`, CodeQL / required-check details, or `ci_failed_checks` from `pr:watch --json`), fix or escalate with evidence, then re-enter the review loop after CI is green.\n\n! PR body \"Test plan\" checkboxes being `[x]` do **not** authorize idle wait — merge-ready is `pr:watch` CLEAN / the merge path only.\n\n⊗ Treat `pr:watch` TIMEOUT or long PENDING with `clean_gate_holdout=ci_failures` as \"Greptile still reviewing\" — it means **CI blocked the clean gate**.\n\n~ Surface the holdout to the user/parent on the first stable `ci_failures` probe (fail-loud), not after burning `max-wait-minutes`. See also [`templates/swarm-greptile-poller-prompt.md`](../../templates/swarm-greptile-poller-prompt.md) CLEAN gate evaluation (#1039).\n\n\n### Runner capacity stall (`runner_capacity_stall` / #2672)\n\n! Framework CI prefers Blacksmith with a timed GH-hosted failover (~20 minute stall budget). When `task pr:watch --json` / `task pr:merge-ready` reports `ci_ready_state=runner_capacity_stall` (or verdict `RUNNER_CAPACITY_STALL`, exit 2): **wait for auto-failover** to the ubuntu-latest lane and the authoritative aggregator check. Do **not** invent `--skip-ci` or merge with pending required checks.\n\n! `runner_capacity_stall` is distinct from ordinary `not_ready_yet` (under budget / `in_progress`) and from execution hangs (#2652). Capacity stall means required checks stayed `queued` with no runner claimed past the budget.\n\n⊗ Use `--skip-ci` / merge-with-pending because CI is capacity-stalled — the failover path is the unblock; skip-ci is an incident-only release escape hatch (#2652), not a runner-capacity remedy.\n\n### CI weather reason codes + thrash caps (#3167)\n\n`pr:watch` / `pr:merge-ready` expose machine-distinguishable `ci_ready_state` values (also `--json`) so agents stop conflating Actions weather with product test failure:\n\n| `ci_ready_state` / verdict | Meaning | Agent action |\n|----------------------------|---------|--------------|\n| `ci_never_scheduled` / `CI_NEVER_SCHEDULED` | No CI workflow check-run for HEAD (empty or bots-only: Greptile/SLizard) | Cap re-triggers; then **BLOCKED** — do not multi-hour empty-commit thrash |\n| `runner_capacity_stall` / `RUNNER_CAPACITY_STALL` | Required still `queued`, no runner past budget (#2672) | Wait auto-failover; ⊗ `--skip-ci` |\n| `ci_failures` / `CI_BLOCKED` | Completed `failure` / `timed_out` with product evidence (#2688) | Own like Greptile P0 — fix or escalate |\n| `ci_cancelled_no_failover` / `CI_CANCELLED_NO_FAILOVER` | Primary `cancelled` and no green required sibling (failover skipped/not armed; workflow sibling **#3168**) | Cap re-triggers; then **BLOCKED** |\n| Greptile CLEAN fields / `greptile_pending` | Existing Step 6 / SHA / confidence | Unchanged |\n\n! **Thrash caps (MUST):** Under stable `ci_never_scheduled`, `ci_cancelled_no_failover`, or repeated capacity stall after failover wait budget, limit **CI re-trigger attempts** (empty-commit push, close/reopen, rebase-for-enqueue) to **at most 2** total across the ownership span. On the **2nd** failed re-trigger (or immediately when the weather code is stable and Greptile Step 6 is already clean), stop automatic re-push and emit a structured **BLOCKED** handoff.\n\n### Platform status probe + outage attribution (#3180)\n\n! When `ci_ready_state` is weather-class (`ci_never_scheduled`, `runner_capacity_stall`, `ci_cancelled_no_failover`, `ci_failures`), CI never starts for HEAD, or many PRs share an empty-check pattern: **MUST probe public status pages** before workflow thrash or drive-by edits. Gates surface static URLs in `pr:watch` / `pr:merge-ready` JSON and human output (v1: no network fetch required).\n\n1. ! **GitHub Status** (Actions, Webhooks): https://www.githubstatus.com/\n2. ! **Blacksmith Status**: https://status.blacksmith.sh/\n\n**Attribution table:**\n\n| Observation | `attribution` | Agent action |\n|-------------|---------------|--------------|\n| GH Actions and/or Webhooks major/partial outage | `platform` | Platform incident; ⊗ workflow drive-by edits; ⊗ empty-commit thrash past thrash caps; wait + re-check HEAD runs + local `task check` |\n| Blacksmith red while GH Actions green | `capacity` | Runner-provider incident; failover doctrine (#2672 / #3168) |\n| Both green + still `ci_never_scheduled` on this PR only | `repo_config` | Workflow paths, branch filters, required-check names, Actions disabled / org policy |\n| Unclear / mixed | `unknown` | Cap thrash; BLOCKED with both status URLs; operator decision |\n\n! **Anti-thrash during attributed platform outage:** After thrash caps, stop automatic re-push loops. Remediation is wait + re-probe HEAD check-runs, not inventing workflow edits for a global outage.\n\n### Forge-outage drop-back (#3422)\n\n! On attributed platform outage (`attribution: platform`) or repeated REST 429/502/503: **drop back** GitHub I/O (empty-commit, close/reopen, tight polls, new poller children), **report once** to the human in chat (what is down, attribution/incident, parked work, next probe time), and **re-probe once per** `plan.policy.forgeOutageRetryMinutes` (default **30**; USER.md Personal wins; min 5; inspect `task policy:show --field=forgeOutageRetryMinutes`). Local work that does not need the forge MAY continue. Depth: [`scm/github.md`](../../scm/github.md) § #3180 / #3422. Complements #3167 (weather codes) and #3180 (status attribution) — does not replace them.\n\n⊗ Tight retry, empty-commit thrash, or sending the human to github.com as the only remediation.\n⊗ Auto-merge / `--skip-ci` because a status page is red.\n\n⊗ Merge or `--skip-ci` solely because a status page is red — status is attribution for wait/thrash policy, not a second branch-protection oracle.\n⊗ Blame Blacksmith when GH Actions/Webhooks are the red components and Blacksmith runners are operational.\n⊗ Edit workflows / empty-commit thrash to \"fix\" a documented global Actions/webhook outage without a status-page probe.\n\nCross-links: #3167 (weather codes), #3168 (failover arms), #2672 (capacity stall), #2688 (Greptile CLEAN + CI holdout).\n\n! **BLOCKED handoff template (CI weather):**\n\n```text\nBLOCKED: ci_weather\nPR: <N>\nHEAD: <sha>\nREASON: ci_never_scheduled|ci_cancelled_no_failover|runner_capacity_stall\nGREPTILE: CLEAN|P0/P1|pending (Step 6 fields)\nCI: <ci_ready_state from pr:watch --json>\nplatform_status_github: https://www.githubstatus.com/\nplatform_status_blacksmith: https://status.blacksmith.sh/\nincident_url: <optional status-page incident URL or n/a>\nattribution: platform|capacity|repo_config|unknown\nATTEMPTS: empty-commit=<0-2> close-reopen=<0-2>\nREMEDIATION: wait for platform recovery | capacity failover (#3168) | repo config fix | human admin-merge playbook below | operator decision\nREDISPATCH_OK: yes|no\n```\n\n! Ownership of Greptile CLEAN + CI holdout is still real (#2688) — **ownership ≠ infinite wait**. After thrash caps, hand off; do not burn multi-hour `gh run watch` / empty-commit loops when Greptile is already CLEAN.\n\n! **Envelope selection under CI weather (#3153):** Prefer deliberate `stop-at: pr-open` implement + this skill as the partner merge-path babysit when known capacity/outage weather dominates; see swarm Envelope selection SLA and partner merge-path section above. Cross-link only — do not re-spec the tree here.\n\n⊗ Multi-hour empty-commit / close-reopen / rebase thrash after thrash caps when `ci_ready_state` is `ci_never_scheduled` or `ci_cancelled_no_failover`.\n⊗ Treat `ci_never_scheduled` as ordinary Greptile latency (`sha_match` / `terminal_check_run` only).\n⊗ Silent `--skip-ci` / admin merge without the outage playbook audit trail below.\n\n### SLizard advisory-only for merge-ready wait (#3167)\n\n! Required bot for **merge-ready wait** / Step 6 exit ownership is **Greptile**. SLizard (Gemini Verify) is **advisory only**: timeouts, retries, missing check, or flaky SLizard conclusions MUST NOT gate the review-cycle wait loop or authorize unbounded re-push.\n\n! `task pr:merge-ready` may still surface SLizard structure when present (#2189); agents MUST NOT idle-poll or thrash solely for SLizard when Greptile Step 6 is clean. Prefer continue / BLOCKED on CI weather / human decision.\n\n⊗ Block merge-ready babysit on SLizard alone when Greptile Step 6 all-of is satisfied on HEAD.\n\n### Outage admin-merge playbook (opt-in / human, #3167)\n\nWhen GitHub Actions is in a **documented major outage** (or multi-hour `ci_never_scheduled` / `ci_cancelled_no_failover` after thrash caps) and product + Greptile are ready:\n\n! Admin / human merge is **opt-in**, never the autonomous agent default. Preconditions:\n\n1. ! Greptile Step 6 fail-closed all-of on current HEAD (dogfood conf floor / `minGreptileConfidence`).\n2. ! Evidence of local or prior green `task check` / merge-gate when available.\n3. ! PR comment **audit note** naming the weather code, HEAD SHA, and who authorized override.\n4. ? Optional explicit env/policy for bot merge (`DEFT_ALLOW_BOT_MERGE` / `task policy:allow-bot-merge`) — **opt-in**, never silent default skip-ci.\n\n⊗ Autonomous `--skip-ci` / `--admin` merge as the default under ordinary CI weather.\n⊗ Replace branch protection with Greptile-only merge on normal days.\n\nWorkflow failover arming (Blacksmith cancelled → GH-hosted lane) is sibling issue **#3168** — this skill owns agent thrash caps and reason codes only.\n\n### Stall Detection Rubric (#564)\n\n! Track per poll: `startedAt` (timestamp of the first observation of the IN_PROGRESS check run for the current commit) and `commit.oid` (head SHA being reviewed). Both fields MUST be re-recorded every time the head SHA changes -- the rubric measures elapsed time on a single commit, not across the whole review cycle.\n\n! Expected duration baseline -- Greptile reviews typically complete in 2-5 minutes, with 7 minutes as the upper bound of normal. The escalation threshold is **3x expected = ~10 minutes** of continuous IN_PROGRESS on the same `commit.oid`. The 21-minute stall observed during the rc4 swarm cascade on PR #561 is the recurrence record; see [`../../meta/lessons.md`](../../../meta/lessons.md) `## Greptile Review Stall Detection (2026-04)`.\n\n! When elapsed time on the current `commit.oid` exceeds 10 minutes (3x expected) without the IN_PROGRESS check transitioning to a terminal state, the agent MUST escalate to the user. The escalation message MUST include: (1) the PR number; (2) the head SHA being reviewed; (3) the elapsed time since `startedAt`; (4) the four canonical user-decision options.\n\n! User-decision options at escalation -- render as a deterministic numbered menu per [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md) (final two options `Discuss` + `Back`):\n\n  1. Wait another N minutes (user picks N).\n  2. Manually re-trigger Greptile by commenting `@greptileai` on the PR (logs the override in a PR comment for auditability per the next rule).\n  3. Skip the bot review for this cycle and exit the loop with a documented reason.\n  4. Cancel the review cycle entirely.\n  5. Discuss.\n  6. Back.\n\n! Auto-restart detection -- when the polling loop observes a NEW `startedAt` (Greptile dropped its prior check run and started a fresh one without any push from the agent, e.g. service-side restart), the agent MUST reset its elapsed-time clock to the new `startedAt` AND notify the user that an auto-restart was detected. Resetting the clock without notifying is forbidden -- the user needs to know the cycle effectively re-started.\n\n! **`INCOMPLETE_BUT_RATED` stall signature (#1259):** when a poll observes a parsed `Confidence Score: X/5` number BUT no terminal check-run (no `completed` status with a `{success, neutral}` conclusion) AND/OR no HEAD-matching `Last reviewed commit:` completion marker, classify the state as **`INCOMPLETE_BUT_RATED`** — Greptile has emitted a confidence rating against a review that has NOT terminally landed on the current HEAD. This is NOT an exit condition (the Step 6 fail-closed all-of resolves the missing fields to `unknown`); treat it as a stall signature and keep polling, escalating per the 10-minute threshold above if it persists. A confidence number is the single most common false-positive for a premature exit — `INCOMPLETE_BUT_RATED` names the trap so the agent does not mistake a rating for a verdict.\n\n⊗ Auto-retrigger Greptile (empty commits, force-pushes, agent-posted `@greptileai` comments, status-check rebuilds) without explicit user approval. The escalation menu's option 2 is the ONLY supported re-trigger path, and even that requires the user to pick it.\n\n! Document any user-approved override in a brief PR comment for auditability -- e.g. `Note: review-cycle stall detected at <SHA> after <N> min; user approved manual re-trigger via @greptileai per skills/deft-directive-review-cycle Stall Detection Rubric (#564).` This makes the override visible to humans reviewing the PR history and to future agents that resume the cycle.\n\n⊗ Treat a stall as silent -- if the elapsed clock crosses the 10-minute threshold the agent MUST surface the menu, even if the agent is mid-poll. Continuing to poll past the threshold without user input is forbidden.\n\n### Owner Continuity Gate (#3090)\n\n! After any claim of `drive-to: merge-ready`, babysit, shepherd, or \"driving review-cycle / merge\" on an **open PR**, the **same turn** MUST end in exactly one of:\n\n- **A.** Approach 1 monitor live + sticky `<!-- deft:review-owner -->` lease registered (or #2878 gh-only lease equivalent). Parent yields with an **active** child / monitor and emits `review_cycle: in_progress:<pr>#<monitor_or_lease_ref>`.\n- **B.** Parent-retained ownership: parent does **not** mark the work complete; the next concrete action is an explicit dual-source poll/fix (Step 1 + Step 6). Emit `review_cycle: in_progress:<pr>#parent-retained` (or lease id when a sticky lease exists).\n- **C.** Explicit finish to caller/principal: `BLOCKED` / needs decision / `FAILED` with PR URL + HEAD SHA + why. Emit `review_cycle: skipped:<reason>` or keep `in_progress` only when a live owner remains; never freeform `started`.\n\n! **`review_cycle` evidence enum (portable — all consumers / handoffs / preamble §11 / swarm finish messages):** **only**\n  - `done` — Step 6 fail-closed all-of met on current HEAD (terminal check + HEAD pin + confidence bar + **0 P0/P1** via **dual-source**)\n  - `in_progress:<pr>#<monitor_or_lease_ref>` — verifiable sticky lease, registered monitor id, or documented `parent-retained` ownership\n  - `skipped:<reason>` — intentional skip (e.g. no-pr, operator cancel)\n  - `n/a` — work never entered review-cycle\n\n! Layer **L4** `status: pass` (or equivalent process-green handoff) is **illegal** unless `review_cycle: done` **or** `review_cycle: in_progress:…` with **verifiable** sticky lease / parent-retained ownership documented on that turn.\n\n! Opening a PR may use `in_progress` + lease; the **merge path** requires `done` (stricter product merge bars remain out of scope).\n\n! When dual-source fetch shows open P0/P1 under Step 6 / CLEAN evaluation: continue the fix loop **or** exit **BLOCKED** to the parent — never idle.\n\n! Optional machine gate: `deft verify:l4-owner --pr <N>` (or `task verify:l4-owner -- --pr <N>`; dual-invoke same order as other gates). Exit **0** only when a sticky lease is fresh on the PR **or** the caller asserts `--review-cycle done` after Step 6 (lease-or-done machine gate). `skipped` / `n/a` / parent-retained are process evidence only and do **not** satisfy this machine gate. Exit **1** on silent hold (no lease, no done). Pair with existing monitor-without-lease regression (#2797).\n\n⊗ End an owning turn with **0 children**, **no sticky lease**, and **no finish signal** after a drive-to-merge / babysit / shepherd claim (**silent hold**).\n⊗ Treat check-run **SUCCESS alone** as CLEAN or merge-ready while dual-source P0/P1 remain open.\n⊗ Emit freeform `review_cycle: started` / `pending` / `initiated` or L4 `status: pass` without **A** (or parent-retained **B** with explicit next action) or full Step 6 `done`.\n⊗ Solve Owner Continuity via host cron-as-Approach-1 or always-block-parent-until-merge — use A/B/C above (#2876 / #3090).\n\n~ **Eval / regression (#3090):** Given PR open + check SUCCESS + open inline P1s + agent text claims driving merge + turn ends with 0 subagents and no lease → **FAIL** (Owner Continuity Gate), not PASS.\n\n### Review Monitoring\n! **Background / independent dispatch (#1880 Gap D):** Long-running review-cycle owners and pollers (>~3 min) MUST be dispatched independently / in the background so the parent conversation stays interactive. On Cursor, use the Task tool background path (`run_in_background: true`) when the current agent is the top-level owner of that primitive (not a nested leaf — see Cursor leaf boundary). On Claude Code, top-level parents/orchestrators use the `Agent` tool with `run_in_background: true` (register primitive `claude-agent`, #3134); implementation leaves follow the Claude Code leaf boundary (blocking `pr:watch` or `stop-at: pr-open` sibling), not nested Agent. This generalizes the Approach-1 sub-agent monitor rule to implementation and fix workers as well — foreground dispatch is reserved for short tasks. The parent receives completion via `DONE` / `BLOCKED` / `FAILED` per `templates/agent-prompt-preamble.md` §11.\n\n! **Worker-owns-lifecycle (#1880 Gap C):** When this skill runs as part of an implementation worker scoped `drive-to: merge-ready`, the worker owns the full review/fix loop through merge-ready in its own tool loop — do NOT exit at PR-open expecting the orchestrator to spawn a separate review leaf.\n\n! **Swarm monitor must not self-implement (#2843 / Gap C):** When a cohort monitor receives `BLOCKED` or DONE-with-blockers from a `drive-to: merge-ready` implementation leaf, the monitor MUST NOT enter the review/fix loop inline on Tier 1 — background-dispatch ONE continuation leaf scoped `drive-to: merge-ready` on the same worktree. Monitor-inline review-cycle is permitted only on Tier 3 or with explicit operator consent (see `skills/deft-directive-swarm/SKILL.md` Phase 5 completion-notification decision tree).\n\n### Partner merge-path when implement stops at PR-open (#3153)\n\n! This skill is the **required partner** for the swarm **Envelope selection SLA** (`skills/deft-directive-swarm/references/core-phase-0.md` / Phase 3). When an implement leaf was deliberately scoped **`stop-at: pr-open`** (or a merge-ready leaf failed thin DONE and recovery chose babysit ownership), the parent/monitor MUST **not** leave the open PR without a merge-path owner.\n\n! **First-class merge-path ownership (MUST, same turn as PR ground-truth):**\n\n1. ! Spawn **or** retain **exactly one** review-cycle owner for the open PR:\n   - **Approach 1** review-monitor (`worker_role: review-monitor`) with sticky `<!-- deft:review-owner -->` lease (#3090 / #3044 / dual-invoke `review-monitor:register` when available), **or**\n   - A continuation leaf scoped **`drive-to: merge-ready`** on that PR/worktree that owns babysit → merge-ready in its tool loop, **or**\n   - Documented **parent-retained** ownership (`review_cycle: in_progress:<pr>#parent-retained`) with an explicit next poll/fix action — never silent hold.\n2. ! Route through **this skill** — ⊗ Cursor global babysit (`#2261`), freestyle main-session poll, or dual parallel monitors (`#3044`).\n3. ! Apply Owner Continuity Gate (#3090) and Single review-monitor lease (#3044) without exception: one sticky lease; force-takeover only when the prior owner is dead.\n4. ! **Post-merge `scope:complete` (#2321 / Gap C):** When the implement leaf stopped at pr-open, it MUST NOT have run `task scope:complete`. After the PR **merges**, the merge-path owner (or swarm Phase 6 `task swarm:finalize-cohort` / `task swarm:complete-cohort` / monitor) MUST run `task scope:complete` or `task scope:cancel`. `task verify:orphan-active` fails closed on stranded active briefs.\n5. ! **Human-merge / CLEAN-before-merge ownership (#3153 / #1193 / #2321):** When `plan.policy.requireHumanMerge` (or missing bot-merge authority) means the review owner reaches Greptile CLEAN / merge-ready but **cannot** squash-merge, lifecycle ownership is **not** complete. Prefer **durable** ownership (not a prose-only promise):\n   - **Preferred:** Parent/monitor **retains** ownership (`review_cycle: in_progress:<pr>#parent-retained` or sticky lease held by the long-lived monitor) until human merge lands, then runs `scope:complete` (or Phase 6 `task swarm:finalize-cohort` / `task swarm:complete-cohort`).\n   - **Allowed handoff:** Only to a **long-lived** parent/monitor / Phase 6 closer — same turn: (1) re-claim sticky `<!-- deft:review-owner -->` lease for the **recipient** (register/force as needed), (2) structured handback with PR, HEAD, `awaiting-human-merge`, and explicit post-merge `scope:complete` duty, (3) recipient acknowledges with `review_cycle: in_progress:<pr>#…` before the giving agent exits.\n   - ! Cohort through-merge: the **swarm monitor** is the default durable post-merge `scope:complete` owner for every `stop-at: pr-open` story (#2321) — do not rely on a review leaf that exits at CLEAN.\n   - ! **Post-CLEAN wake path (MUST):** After CLEAN under human-merge, the durable owner MUST keep a **reachable observe path** until the PR is `MERGED` (or closed without merge → `scope:cancel` / operator decision). Concrete options (pick one, same ownership):\n     1. **Background poller** (Approach 1 preferred when Tier 1): spawn/retain a review-monitor or short poll loop that probes `gh api repos/<owner>/<repo>/pulls/<N>` for `merged` / `state` on adaptive cadence (or host merge webhook when available), then runs post-merge verification + `scope:complete`.\n     2. **Parent-retained yield-with-wake:** parent keeps `review_cycle: in_progress:<pr>#parent-retained` and re-enters on the next operator message / scheduled re-invocation (Approach 2) with an explicit first action of \"check merge state → if merged, `scope:complete`\".\n     3. **Phase 6 cohort closer:** for swarm, record the PR as `awaiting-human-merge` in the monitor checkpoint and **require** the Phase 6 pre-sweep merge re-poll (`skills/deft-directive-swarm/references/core-phase-5-6.md` § Human-merge observe path / Step 1.5) before `task swarm:complete-cohort` / finalize — never skip `scope:complete` solely because Greptile was CLEAN earlier.\n   ⊗ Keep only a sticky lease with no poller, no parent re-entry plan, and no Phase 6 re-poll checklist — that is ownership-in-name-only and still strands `scope:complete`.\n   ⊗ Handoff to a short-lived leaf that exits at CLEAN without lease transfer.\n   ⊗ Emit terminal `DONE` / stand down at CLEAN when merge authority is human-only and no **reachable** durable owner (sticky lease + live parent/monitor/cohort closer **with an observe path above**) remains for post-merge `scope:complete`.\n6. ! **Thin DONE recovery (#2943 / #3153):** A failed `drive-to: merge-ready` leaf that only opened a PR is **not** success. After ground truth, hand merge path to **one** of the owners above — never improvise a second lease or re-dispatch implement + babysit in parallel without releasing the first.\n\n! **Cohort through-merge intent is unchanged:** stories still land on master. Envelope selection only assigns **who owns implement vs who owns Greptile/CI/merge** under capacity stall, conf floors, wall-clock budgets, or large multi-gate stories. Happy-path single `drive-to: merge-ready` leaves remain the default and do not use this partner handoff.\n\n! **Does not authorize:** lowering `minGreptileConfidence`, `--skip-ci` for capacity stalls, or unbounded redesign on conf-only holds (#2881 / #2672 / #3095).\n\nCross-links: swarm decision tree `skills/deft-directive-swarm/references/core-phase-0.md` § Envelope selection SLA; Phase 3 Gap C `skills/deft-directive-swarm/references/core-phase-3.md`; thin SKILL pointer `skills/deft-directive-swarm/SKILL.md` § Envelope selection SLA.\n\n\n\n! Select the monitoring approach based on runtime capability detection (the matrix in `skills/deft-directive-swarm/SKILL.md` Phase 3 Step 1, extended per #1342 slices 1-2 for `spawn_subagent` / \"grok-build\", per #1877 for Cursor as first-class Tier-1 tiers, per #2876 for OpenClaw `sessions_spawn`, and per #3134 for Claude Code `claude-code` / `claude-agent`). Probe the environment (tool set + env vars) to obtain the stable platform descriptor (`grok-build`, `warp-orchestrated`, `warp-manual`, `cursor-composer`, `cursor-cloud-agent`, `claude-code`, `openclaw`, etc.) from the launch adapter / `get_platform_capabilities` and map the descriptor to the appropriate tier + dispatch primitive (`start_agent`, `spawn_subagent`, the Cursor `Task` tool, Claude Code `Agent` / `claude-agent`, or OpenClaw `sessions_spawn`). The descriptor (not hard-coded tool presence) is the single source of truth for both launch and review monitoring.\n\n- **Tier 1 (orchestrated sub-agent)** → Approach 1 (spawn review-monitor sub-agent via the primitive matching the descriptor: `start_agent`, `spawn_subagent`, the Cursor `Task` tool with `run_in_background: true`, Claude Code `Agent` with `run_in_background: true` / register `claude-agent`, or OpenClaw `sessions_spawn`)\n- **Tier 2 (no sub-agent primitive, but scheduler/timer/auto-reinvocation)** → Approach 2 (yield-between-polls) — includes OpenClaw `cron` / host scheduler **only when** `sessions_spawn` is unavailable (#2876)\n- **Tier 3 (interactive session, nothing else)** → Approach 3 (blocking sleep loop as last resort)\n\n! Detection: use the full runtime capability matrix (swarm Phase 3 + launch adapter from #1342 slice 2). The old single-probe for `start_agent` is superseded; the returned platform descriptor determines both the orchestration path and the MCP surface (see MCP probe below). If the descriptor is `grok-build` (spawn_subagent present, start_agent + WARP_* absent), treat as Tier 1 with the spawn_subagent poller path. If the descriptor is `cursor-composer` / `cursor-cloud-agent` (Cursor `Task` tool present, start_agent + WARP_* + spawn_subagent absent), treat as **Tier 1 with the backgrounded Cursor `Task` poller path** (#1877) — NOT Tier 3. Cursor's `Task` tool is a first-class sub-agent primitive; degrading a Cursor session to the Approach-3 blocking poll is the misclassification #1877 closes. If the descriptor is `claude-code` (Claude-unique `Agent` / `CLAUDECODE` / `DEFT_PROBE_CLAUDE_CODE` signals), treat as **Tier 1 with the backgrounded Claude Code `Agent` poller path** (#3134) — NOT Tier 3 and NOT `cursor-composer` (bare `Task` is not a Claude-unique signal). If the descriptor is `openclaw` (`sessions_spawn` present), treat as **Tier 1 with the backgrounded `sessions_spawn` poller path** (#2876) — NOT Approach 2 cron and NOT main-session gh poll.\n\n! Swarm agents (whether launched via `start_agent`, `spawn_subagent`, or OpenClaw `sessions_spawn` per the platform descriptor) SHOULD prefer Approach 1 for their own review-monitor sub-agent. Approach 2's yield-between-polls is not self-sustaining for swarm agents (see warning below). Always include the canonical `templates/agent-prompt-preamble.md` (AGENTS.md read mandate, #810 xBRIEF gate, #798 PowerShell UTF-8, pre-PR + review-cycle mandates) when spawning a poller sub-agent.\n\n! **Deterministic review-monitor gate (#2655 / #2814 / #2876 / #2893):** When Tier 1 is available **and** a dual-invoke probe succeeds for review-monitor verbs (`deft verify:review-monitor` / `deft review-monitor:register`, or `task deft:verify:review-monitor` / `task deft:review-monitor:register`), run that verify form before yielding, entering Approach 3, or claiming review monitoring started — CLI: `deft verify:review-monitor --pr <N> [--call-site solo]`; task: `task deft:verify:review-monitor -- --pr <N> [--call-site solo]`. After spawning Approach 1, claim the PR-anchored lease with the matching register form (CLI: `deft review-monitor:register --pr <N> --monitor-agent-id <id> --platform-primitive ...`; task: `task deft:review-monitor:register -- --pr <N> --monitor-agent-id <id> --platform-primitive start_agent|spawn_subagent|cursor-task|claude-agent|sessions_spawn|openclaw-sessions-spawn`). Release with the matching release form (CLI: `deft review-monitor:release --pr <N>`; task: `task deft:review-monitor:release -- --pr <N>`) when done. Exit `0` ready / `1` not ready or held-by-other / `2` config. The sole source of truth is the sticky GitHub PR comment (`<!-- deft:review-owner -->`); legacy `.deft/review-monitor.json` is obsolete and ignored. On register conflict, attach to the existing owner or stop — do not parallel-fix.\n\n! **Missing review-monitor surface carve-out (#2878 / #2893):** When dual-invoke probes fail for `pr:watch` **and** `review-monitor:*` (no `deft` CLI, no `task deft:` include), do **not** invoke those gates and do **not** block Approach 1 on them. Fail-loud once with `missing-task: review-monitor` / `missing-task: pr:watch`, then:\n1. Still spawn Approach 1 with the official gh-only fallback when a sub-agent primitive exists.\n2. Post (or update) the sticky lease comment via raw `gh api` using the same `<!-- deft:review-owner -->` field shape the tasks would write — parent may yield after that claim succeeds — **or**, if the agent cannot write issue comments, keep ownership in the parent with the gh-only poll and document that lease tasks were unavailable.\n3. Never invent a local `.deft/review-monitor.json` as a substitute gate.\n⊗ Require successful review-monitor register/verify on a consumer where dual-invoke probes failed — that is the conf=3 / #2878 inconsistency Greptile flagged.\n\n! **Regression trigger (#2797 / #2878):** A leaf that claims a monitor is active without a preceding successful **GitHub sticky lease claim** MUST fail the review-monitor checklist/eval; a backgrounded `pr:watch` shell is insufficient. When a dual-invoke probe finds `review-monitor:register`, that form is the required claim path. When the missing-task carve-out applies (#2878), a raw `gh api` post/update of the same `<!-- deft:review-owner -->` sticky comment satisfies the claim (or the parent keeps ownership and does not claim a separate monitor). The regression fails only on a claim with **no** sticky lease evidence — not on consumers that legitimately lack the gate surface.\n\n\n\n! **CI-holdout carve-out (#2688):** When `task pr:watch --one-shot --json` reports `clean_gate_holdout=ci_failures` with Greptile fields otherwise satisfied on current HEAD, do **not** freeze on `verify:review-monitor` / spawn-monitor as if Greptile latency were the blocker. Fix CI first (same ownership as Greptile P0). Keep or register a review-monitor only while still waiting on Greptile latency; a `BLOCKED: ci_failures` DONE handback to the implementation owner is correct.\n\n\n! **Cursor leaf boundary (#2797 / #2893):** A Cursor `Task` leaf cannot reliably spawn another Cursor `Task`; nested Task (leaf spawning leaf) is unsupported for an Approach 1 review-monitor. A Cursor `drive-to: merge-ready` leaf MUST either keep ownership in the same agent by blocking on `deft pr:watch <N>` (or `task deft:pr:watch -- <N>` when include-present), or its envelope MUST instead be `stop-at: pr-open` so the orchestrator can spawn and register a sibling review-monitor. A background shell `pr:watch` is not a monitor and MUST NOT be claimed as one.\n\n! **Claude Code leaf boundary (#3134 / #2797 analogue):** Nested `Agent` (implementation leaf spawning a second-level review-monitor Agent) is unsupported/unreliable on some Claude Code surfaces. A Claude Code `drive-to: merge-ready` leaf MUST either keep ownership in the same agent by blocking on `deft pr:watch <N>` (or `task deft:pr:watch -- <N>` when include-present), or its envelope MUST instead be `stop-at: pr-open` so the orchestrator can spawn and register a sibling review-monitor with `--platform-primitive claude-agent`. ⊗ Background a nested Agent poller from an implementation leaf and exit claiming monitoring is active. Top-level parents/orchestrators that own the `Agent` primitive MAY still Approach-1 background a review-monitor Agent.\n\n**Approach 1 (preferred -- sub-agent orchestration available per platform descriptor):**\n\n! **Background dispatch (#1880 / #2876 / #3134):** Spawn the review-monitor sub-agent via the matching primitive IN THE BACKGROUND (Cursor: Task `run_in_background: true`; Claude Code: `Agent` `run_in_background: true`; Grok Build: `spawn_subagent` with parent yielding; OpenClaw: `sessions_spawn` with parent yielding). The parent MUST remain interactive while the poller runs — never block the parent OpenClaw/Cursor/Claude Code/Grok session for >~3 min of monitor ownership.\n\n! **Heartbeat contract for Cursor pollers (#1877 / #1166 / #2876 / #3134):** Claude Code `Agent` and OpenClaw `sessions_spawn` pollers share this contract. A Cursor `Task`, Claude Code `Agent`, or OpenClaw `sessions_spawn` review-monitor poller whose loop runs > ~3 min MUST honour the sub-agent heartbeat contract (`docs/subagent-heartbeat.md`), same as the `spawn_subagent` path — emit periodic progress so the parent can distinguish a live poller from a hung one.\n\n~ **Visible Control UI (OpenClaw / #3044):** When OpenClaw Control UI is the operator control plane, SHOULD spawn the review-monitor with `visible:true` when the tool surface allows so humans can inspect progress without attaching to the parent session; invisible empty settles are higher FC04 residual risk.\n\n! When the platform descriptor indicates Tier 1 (sub-agent support), spawn a review-monitor sub-agent using the primitive matching the descriptor:\n\n1. ! Launch via the matching primitive: `start_agent` (Warp), `spawn_subagent` (grok-build / TUI / non-Warp), the Cursor `Task` tool with `run_in_background: true` (`cursor-composer` / `cursor-cloud-agent`, #1877), the Claude Code `Agent` tool with `run_in_background: true` (`claude-code` / register `claude-agent`, #3134), **or OpenClaw `sessions_spawn` (`openclaw`, #2876)** with a prompt that instructs it to poll for Greptile completion. For `spawn_subagent`, Cursor `Task`, Claude Code `Agent`, and OpenClaw `sessions_spawn` the prompt MUST reference the canonical poller template `templates/swarm-greptile-poller-prompt.md` (with placeholders filled) plus the agent preamble; the working directory / context must be the PR branch (worktree or equivalent for hybrid).\n2. ! The sub-agent polls using the mechanism for its primitive: for `spawn_subagent` use `get_command_or_subagent_output` (adaptive cadence: ~20-30s first check after push, ~60s second, ~90s thereafter; Greptile typically lands in 3-7 min); for `start_agent` the native messaging path; for the Cursor `Task` tool the backgrounded-task completion-notification path; for Claude Code `Agent` the backgrounded-agent completion-notification path; for OpenClaw `sessions_spawn` the host session completion / messaging channel (prefer `task pr:watch` inside the child when available). Front-load the first check to catch fast reviews.\n3. ! When the exit condition is met (Greptile review current on the HEAD commit SHA, confidence meets resolved min (policy/dogfood/default; see Step 6 #3095), no P0/P1 remaining), the sub-agent reports completion back to the parent (via `send_message_to_agent`, the spawn_subagent result channel, or the OpenClaw sessions completion channel).\n4. ! The main conversation pane stays fully interactive during monitoring -- the user (or parent monitor) can continue other work.\n5. ! On receiving the completion message / result, the parent re-fetches findings (both gh pr view --comments and the secondary source) and proceeds to Step 5.\n\n⊗ Use OpenClaw `cron` alone as Approach 1 when `sessions_spawn` is available — cron is Approach 2 scheduler fallback only (#2876).\n\n### Empty announce ≠ done (parent DoD) (#3044 / FC04 residual)\n\n! When a review-monitor settle arrives with **empty body**, **missing `STATUS:` line**, or **status unknown** (including host `(no output)` / empty `subagent_announce`):\n\n1. ! The parent MUST run **same-turn ground truth** before any DONE / CLEAN / merge-ready claim: at least `gh pr view <N>` (or REST `pulls/<N>`), `gh pr checks <N>`, and current HEAD SHA (`gh api repos/<owner>/<repo>/pulls/<N> -q .head.sha`).\n2. ! Classify the settle as **FC04 residual** (empty babysit ≠ done) until ground truth shows a terminal merge/close outcome **or** an explicit structured `BLOCKED` / `FAILED` handback.\n3. ⊗ Treat empty / unknown settle as `DONE`, `CLEAN`, merge-ready, or batch-complete.\n4. ⊗ Spawn a second review-monitor solely because the first settle was empty/unknown without completing the ground-truth batch first (#3044 dual-lease recurrence).\n\n~ Recurrence: enterprize PR #43 (2026-08-02) — first monitor polled live, host settled empty/unknown; parent spawned a second same-`taskName` monitor; dual lease collision while PR stayed open. See also `meta/lessons.md` and FC04 / growth friction R1 + R10.\n\n\n### Completion latch on settle replay (#3092)\n\n! **Empty settle** is not a latch hit — use Empty announce ≠ done (#3044) above. When the parent has already emitted **one** consolidate for a monitor/leaf `runId` and the harness re-delivers an **identical or equivalent** non-empty settle for the same key, stay **silent** (no re-QC, no second final; host silent token when defined). Re-open only on new runId, principal reopen, or material new evidence. Full MUST: `templates/agent-prompt-preamble.md` §11.5.\n\n### Single review-monitor lease (#3044 / #2814)\n\n! **One sticky lease per PR:** ownership is the single sticky GitHub PR comment `<!-- deft:review-owner -->` (or the dual-invoke `review-monitor:register` form that writes it). Parallel ownership is forbidden.\n\n! **Pre-spawn check:** before launching another Approach 1 review-monitor (`sessions_spawn`, `spawn_subagent`, Cursor `Task`, Claude Code `Agent`, `start_agent`):\n\n1. ! Read the sticky lease (dual-invoke `verify:review-monitor` when available, else `gh api` issues comments for `<!-- deft:review-owner -->`).\n2. ! List active same-PR / same-`taskName` subagents when the host exposes that surface (OpenClaw `subagents list` or equivalent).\n3. ⊗ Spawn a second monitor while a prior owner is **running**.\n4. ⊗ Spawn a second monitor when the last settle was **empty/unknown** and ground truth has **not** shown a terminal merge/close (or explicit structured handback that releases ownership).\n5. ! If the prior owner is **dead** (liveness fail / `REDISPATCH_OK` / `verify:subagent-alive` exit 1) and the PR is still open: spawn **one** replacement monitor and re-claim the lease with **`--force`** (CLI: `deft review-monitor:register --pr <N> --monitor-agent-id <id> --force` / task: `task review-monitor:register -- --pr <N> --monitor-agent-id <id> --force`, or host equivalent force takeover) so a non-expired foreign lease does not block replacement — then **update** the sticky lease comment to the new owner. Never silent dual ownership.\n6. ! On register conflict when the prior owner is **still alive**: attach to the existing owner or stop — do not parallel-fix.\n7. ⊗ Refuse replacement of a dead owner solely because the 30-minute lease has not expired without attempting force takeover (#3044).\n\n### Required non-empty monitor handback (#3044)\n\n! Approach 1 review-monitor prompts (including `templates/swarm-greptile-poller-prompt.md` and any host-filled spawn prompt) MUST require a **non-empty** final handback with these fields:\n\n```text\nSTATUS: DONE|BLOCKED|FAILED\nHEAD: <sha>\nCHECKS: <summary>\nMERGE: <url|error|n/a>\nISSUE: <closed|open|n/a>\nNOTES: <short>\n```\n\n⊗ Empty final assistant message from a review-monitor.\n⊗ Parent treating a settle that lacks `STATUS:` as success.\n\n~ **Visible Control UI risk (#3044):** When OpenClaw Control UI is the operator plane, prefer `visible:true` on the review-monitor spawn; invisible empty settles are higher risk for FC04 misclassification. Cross-link: `skills/deft-directive-swarm/references/host-openclaw.md` Babysit / review-monitor residual.\n\n\n\n**Approach 2 (fallback -- no sub-agent primitive for the descriptor):**\n\n! When the platform descriptor indicates no sub-agent orchestration (or the primitive is unavailable), use discrete tool calls with a yield between checks. For `grok-build` / spawn_subagent descriptor this path is normally avoided in favor of Approach 1; it exists for pure interactive or limited runtimes.\n\n1. ! Use the current shell execution tool (`run_terminal_command` or equivalent in the runtime) in wait mode to run `gh pr view <number> --comments` and `gh pr checks <number>`.\n2. ! After each check, yield control (end all tool calls) -- the agent runtime will re-invoke after its interval or on next interaction.\n3. ! Target adaptive cadence (20-30s / 60s / 90s) where the runtime permits. The full cadence is easiest in Approach 1 (sub-agent) or 3 (blocking); pure yield is runtime-controlled.\n4. ! No blocking shell pane lock -- the conversation remains interactive between checks.\n5. ~ Approach 2 requires a periodic re-invocation trigger (timer, scheduler, user nudge, or external orchestrator for hybrid/worktree cases). Without it the poller stops after the first yield.\n6. ! When the exit condition is met, proceed to Step 5.\n\n⚠️ **Swarm / hybrid limitation**: Approach 2 is NOT autonomous for swarm agents or manual worktree setups. Yielding ends the turn with no self-wake; the parent monitor (or external scheduler) must detect idle and re-trigger or send a message. For true `grok-build` / spawn_subagent hybrids, prefer Approach 1 (spawn_subagent + get_command_or_subagent_output poller) exactly as the swarm launch adapter does.\n\n⊗ Use blocking `Start-Sleep` shell loops or `time.sleep()` loops EXCEPT as Approach 3 (see below) -- these lock the conversation and prevent user interaction.\n⊗ Poll more frequently than every 20 seconds -- use a real delay between checks, not back-to-back calls. Adaptive cadence (20-30s / 60s / 90s) replaces the fixed 60s minimum.\n\n**Approach 3 (last resort -- interactive session, no `start_agent`, no timer/scheduler):**\n\n! Approach 3 is a blocking sleep-poll loop used ONLY when both Approach 1 and Approach 2 are unavailable (interactive session with no `start_agent` and no auto-reinvocation mechanism). Uses PowerShell `sleep` / Unix `sleep` commands between polls.\n\n! **User warning gate:** Before activating Approach 3, the agent MUST warn the user that the conversation pane will be locked during polling and ask for explicit confirmation. Example: \"No sub-agent or auto-reinvocation available. I will poll in a blocking loop (~20-30s / 60s / 90s cadence). The conversation will be locked during polling. Proceed? (yes/no)\"\n\n⊗ Activate Approach 3 without first warning the user that it will lock the conversation pane.\n\n1. ! After receiving user confirmation, use a blocking shell loop with adaptive cadence:\n   - First check: wait ~25 seconds (e.g. `sleep 25`), then poll\n   - Second check: wait ~60 seconds, then poll\n   - Subsequent checks: wait ~90 seconds, then poll\n2. ! Poll using `gh pr view <number> --comments` and `gh pr checks <number>` in the same shell session\n3. ! When the exit condition is met (Greptile review current, confidence meets resolved min (policy/dogfood/default; see Step 6 #3095), no P0/P1), exit the loop and proceed to Step 5\n4. ! If the user interrupts (Ctrl+C or equivalent), exit gracefully and report current review status\n\n! Greptile may advance its review by **editing an existing PR issue comment** rather than creating a new PR review object. Do NOT rely solely on `pulls/{number}/reviews` — that endpoint may remain stale at an older commit SHA even after Greptile has reviewed the latest commit.\n\n! To confirm the review is current, check **both** surfaces:\n\n1. **PR issue comments** (primary signal) — Greptile edits its existing summary comment in place:\n   - `gh pr view <number> --comments` (with `do_not_summarize_output: true`)\n   - Or `gh api repos/<owner>/<repo>/issues/<number>/comments`\n   - Parse the comment body for `Last reviewed commit` and compare to the pushed commit SHA\n   - Check the comment's `updated_at` timestamp to confirm it was refreshed after your push\n2. **PR review objects** (secondary signal) — may or may not be updated:\n   - `gh api repos/<owner>/<repo>/pulls/<number>/reviews`\n   - Check `commit_id` on the latest review object\n\n! Treat an edited Greptile issue comment as a valid new review pass even if no new PR review object was created.\n\n! Fetch the full untruncated comment body or use MCP `get_comments` to get the actual commit URL containing the full SHA — do NOT rely on grepping truncated link text.\n\n⊗ Re-fetch or re-trigger while the bot's last review still targets an older commit on **both** surfaces.\n\n### Step 5: Re-fetch and analyze\n\n! Fetch the new review using both methods from Step 1.\n\n! Analyze all new findings before planning any changes.\n\n### Step 6: Exit condition check — fail-closed ReviewerStatus all-of (#1259)\n\n! The loop MAY exit clean ONLY when a SINGLE fresh fetch (not cached state, not a verdict assembled across earlier polls) satisfies ALL of the `ReviewerStatus` fields below. This is a **fail-closed all-of**: any field that is missing, unparsed, or ambiguous resolves to **`unknown`**, and `unknown` is NOT a pass — the agent stays in the loop and returns to Step 2. A PARTIAL or STALE Greptile review MUST NOT satisfy the exit predicate; the predicate is what prevents merging un-reviewed code while a P0/P1 finding is still in flight (#1259).\n\n1. ! **Terminal check-run** — the `Greptile Review` check run on the current HEAD has `status == \"completed\"` AND `conclusion` in `{success, neutral}`. The conclusions `null`, `cancelled`, `timed_out`, `stale`, `action_required`, and `failure` are explicitly NOT terminal-clean: any of them resolves to `unknown` and the loop continues. A check run still `queued` / `in_progress` is `unknown`.\n2. ! **HEAD-SHA pinned AT READ TIME** — read the current HEAD SHA in the SAME fetch used to evaluate this predicate (`gh api repos/<owner>/<repo>/pulls/<number> -q .head.sha`, read AT exit-evaluation time, NOT carried over from an earlier poll) and require `head_sha_reviewed == current HEAD`. A review whose reviewed SHA lags HEAD is `unknown`.\n3. ! **Completion marker present and matching** — the rolling-summary comment body carries `Last reviewed commit: <sha>` AND that `<sha>` matches the current HEAD. Extract the SHA with the markdown-link-aware NON-GREEDY regex below. Markdown link text can contain escaped brackets (e.g. a commit subject `add \\[Unreleased\\] entry`), so a greedy `[^\\]]*` stops at the first `]` and yields no match → false `unknown` on a clean review (#1326):\n\n    ```\n    Last reviewed commit:\\s*\\[.*?\\]\\(https?://github\\.com/[^/]+/[^/]+/commit/(?P<sha>[0-9a-f]{7,40})\n    ```\n\n   A missing or non-matching completion marker is `unknown`. See [`../../templates/swarm-greptile-poller-prompt.md`](../../templates/swarm-greptile-poller-prompt.md) `### Last reviewed commit:` for the canonical regex shared with the push-driven poller loop.\n4. ! **Confidence meets resolved min (#3095)** — the parsed `Confidence Score: X/5` is **>=** the resolved floor from `plan.policy.review.minGreptileConfidence` (inspect: `task policy:show --field=minGreptileConfidence`; `pr:watch` / `pr:merge-ready` share this SoT). Resolution order: typed project policy > framework dogfood detect (framework source → **5**) > consumer default (**4**, legacy confidence > 3 / 4/5+). A score below the floor, an unparsed confidence, or an absent confidence is `unknown`. Directive dogfood MUST NOT exit CLEAN on 4/5.\n5. ! **No P0/P1 findings** — the triple-tier (+ Tier 2.5) detector reports zero P0 and zero P1 findings (P2 issues are non-blocking style suggestions and do not gate the loop).\n\n! All five fields MUST hold on the SAME single fresh fetch. The agent MUST NOT assemble a \"pass\" by combining a terminal check-run observed on one poll with a confidence parsed on an earlier poll — the read is atomic per the SHA-pinned-AT-READ-TIME rule above.\n\n? If the bot says \"all prior issues resolved\" but lists new issues, treat it as one final batch — not the start of another loop. Go back to Step 2 one more time, re-evaluate this all-of, then stop.\n\n⊗ Exit the loop on a confidence number alone while the check run is non-terminal (`queued` / `in_progress` / `cancelled` / `timed_out` / `stale` / `action_required`) — a confidence score is NOT a verdict without a terminal check-run AND a HEAD-matching completion marker (#1259).\n⊗ Exit the loop against a reviewed SHA that lags the current HEAD — a partial or stale review MUST resolve to `unknown`, never to a pass (#1259).\n\nIf the exit predicate is not met (any field `unknown`), go back to Step 2.\n\n## Mechanical mergeability is necessary, never sufficient (#3225)\n\n! GitHub **Ready to merge**, green required checks, and formal review state without Changes-Requested are **necessary but never sufficient** clean signals. Reviewer bots on repos without enforced review wiring often express **should-not-merge** + sub-threshold confidence **only in comment body prose** (no formal `REQUEST_CHANGES`, no blocking CheckRun). A shepherd that merges on mechanical signals alone merges against explicit advisory verdicts.\n\n! **`task pr:merge-ready` / `task pr:watch` / Step 6 clean** MUST parse advisory bot verdict text and confidence from comment bodies (the #1282-style body extraction path; shared detector in `packages/core/src/content-contracts/skills/greptile-detector.ts`). Treat any of the following as **blocking** regardless of formal review state or the Ready-to-merge box:\n\n1. Advisory should-not-merge prose (`should-not-merge`, `Not safe to merge`, `Do not merge`, `Safe to merge once corrected`, `not ready to merge`, …)\n2. Confidence below the resolved `minGreptileConfidence` floor (#3095 — project policy > dogfood 5 > consumer default 4)\n3. P0/P1 findings (triple-tier + inline threads) or errored Greptile sentinel\n\n! When advisory prose blocks or confidence is sub-threshold: continue the fix/document loop or exit **BLOCKED** — ⊗ do not treat mechanical mergeability as CLEAN.\n\n~ Recommend repo-level review-gate wiring (required review / blocking Greptile CheckRun) for org repos that lack it, so formal state and prose verdict cannot diverge silently. Directive dogfood already enforces #3095; portable babysit paths on other org repos still need this prose gate.\n\n⊗ Merge because the merge box says Ready to merge while bot comment prose says should-not-merge or confidence is below the resolved floor (#3225 / #3095).\n⊗ Treat formal Comment (non-blocking) review state as sufficient when the rolling-summary body carries an advisory block.\n\n## Pre-Merge Re-Poll Gate (#1259)\n\n! Immediately before any `gh pr merge` invocation, the agent MUST re-fetch reviewer state ONE more time — a fresh `gh pr view <number> --comments`, a fresh `gh api repos/<owner>/<repo>/commits/<HEAD>/check-runs`, and a fresh HEAD-SHA read — and re-evaluate the Step 6 fail-closed all-of against that fresh fetch. The exit-condition pass recorded at the end of the review loop is NOT sufficient authorization to merge: review state can go stale between the loop's last poll and the merge call (a new push, a Greptile re-trigger, a service-side check-run reset).\n\n! Treat the re-poll and the `gh pr merge` as an atomic freshness window. If the re-poll shows ANY field `unknown`, ABORT the merge and return to Step 2.\n\n! Re-poll MUST also re-check advisory should-not-merge prose + confidence (#3225) — mechanical Ready-to-merge alone is never sufficient.\n\n⊗ Call `gh pr merge` on the strength of a review verdict observed earlier in the loop without an immediately-preceding re-poll that re-satisfies the Step 6 all-of — merging on cached review state is forbidden (#1259).\n⊗ Call `gh pr merge` on mechanical Ready-to-merge / green checks while advisory bot prose still records should-not-merge or sub-threshold confidence (#3225).\n\n### Informal-clean missing canonical fields (#1543)\n\nGreptile can post a **separate** informal clean reply that says prior issues are resolved and the current diff is clean while omitting the canonical rolling-summary fields Directive merge gates require: `Last reviewed commit:` and `Confidence Score: X/5`. `task pr:merge-ready` and `task swarm:verify-review-clean` correctly refuse merge-ready in this state -- prose alone cannot prove review currency or confidence.\n\n! When the latest Greptile bot comment is found, reports P0=0 and P1=0, but BOTH canonical fields are unparsed, classify the state as **`informal-clean missing-canonical-fields`** (see `task pr:merge-ready` diagnostic output) instead of treating it as \"review still writing\" or silently polling.\n\n! Recovery for informal-clean missing canonical fields -- route to ONE of these operator actions; do NOT keep polling:\n\n1. Comment `@greptileai review` on the PR to retrigger a canonical rolling summary on the current HEAD.\n2. Wait for Greptile to edit its primary rolling-summary comment with both canonical fields, then re-run `task pr:merge-ready -- <N>`.\n3. Document an explicit operator override per `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 1 (merge with rationale in the merge commit body).\n\n⊗ Treat informal clean Greptile prose (`current diff is clean`, `looks solid`, `no new issues`) as merge-ready without canonical `Last reviewed commit:` and `Confidence Score: X/5` evidence.\n\n⊗ Keep polling silently when `task pr:merge-ready` reports the informal-clean missing-canonical-fields diagnostic -- this is a blocked recovery state, not a late-arriving review.\n\n~ Swarm pollers MUST surface this state via the `### (6) INFORMAL-CLEAN` terminal exit in `templates/swarm-greptile-poller-prompt.md` instead of falling through to generic `(4) TIMEOUT` or `(5) STALL`.\n\n## Submitting GitHub Reviews\n\n! When submitting PR reviews via the GitHub MCP tool, always use `pull_request_review_write` with method `create` and the appropriate event:\n\n- `APPROVE` — formally approve the PR (shows green \"Approved\" status)\n- `REQUEST_CHANGES` — block the PR with requested changes\n- `COMMENT` — review feedback without approving or blocking\n\n⊗ Use `add_issue_comment` for review notes — that creates a regular comment, not a formal review. Review notes must always go in the review body via `pull_request_review_write`.\n\n## GitHub Interface Selection\n\n~ Use the most efficient interface for the task:\n\n- **MCP GitHub tool** — structured/programmatic operations (querying issues, creating PRs, bulk operations, filtering data)\n- **GitHub CLI (`gh`)** — quick ad-hoc commands and direct shell integration\n\nChoose whichever minimizes steps and maximizes clarity for the given task.\n\n~ When MCP is unavailable (agents without MCP tools in their dispatch environment, including `start_agent` / `spawn_subagent` (\"grok-build\") cases, cloud agents, `oz agent run`), `gh` CLI is sufficient as the sole interface. The dual-source requirement (MCP + `gh`) in Step 1 applies only when both are available -- agents without MCP access should use `gh pr view --comments` and `gh api` as their primary and only review detection surface. Runtime capability detection (swarm Phase 3 matrix) informs both orchestration tier and MCP surface choice.\n\n## Framework Events Emitted Here\n\n! When the user replies `yes` / `confirmed` / `approve` on a ready-to-merge PR thread (Phase 5 -> 6 gate per the canonical #642 workflow comment), emit a `plan:approved` framework event via `task lifecycle:event` so the approval is captured as a structural artifact rather than prose-only:\n\n```\ntask lifecycle:event -- emit plan:approved \\\n  --plan-ref https://github.com/<owner>/<repo>/pull/<N> \\\n  --approver <github-login> \\\n  --approval-phrase <yes|confirmed|approve> \\\n  --pr-number <N>\n```\n\n? Downstream consumers of `plan:approved` (auto-merge bots, status updates, audit reporting) are explicitly deferred to follow-up work; this event currently emits a record only (#635 events behavioral wiring).\n\n## Post-Merge Verification\n\n! Apply [`coding/review.md`](../../coding/review.md) post-merge closing-keyword verification. Adapter HOW for GitHub:\n\n! After a PR is squash-merged, verify that all referenced issues were actually closed. Squash merges can silently fail to process closing keywords (`Closes #N`, `Fixes #N`) from the PR body (#167).\n\n1. ! For each issue referenced with a closing keyword in the PR body, run:\n   ```\n   gh issue view <N> --json state --jq .state\n   ```\n2. ! If the issue state is not `CLOSED`, close it manually with a comment referencing the merged PR:\n   ```\n   gh issue close <N> --comment \"Closed by #<PR> (squash merge — auto-close did not trigger)\"\n   ```\n3. ~ This step mirrors `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 2 and applies to ALL PR merges, not just swarm runs.\n4. ! For PRs that referenced any umbrella / staying-OPEN issue (`Refs #N`), the INVERSE check applies: any protected issue that auto-closed MUST be reopened with a comment citing #701 and the merged PR. See `skills/deft-directive-swarm/SKILL.md` Phase 6 Step 1 protected-issue reopen sweep and `meta/lessons.md` `## GitHub Closing-Keyword False-Positive Layer 3` for the persistent `closingIssuesReferences` link case (Layer 3, #701).\n\n\n## Probe-then-fill remote claims (#3120)\n\n! Before filling any **remote** handoff field (PR URL, PR number, commit/HEAD SHA, CI green/success, review score) or claiming `status: pass` / ship/gate done, MUST **probe then fill**:\n\n1. Run same-turn `git` + forge probes (examples: `git rev-parse HEAD`, `gh api repos/<owner>/<repo>/pulls/<N>`, `task pr:watch -- <N> --one-shot`, checks API).\n2. Copy IDs / URLs / SHAs / scores **only** from that probe JSON/text into the evidence block.\n3. Set `proof_status: bound` and attach short raw probe snippets (`command` + `snippet`) for each remote claim.\n\n! Handoff evidence axes: **work** (local) / **ship** (pushed branch or PR) / **gate** (CI/review on HEAD). `proof_status` is `bound` | `unbound` | `n/a-no-remote-claim`.\n! **Legal partial:** local work `done` + ship `not_started` / `blocked` **without** PR/SHA/CI/review fields and `proof_status: n/a-no-remote-claim` (or `status: partial`) is valid — do not invent ship state.\n! **Fail ranking:** **invented-done** (false/unbound remote artifacts under pass) is **stricter** than **empty-done**. Unbound remote claims → invalid evidence (fail), not pass-with-notes.\n! Machine check: `validateHandoffEvidence` in `packages/core/src/handoff-evidence/` (see `templates/agent-prompt-preamble.md` §11).\n⊗ Fill PR / SHA / CI / review fields from recollection, narration, or prior-turn memory.\n⊗ Claim `status: pass` with remote fields when `proof_status` is not `bound` or probes are missing (#3120).\n\n## Anti-Patterns\n\n- ⊗ Multi-hour empty-commit / close-reopen thrash after CI weather thrash caps when `ci_never_scheduled` or `ci_cancelled_no_failover` (#3167)\n- ⊗ Workflow thrash or empty-commit spam during attributed platform outage without status-page probe (#3180)\n- ⊗ Tight forge-outage retry / empty-commit thrash without a one-shot human report (#3422)\n- ⊗ Merge or `--skip-ci` solely because a status page is red without check-run evidence (#3180)\n- ⊗ Block merge-ready wait on SLizard alone when Greptile Step 6 is clean (#3167)\n- ⊗ Silent admin / `--skip-ci` merge under Actions outage without audit comment and opt-in authority (#3167)\n- ⊗ Leave a deliberate `stop-at: pr-open` (or thin-DONE recovery) open PR without spawning/retaining one review-cycle babysit owner + lease continuity and post-merge `scope:complete` plan (#3153)\n- ⊗ Stand down at CLEAN under human-merge policy without a durable owner (sticky lease + live parent/monitor/Phase 6 closer) **and** a post-CLEAN observe path (poller / parent wake / Phase 6 re-poll) for post-merge `scope:complete` (#3153 / #1193 / #2321)\n- ⊗ Handoff human-merge cleanup to a short-lived leaf that exits at CLEAN without re-claiming the sticky lease (#3153)\n- ⊗ Retain only a sticky lease after CLEAN with no poller, no parent re-entry, and no Phase 6 merge re-poll — ownership-in-name-only (#3153)\n- ⊗ Dual-lease or freestyle Cursor global babysit for the partner merge-path after implement stops at PR-open (#3153 / #2261 / #3044)\n- ⊗ End owning turn with 0 children, no sticky lease, and no finish after drive-to-merge / babysit / shepherd claim — silent hold (#3090)\n- ⊗ Emit freeform `review_cycle: started` / `pending` / `initiated` or L4 `status: pass` without `done` or verifiable `in_progress:<pr>#…` lease/parent-retained (#3090)\n- ⊗ Treat check-run SUCCESS alone as CLEAN / merge-ready while dual-source P0/P1 remain (#3090)\n- ⊗ Ignore [`coding/review.md`](../../coding/review.md) while running this adapter — universal batch/severity/exit/post-merge rules live there\n- ⊗ Route PR shepherding to Cursor global `babysit` on Deft-managed repos when `.deft/core/` is installed -- use this review-cycle skill instead (#2261)\n- ⊗ Route OpenClaw babysit/shepherd/watch to main-session gh poll + cron when `sessions_spawn` is available -- use Approach 1 with `sessions_spawn` (#2876 / #2261)\n- ⊗ Treat OpenClaw `cron` alone as Approach 1 — cron/timer is Approach 2 only if spawn is unavailable (#2876)\n- ⊗ Route Claude Code babysit/shepherd/watch to Approach 3 blocking poll when Claude `Agent` spawn is available — use Approach 1 with backgrounded `Agent` / `claude-agent` (#3134)\n- ⊗ Misclassify Claude Code as `cursor-composer` from bare `Task` alone (#3134)\n- ⊗ Expand active story scope past xBRIEF AC mid-babysit without follow-up issue or consented brief amend (#2881)\n- ⊗ Treat confidence-only holds (0 P0/P1) as a mandate for unbounded redesign (#2881)\n- ⊗ Dual-stop / conf-residual terminal halt without #3273 resume line (leftover class + residual class + resolved floor + standing vs one-shot + pursue residual / until floor or loop + skill section pointer) (#3273 / #3448)\n- ⊗ Unlimited residual auto-retry after dual-stop without new operator consent (#3273 / #2442)\n- ⊗ Hard-code 5/5 as the continue-until target, or treat one-shot `pursue residual` as standing, or park a class A already-touched leftover as a new story (#3448 / #2881 / #3095)\n- ⊗ Invent freestyle sleep/poll loops when dual-invoke probes fail for `pr:watch` — use the official gh-only fallback and fail-loud missing-task (#2878 / #2893)\n- ⊗ Treat bare `task pr:watch` as the only consumer gate form — probe `deft` then `task deft:` first (#2893)\n- ⊗ Treat a passing SLizard/Greptile check run, a non-blocking review comment, or an ad hoc fix commit as the review-cycle exit predicate -- Step 6 fail-closed all-of (#1259) and multi-reviewer registry triage (#769) still apply\n- ⊗ Push individual fix commits per finding\n- ⊗ Start fixing before analyzing ALL findings\n- ⊗ Rely on the bot to catch syntax errors in structured data files\n- ⊗ Re-trigger a bot review before the previous one has updated\n- ⊗ Report \"all comments resolved\" without checking both `gh pr view --comments` and a second source (`get_review_comments` via MCP, or `gh api` fallback when MCP is unavailable)\n- ⊗ Use `add_issue_comment` for formal review submission\n- ⊗ Commit or push Phase 1 audit fixes independently — always batch with Phase 2 fixes\n- ⊗ Proceed to Phase 2 while any Phase 1 prerequisite is unmet\n- ⊗ Rely solely on `pulls/{number}/reviews` to detect whether Greptile has reviewed the latest commit — Greptile may update via an edited issue comment instead of a new review object\n- ⊗ Push additional commits while Greptile is reviewing the current head — each push re-triggers Greptile and resets the review clock\n- ⊗ Use blocking `Start-Sleep` shell loops or `time.sleep()` loops to poll for review updates when Approach 1 or 2 is available -- Approach 3 (blocking loop) is permitted only as a last resort with user warning\n- ⊗ Poll more frequently than every 20 seconds -- use a real delay between checks, not back-to-back calls; adaptive cadence (20-30s / 60s / 90s) replaces the fixed 60s minimum\n- ⊗ Stop and ask the user whether to continue after pushing -- the review/fix loop MUST run autonomously to the exit condition\n- ⊗ Push fix commits without scanning changed lines for untested code paths — always check test coverage before pushing\n- ⊗ Push a fix commit that addresses fewer findings than the current Greptile review surfaces — if Greptile flags 3 issues, all 3 must be fixed in one commit before pushing\n- ⊗ Push after fixing a P1 without first checking whether the same Greptile review contains additional P0 or P1 findings\n- ⊗ Assume squash merge auto-closed referenced issues — always verify with `gh issue view` after merge (#167)\n- ⊗ Assume Approach 2 (yield-between-polls) produces a self-sustaining polling loop -- yielding ends the agent's turn with no self-wake; swarm agents will silently stop polling\n- ⊗ Skip the second review source (MCP or `gh api` fallback) without probing for MCP capability and documenting the fallback used\n- ⊗ Run a partial test suite instead of `task check` without documenting the pre-existing failure reason and open issue number in the PR body\n- ⊗ Create a PR without running `skills/deft-directive-pre-pr/SKILL.md` first -- the pre-PR quality loop catches issues before they reach the reviewer\n- ⊗ Activate Approach 3 (blocking `Start-Sleep` loop) without first warning the user that it will lock the conversation pane and receiving confirmation\n- ⊗ Exit the review loop on a Greptile confidence number alone while the check run is non-terminal -- a confidence score is NOT a verdict without a terminal check-run (`completed` + `{success, neutral}`) AND a HEAD-matching `Last reviewed commit:` completion marker (#1259)\n- ⊗ Call `gh pr merge` on cached/earlier review state without an immediately-preceding pre-merge re-poll that re-satisfies the Step 6 fail-closed all-of (#1259)\n- ⊗ Merge on mechanical Ready-to-merge / green checks while bot comment prose records should-not-merge or confidence below `minGreptileConfidence` (#3225 / #3095)\n- ⊗ Treat formal non-blocking review state as sufficient when rolling-summary body carries an advisory block (#3225)\n- ⊗ Treat empty/unknown review-monitor settle as DONE/CLEAN/merge-ready without same-turn ground truth (#3044 / FC04 residual)\n- ⊗ Spawn a second review-monitor while prior owner is running or last settle was empty/unknown without terminal ground truth (#3044)\n- ⊗ Accept empty review-monitor final message missing STATUS/HEAD/CHECKS/MERGE handback (#3044)\n- ⊗ Invent remote PR/SHA/CI/review claims in handoff evidence without same-turn probe binding — invented-done (#3120)\n- ⊗ Fill remote ship/gate fields from memory when only local work completed; legal partial omits PR fields (#3120)",
       "frontmatter_extra": null
     },
     {
@@ -306,7 +334,7 @@
       ],
       "path": "skills/deft-directive-swarm/SKILL.md",
       "version": "0.1",
-      "body": "# Deft Directive Swarm\n\nStructured workflow for a monitor agent to orchestrate N parallel local agents working on story-level xBRIEFs from `xbrief/active/`.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n**⚠️ See also**: [swarm.md](../../swarm/swarm.md) | [deft-directive-review-cycle](../deft-directive-review-cycle/SKILL.md)\n\n## Platform Requirements\n\n! This skill requires **GitHub** as the SCM platform and the **GitHub CLI (`gh`)** to be installed and authenticated. Issue fetching, PR creation, and post-merge verification all depend on `gh`.\n\n## Branch-Protection Policy Guard\n\n! Before any state mutation (creating worktrees, dispatching sub-agents, opening PRs), run the skill-level branch-policy guard (#746 / #747). Halt with the actionable disclosure message when the project's `plan.policy.allowDirectCommitsToMaster` is unresolvable AND `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT` is unset:\n\n```\ntask verify:branch || exit 1\n```\n\nThe swarm skill creates branches per agent so the guard is mostly informational here, but a malformed PROJECT-DEFINITION (missing `plan.policy` block AND no legacy narrative) is a fail-closed signal worth surfacing before the swarm spawns N agents.\n\n### Forge-outage drop-back (#3422)\n\n! On attributed platform outage or repeated REST 429/502/503: drop GitHub I/O, report once to the human in chat, and re-probe on `plan.policy.forgeOutageRetryMinutes` (default **30**; USER.md Personal wins; min 5; `task policy:show --field=forgeOutageRetryMinutes`). Local work that does not need the forge MAY continue. Depth: [`scm/github.md`](../../scm/github.md) § #3180 / #3422. Complements #3167 / #3180.\n\n⊗ Tight retry, empty-commit thrash, or sending the human to github.com as the only remediation.\n⊗ Auto-merge / `--skip-ci` because a status page is red.\n\n## Deterministic Questions Contract\n\n! Every numbered-menu prompt rendered in this skill (Phase 0 Step 0 queue-driven promote prompts (#1142 / N2), Step 0.5 bridge approval gate, Step 5 final-approval gate, Phase 1 Step 3 file-overlap audit gate, Phase 5->6 ready-to-merge gate) MUST follow [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md): render the canonical numbered menu in chat unless the host UI visibly preserves numeric option labels and returns numeric selections or exact displayed option text. The final two numbered options MUST be `Discuss` and `Back`, in that order. The Discuss-pause semantic is documented verbatim there -- on `Discuss` selection the agent MUST halt the in-progress sequence immediately, prompt `What would you like to discuss?`, and resume only on an explicit user signal. Implicit resumption is forbidden, and fallback chat replies MUST map only to the displayed number or exact displayed option text.\n\n## When to Use\n\n- User says \"run agents\", \"parallel agents\", \"swarm\", or \"launch N agents on stories\"\n- Multiple independent story-level xBRIEFs in `xbrief/active/` need to be worked on simultaneously\n- A batch of stories are ready and have no mutual dependencies\n- Operator re-authorizes a dual-stopped / hard-stopped / conf-hold unit: **pursue residual**, **follow-up hard-stop**, **same as conf-hold**, **continue dual-stopped PR**, or **re-babysit residual** — route to § Operator follow-up after dual-stop / hard stop (#3273) **one-shot** path\n- Operator issues a **standing residual order**: **until floor or loop**, **until greptile meets policy**, or **pursue residuals until told otherwise** — route to the same § **standing** path (#3448); applies to open cohort / ordered-plan units, not only the last halted PR\n\n## Prerequisites\n\n- ! `xbrief/active/` contains one or more story-level xBRIEFs with status `running`\n- ! GitHub CLI (`gh`) is authenticated\n- ! `git` supports worktrees (`git worktree` available)\n- ~ `oz` CLI available (for `oz agent run-cloud` cloud launch — see host-generic / Phase 3)\n\n## Host-adapter load path (#2928)\n\nLarge multi-host skills use a **host-neutral core** plus **one** per-host adapter after detect.\n\n| Step | Action |\n|------|--------|\n| 1 | Read this thin SKILL (triggers, MUST gates, detect, route table) |\n| 2 | Run **Runtime Capability Detection** (below) → stable platform descriptor |\n| 3 | Load host-neutral depth: `references/core-phase-*.md` + `references/core-ops.md` as needed for the current phase |\n| 4 | Load **exactly one** `references/host-*.md` from the route table |\n| 5 | Launch / monitor / hand off using core + that adapter only |\n\n### Route table (detect → one adapter)\n\n| Detected descriptor | Spawn primitive | Load adapter |\n|---------------------|-----------------|--------------|\n| `warp-orchestrated` / `warp-manual` | `start_agent` / Warp tabs | [`references/host-warp.md`](references/host-warp.md) |\n| `cursor-composer` / `cursor-cloud-agent` | Cursor `Task` | [`references/host-cursor.md`](references/host-cursor.md) |\n| `claude-code` | Claude `Agent` (`run_in_background`) / `claude-agent` | [`references/host-claude-code.md`](references/host-claude-code.md) |\n| `openclaw` | `sessions_spawn` | [`references/host-openclaw.md`](references/host-openclaw.md) |\n| `grok-build` | `spawn_subagent` | [`references/host-grok-build.md`](references/host-grok-build.md) |\n| `generic-terminal` (or explicit cloud) | serial / paste / `oz agent run-cloud` | [`references/host-generic.md`](references/host-generic.md) |\n\n### Core reference index (host-neutral)\n\n| Phase / topic | File |\n|---------------|------|\n| Phase 0 — Allocate | [`references/core-phase-0.md`](references/core-phase-0.md) |\n| Phase 1–2 — Select + Setup | [`references/core-phase-1-2.md`](references/core-phase-1-2.md) |\n| Phase 3 — Launch (neutral + detect detail) | [`references/core-phase-3.md`](references/core-phase-3.md) |\n| Phase 4 — Monitor | [`references/core-phase-4.md`](references/core-phase-4.md) |\n| Phase 5–6 — Review + Close | [`references/core-phase-5-6.md`](references/core-phase-5-6.md) |\n| Crash recovery, prompts, anti-patterns | [`references/core-ops.md`](references/core-ops.md) |\n\n⊗ Load all host adapters “just in case.” Unused host wiring stays out of context (#2928).\n≉ Paste full host manuals into this thin SKILL — keep detect short; depth lives in one adapter.\n\n## Hard gates (all hosts)\n\n### Worktree isolation before parallel spawn\n\n! One isolated git worktree per parallel agent (Phase 2). Create worktrees or consume a worktree-map **before** dispatch.\n! On **OpenClaw**, parallel leaves: worktree or worktree-map **before** `sessions_spawn`; worker cwd = that worktree; fail loud if the cohort would share the repo root (#2929). Full rules: [`references/host-openclaw.md`](references/host-openclaw.md).\n⊗ DIY multi-leaf `sessions_spawn` without worktree prep (#2929).\n\n### Next-phase tool dispatch (#2934)\n\n! After a coding cohort completes (last expected child completion / cohort phase boundary), the parent **MUST** in the **same turn** either:\n- dispatch the next phase with a real tool call (`sessions_spawn` / host spawn / `task swarm:launch` / review-cycle start / merge cascade start), **or**\n- write explicit terminal status (`blocked` / `awaiting-human` / `done`) with a machine-checkable reason.\n\n⊗ End the turn with only narrative “I will spawn…” / “review next” and zero tools (#2934).\n~ Keep a small phase-state note: `cohort_id → phase → next_action|terminal`.\n\n### Parent-monitor after leaf announce (#2943 / hard-stop #3131)\n\n! After any leaf completion event (`subagent_announce` / parent-push / host completion notify), the parent’s **first response** MUST be one of:\n- tool-first ground-truth batch (`gh` / `git` / worktree or file status) then one consolidate, **or**\n- host yield (`sessions_yield` on OpenClaw, or equivalent), **or**\n- one short user answer that is **not** a repeated progress line.\n\n! **Hard-stop (machine-checkable, not prose-only):** **MUST NOT** emit N>2 near-identical assistant sentences (or streaming text chunks) in one turn with no `tool_use` / yield — **FC14** text-repetition hang. Library: `evaluateParentTurnShape` in `@deftai/directive-core/parent-turn-shape` (`packages/core/src/parent-turn-shape/`). Hosts SHOULD abort the turn when `ok === false`. Operator recovery: `docs/openclaw-agent-host.md` § Operator recovery — FC14. Soft skill text is **not** sole mitigation (#3131).\n\n! **Thin DONE = failed leaf:** completion without PR URL / merge evidence is **failed** (re-dispatch or take over) — not success. Prefer structured fields when present (`prUrl`, `mergeStatus`, `emptyDiff`).\n\n⊗ Multi-sentence progress-only first response after announce with zero tools / yield (#2943 text-repetition hang).\n⊗ N>2 near-identical assistant sentences with no tool_use / yield (FC14 / #3131 hard-stop).\n⊗ Treat thin DONE (no PR URL / merge evidence) as success (#2943).\n⊗ Rely on soft skill prose alone as the sole mitigation for the parent hang (#3131).\n\n\n\n### Completion latch after first consolidate (#3092)\n\n! After the parent emits **one** user/caller-visible consolidate for a child `runId` / settle batch, **identical or equivalent completion replay** for the same key MUST be **silent** (no tools, no re-QC, no second final; host silent token when defined, e.g. OpenClaw `NO_REPLY`). Re-open only on new `runId`/batch, principal explicit reopen, or materially new evidence (new HEAD, new blocker class). Replay storms: at most one fail-loud note, then silent. Full MUST: `templates/agent-prompt-preamble.md` §11.5. Depth: `references/core-phase-5-6.md`. Orthogonal to empty settle ≠ done (#3044).\n\n### Dual stop — repair and monitor loops (#2442)\n\n! Multi-iteration swarm **repair** and **monitor** loops MUST carry dual stop: success (goal/AC/clean gate) **and** a failure/budget stop. Single-turn probes (one status check, one heartbeat read) are exempt. Principle: `main.md` `## Dual Stop Rule (#2442)`. Defaults and halt-report shape live in [`references/core-phase-4.md`](references/core-phase-4.md) (monitor / takeover) and [`references/core-ops.md`](references/core-ops.md) (prompts + anti-patterns).\n\n! Default failure envelope for repair/monitor class work (unless the operator or xBRIEF names a stricter one):\n- **max iterations:** 3 monitor repair actions (re-dispatch, takeover complete, re-trigger review) for the same leaf/PR failure class, **or**\n- **no-progress:** same error / same idle state **3+** times with no material worktree or review change (composes with Phase 4 \"stuck in an error loop\" takeover trigger). Same-fingerprint Greptile residual uses [`deft-directive-review-cycle/SKILL.md`](../deft-directive-review-cycle/SKILL.md) Dual stop — **Same-fingerprint stop**. **or**\n- **budget:** existing poll caps (`pr:watch` max-wait, Greptile service-error single retry + escalate) count as budget stops -- do not invent a second unbounded poll loop outside them.\n\n! On failure stop: halt automatic continuation; emit an operator-visible report (what was tried, what is missing, what human decision is needed). ⊗ Silent re-dispatch or infinite monitor continuation after the envelope is exhausted.\n\n! **Halt-report resume line (MUST, #3273 / #3448):** Terminal dual-stop / hard-stop / conf-residual halt reports MUST end with leftover class (A/B/C) + residual class + conf (if any) + resolved `#3095` floor + standing vs one-shot + PR URL (`leftover=` / `floor=` / `standing=`). One-shot phrases: **pursue residual** | **follow-up hard-stop** | **same as conf-hold** | **continue dual-stopped PR**. Standing phrases: **until floor or loop** | **until greptile meets policy** | **pursue residuals until told otherwise**. Pointer to § Operator follow-up after dual-stop / hard stop. Full template: [`references/core-phase-4.md`](references/core-phase-4.md).\n\n! Composes with minimal-subgraph repair guidance (#2439): keep repairs minimal **and** bounded by dual-stop -- minimal repair is not a license to thrash. Durable delivery/acceptance circuit-breaker: **#3143** `packages/core/src/delivery-attempt/` (`evaluatePreDispatch`, unit ledger). Docs: `docs/delivery-attempt.md`. Skill defaults remain behavioral; mechanical gate lives in core.\n\n### Operator follow-up after dual-stop / hard stop (#3273)\n\nOperator-initiated resume after dual-stop / hard stop / conf-hold — not automatic re-thrash. Depth (A/B/C leftover classes, standing vs one-shot, steps): [`references/core-phase-4.md`](references/core-phase-4.md) same section title. Portable consumer + maintainer (`task` / `deft` dual-invoke). Continue-until target is the **resolved `#3095` floor** (`task policy:show --field=minGreptileConfidence` / `deft policy:show --field=minGreptileConfidence`: typed project policy > framework dogfood **5** > consumer default **4**). ⊗ Hard-code 5/5. ⊗ Lower project policy to clear one PR.\n\n**Leftover classes (A/B/C, #3448):** **class A** named leftover on already-touched files = in-AC residual, auto-continue under standing until floor or same-fingerprint loop. **class B** new subsystem / AC fight = park or follow-up. **class C** score-only = document / same-as-conf-hold. Already-touched leftover is class A unless it needs a new ledger/protocol/story (#2881).\n\n**One-shot vs standing:** one-shot `pursue residual` = one pass then re-stop. Standing (`until floor or loop` / `until greptile meets policy` / `pursue residuals until told otherwise`) applies to **open cohort / ordered-plan units**, not only the last halted PR. Same-fingerprint stop: [`deft-directive-review-cycle/SKILL.md`](../deft-directive-review-cycle/SKILL.md) Dual stop (normative). `#2442` batch cap still applies.\n\nThin pointer: dual-invoke `pr:merge-ready` / `pr:watch`; spawn **one** residual worker or review-cycle owner per batch; document authorized conf floor for this PR only as human-merge/override trail (⊗ silent policy rewrite; `pr:merge-ready` still uses policy floor). ⊗ Unlimited auto-retry. ⊗ Parent self-implement (#2843).\n\n## Runtime Capability Detection (summary)\n\n! Before selecting a launch method, probe the environment. Full probe text: [`references/core-phase-3.md`](references/core-phase-3.md).\n\n1. ! **Probe for `start_agent` tool** — Warp orchestrated.\n2. ! **Probe for Warp environment** — `WARP_*` without `start_agent` → warp-manual.\n3. ! **Probe for the Cursor `Task` tool** — Tier 1; descriptor `cursor-composer` / `cursor-cloud-agent` (#1877). Require Cursor signals (`CURSOR_*` or Cursor-only Task surface) — not bare `Task` alone.\n4. ! **Probe for Claude Code** — Tier 1; descriptor `claude-code` (#3134). Claude-unique signals only: `Agent` (or `CreateAgent` / `SubagentStart`) with background / `run_in_background`, and/or `DEFT_PROBE_CLAUDE_CODE` / `DEFT_AGENT_RUNTIME=claude-code` / `CLAUDECODE`. ⊗ Misclassify as `cursor-composer` via bare `Task`.\n5. ! **Probe for the OpenClaw `sessions_spawn` tool** — Tier 1; descriptor `openclaw` (#2875). Do NOT misclassify as `grok-build` or `generic-terminal`.\n6. ! **Probe for `spawn_subagent` tool** — descriptor `grok-build`.\n7. ! **Select launch path automatically** — load the matching host adapter (route table). No static A/B/C menu.\n8. ! **Return a stable platform descriptor** for Phase 4/6: `warp-orchestrated`, `warp-manual`, `cursor-composer`, `cursor-cloud-agent`, `claude-code`, `openclaw`, `grok-build`, or `generic-terminal`.\n9. ? **Cloud escape hatch** — `oz agent run-cloud` only on explicit user request (host-generic).\n\n⊗ Present static launch options instead of detecting capabilities at runtime.\n⊗ Offer Warp-specific launch paths when not inside Warp.\n⊗ Classify Claude Code as `cursor-composer` / `generic-terminal` when Claude-unique signals are present (#3134).\n\n## Retained addressable sub-agents (#3158)\n\nNamed mode **beside** dispatch-and-collect. Canon: [`../../swarm/swarm.md`](../../swarm/swarm.md) `## Retained addressable sub-agents (#3158)`.\n\n| Mode | When | Mid-scope gate |\n|------|------|----------------|\n| **retained-child** (message-later / steer-mid-flight) | Host keeps a live, addressable child (`agent_id` / session name); parent can re-message or steer mid-flight | Single dispatch MAY pause for approval and continue the **same** child |\n| **dispatch-and-collect** (one-shot) | Host has no continue/resume; worker terminal on tool-loop exit | **Split-dispatch** mandatory (#954): Scope A → report → approve → Scope B |\n\n! After platform detect, read the loaded host adapter's **Retained / continue-by-id** note. Prefer continue-by-agent-id / resume-by-name / steerable mid-flight **only when that adapter documents support**.\n! When the host cannot retain: keep one-shot envelopes and split-dispatch mid-scope gates. Do not claim message-later semantics the platform cannot deliver.\n! Stance (#3164): retention is **orchestration only** — not mid-run constitution self-edit (managed AGENTS, pinned skills, policy).\n! Topology (#3155): retained children MUST obey nuclear-family A2A bounds (parent/sibling/child only).\n⊗ Force a second full dispatch on a retain-capable host solely because a mid-scope gate exists — re-message the live child instead.\n⊗ Invent retain / resume on hosts whose adapter marks one-shot only.\n\n## Phase overview\n\n| Phase | Goal | Depth |\n|-------|------|-------|\n| 0 Allocate | Queue cohort, readiness, approval | `core-phase-0.md` |\n| 1 Select | Confirm candidates, file-overlap | `core-phase-1-2.md` |\n| 2 Setup | Worktrees + prompt files | `core-phase-1-2.md` |\n| 3 Launch | Detect, preflight, **one** host spawn | `core-phase-3.md` + **one** `host-*.md` |\n| 4 Monitor | Heartbeats, takeover, no duplicate agents | `core-phase-4.md` (+ host notes) |\n| 5 Review | Greptile clean, gates, **next-phase tools** | `core-phase-5-6.md` |\n| 6 Close | Merge cascade, cohort sweep, cleanup | `core-phase-5-6.md` |\n\n! Follow phases in order. Depth files hold the operative MUST rules; this page is the dispatch card.\n\n## Effort estimate on dispatch (#1581)\n\n! When plan items carry optional `effort` (S/M/L/XL with time anchors in `vbrief/vbrief.md`), use them for sizing: S/M single-agent, L may need a dedicated agent, XL blocks dispatch until broken into S/M/L. Activate fails closed on XL. Depth: [`references/core-phase-0.md`](references/core-phase-0.md) Steps 2–3.\n! Plan-item effort is **post-planning** (confirms/corrects provisional intake estimates). It is **not** session-start ritual input; ceremony dial (#3214) starts rapid and escalates — do not block cold-start ritual on missing plan-item `effort`. Headless: no operator confirmation for size or stage transitions.\n\n## Critical anti-patterns (dispatch card)\n\n- ⊗ Load all host adapters “just in case” (#2928)\n- ⊗ Parallel OpenClaw `sessions_spawn` on shared repo root without worktrees (#2929)\n- ⊗ Prose-only phase handoff after cohort complete (“I will spawn…”) (#2934)\n- ⊗ Multi-sentence progress-only first response after leaf announce with zero tools / yield (#2943)\n- ⊗ N>2 near-identical assistant sentences with no tool_use / yield (FC14 / #3131 hard-stop)\n- ⊗ Treat thin DONE (no PR URL / merge evidence) as success (#2943)\n- ⊗ Rely on soft skill prose alone as the sole parent-hang mitigation (#3131)\n- ⊗ Second+ user-visible consolidate for the same child runId without new evidence (#3092)\n- ⊗ Assign overlapping files to multiple agents\n- ⊗ Dispatch or activate work that still has `plan.items[].effort: \"XL\"` without breakdown (#1581)\n- ⊗ Merge before Greptile exit condition (score > 3, no P0/P1)\n- ⊗ Skip Phase 0 approval before Phase 1\n- ⊗ Misclassify OpenClaw `sessions_spawn` as `grok-build` or `generic-terminal` (#2875)\n- ⊗ Misclassify Claude Code as `cursor-composer` / `generic-terminal` (#3134)\n- ⊗ Run multi-iteration repair/monitor loops without a failure stop or with silent continuation after the envelope is exhausted (#2442)\n- ⊗ Dual-stop/hard-stop halt without #3273 resume line (leftover class + resolved floor + standing vs one-shot), or unlimited residual auto-retry without new operator consent (#3273 / #3448)\n- ⊗ Hard-code 5/5 as the continue-until target, or park a class A already-touched leftover as a new story (#3448 / #2881 / #3095)\n- ⊗ Force a second full dispatch on a retain-capable host solely for a mid-scope gate, or invent retain on one-shot hosts (#3158)\n- ⊗ Use retained-child messaging for mid-run constitution self-edit (#3158 / #3164)\n- ⊗ Tight forge-outage retry / empty-commit thrash without a one-shot human report (#3422)\n\nFull anti-pattern list: [`references/core-ops.md`](references/core-ops.md).",
+      "body": "# Deft Directive Swarm\n\nStructured workflow for a monitor agent to orchestrate N parallel local agents working on story-level xBRIEFs from `xbrief/active/`.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n**⚠️ See also**: [swarm.md](../../swarm/swarm.md) | [deft-directive-review-cycle](../deft-directive-review-cycle/SKILL.md)\n\n## Platform Requirements\n\n! This skill requires **GitHub** as the SCM platform and the **GitHub CLI (`gh`)** to be installed and authenticated. Issue fetching, PR creation, and post-merge verification all depend on `gh`.\n\n## Branch-Protection Policy Guard\n\n! Before any state mutation (creating worktrees, dispatching sub-agents, opening PRs), run the skill-level branch-policy guard (#746 / #747). Halt with the actionable disclosure message when the project's `plan.policy.allowDirectCommitsToMaster` is unresolvable AND `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT` is unset:\n\n```\ndeft verify:branch || exit 1\n```\n\nThe swarm skill creates branches per agent so the guard is mostly informational here, but a malformed PROJECT-DEFINITION (missing `plan.policy` block AND no legacy narrative) is a fail-closed signal worth surfacing before the swarm spawns N agents.\n\n### Forge-outage drop-back (#3422)\n\n! On attributed platform outage or repeated REST 429/502/503: drop GitHub I/O, report once to the human in chat, and re-probe on `plan.policy.forgeOutageRetryMinutes` (default **30**; USER.md Personal wins; min 5; `task policy:show --field=forgeOutageRetryMinutes`). Local work that does not need the forge MAY continue. Depth: [`scm/github.md`](../../scm/github.md) § #3180 / #3422. Complements #3167 / #3180.\n\n⊗ Tight retry, empty-commit thrash, or sending the human to github.com as the only remediation.\n⊗ Auto-merge / `--skip-ci` because a status page is red.\n\n## Deterministic Questions Contract\n\n! Every numbered-menu prompt rendered in this skill (Phase 0 Step 0 queue-driven promote prompts (#1142 / N2), Step 0.5 bridge approval gate, Step 5 final-approval gate, Phase 1 Step 3 file-overlap audit gate, Phase 5->6 ready-to-merge gate) MUST follow [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md): render the canonical numbered menu in chat unless the host UI visibly preserves numeric option labels and returns numeric selections or exact displayed option text. The final two numbered options MUST be `Discuss` and `Back`, in that order. The Discuss-pause semantic is documented verbatim there -- on `Discuss` selection the agent MUST halt the in-progress sequence immediately, prompt `What would you like to discuss?`, and resume only on an explicit user signal. Implicit resumption is forbidden, and fallback chat replies MUST map only to the displayed number or exact displayed option text.\n\n## When to Use\n\n- User says \"run agents\", \"parallel agents\", \"swarm\", or \"launch N agents on stories\"\n- Multiple independent story-level xBRIEFs in `xbrief/active/` need to be worked on simultaneously\n- A batch of stories are ready and have no mutual dependencies\n- Operator re-authorizes a dual-stopped / hard-stopped / conf-hold unit: **pursue residual**, **follow-up hard-stop**, **same as conf-hold**, **continue dual-stopped PR**, or **re-babysit residual** — route to § Operator follow-up after dual-stop / hard stop (#3273) **one-shot** path\n- Operator issues a **standing residual order**: **until floor or loop**, **until greptile meets policy**, or **pursue residuals until told otherwise** — route to the same § **standing** path (#3448); applies to open cohort / ordered-plan units, not only the last halted PR\n\n## Prerequisites\n\n- ! `xbrief/active/` contains one or more story-level xBRIEFs with status `running`\n- ! GitHub CLI (`gh`) is authenticated\n- ! `git` supports worktrees (`git worktree` available)\n- ~ `oz` CLI available (for `oz agent run-cloud` cloud launch — see host-generic / Phase 3)\n\n## Host-adapter load path (#2928)\n\nLarge multi-host skills use a **host-neutral core** plus **one** per-host adapter after detect.\n\n| Step | Action |\n|------|--------|\n| 1 | Read this thin SKILL (triggers, MUST gates, detect, route table) |\n| 2 | Run **Runtime Capability Detection** (below) → stable platform descriptor |\n| 3 | Load host-neutral depth: `references/core-phase-*.md` + `references/core-ops.md` as needed for the current phase |\n| 4 | Load **exactly one** `references/host-*.md` from the route table |\n| 5 | Launch / monitor / hand off using core + that adapter only |\n\n### Route table (detect → one adapter)\n\n| Detected descriptor | Spawn primitive | Load adapter |\n|---------------------|-----------------|--------------|\n| `warp-orchestrated` / `warp-manual` | `start_agent` / Warp tabs | [`references/host-warp.md`](references/host-warp.md) |\n| `cursor-composer` / `cursor-cloud-agent` | Cursor `Task` | [`references/host-cursor.md`](references/host-cursor.md) |\n| `claude-code` | Claude `Agent` (`run_in_background`) / `claude-agent` | [`references/host-claude-code.md`](references/host-claude-code.md) |\n| `openclaw` | `sessions_spawn` | [`references/host-openclaw.md`](references/host-openclaw.md) |\n| `grok-build` | `spawn_subagent` | [`references/host-grok-build.md`](references/host-grok-build.md) |\n| `generic-terminal` (or explicit cloud) | serial / paste / `oz agent run-cloud` | [`references/host-generic.md`](references/host-generic.md) |\n\n### Core reference index (host-neutral)\n\n| Phase / topic | File |\n|---------------|------|\n| Phase 0 — Allocate | [`references/core-phase-0.md`](references/core-phase-0.md) |\n| Phase 1–2 — Select + Setup | [`references/core-phase-1-2.md`](references/core-phase-1-2.md) |\n| Phase 3 — Launch (neutral + detect detail) | [`references/core-phase-3.md`](references/core-phase-3.md) |\n| Phase 4 — Monitor | [`references/core-phase-4.md`](references/core-phase-4.md) |\n| Phase 5–6 — Review + Close | [`references/core-phase-5-6.md`](references/core-phase-5-6.md) |\n| Crash recovery, prompts, anti-patterns | [`references/core-ops.md`](references/core-ops.md) |\n\n⊗ Load all host adapters “just in case.” Unused host wiring stays out of context (#2928).\n≉ Paste full host manuals into this thin SKILL — keep detect short; depth lives in one adapter.\n\n## Hard gates (all hosts)\n\n### Worktree isolation before parallel spawn\n\n! One isolated git worktree per parallel agent (Phase 2). Create worktrees or consume a worktree-map **before** dispatch.\n! On **OpenClaw**, parallel leaves: worktree or worktree-map **before** `sessions_spawn`; worker cwd = that worktree; fail loud if the cohort would share the repo root (#2929). Full rules: [`references/host-openclaw.md`](references/host-openclaw.md).\n⊗ DIY multi-leaf `sessions_spawn` without worktree prep (#2929).\n\n### Next-phase tool dispatch (#2934)\n\n! After a coding cohort completes (last expected child completion / cohort phase boundary), the parent **MUST** in the **same turn** either:\n- dispatch the next phase with a real tool call (`sessions_spawn` / host spawn / `task swarm:launch` / review-cycle start / merge cascade start), **or**\n- write explicit terminal status (`blocked` / `awaiting-human` / `done`) with a machine-checkable reason.\n\n⊗ End the turn with only narrative “I will spawn…” / “review next” and zero tools (#2934).\n~ Keep a small phase-state note: `cohort_id → phase → next_action|terminal`.\n\n### Parent-monitor after leaf announce (#2943 / hard-stop #3131)\n\n! After any leaf completion event (`subagent_announce` / parent-push / host completion notify), the parent’s **first response** MUST be one of:\n- tool-first ground-truth batch (`gh` / `git` / worktree or file status) then one consolidate, **or**\n- host yield (`sessions_yield` on OpenClaw, or equivalent), **or**\n- one short user answer that is **not** a repeated progress line.\n\n! **Hard-stop (machine-checkable, not prose-only):** **MUST NOT** emit N>2 near-identical assistant sentences (or streaming text chunks) in one turn with no `tool_use` / yield — **FC14** text-repetition hang. Library: `evaluateParentTurnShape` in `@deftai/directive-core/parent-turn-shape` (`packages/core/src/parent-turn-shape/`). Hosts SHOULD abort the turn when `ok === false`. Operator recovery: `docs/openclaw-agent-host.md` § Operator recovery — FC14. Soft skill text is **not** sole mitigation (#3131).\n\n! **Thin DONE = failed leaf:** completion without PR URL / merge evidence is **failed** (re-dispatch or take over) — not success. Prefer structured fields when present (`prUrl`, `mergeStatus`, `emptyDiff`).\n\n⊗ Multi-sentence progress-only first response after announce with zero tools / yield (#2943 text-repetition hang).\n⊗ N>2 near-identical assistant sentences with no tool_use / yield (FC14 / #3131 hard-stop).\n⊗ Treat thin DONE (no PR URL / merge evidence) as success (#2943).\n⊗ Rely on soft skill prose alone as the sole mitigation for the parent hang (#3131).\n\n\n\n### Completion latch after first consolidate (#3092)\n\n! After the parent emits **one** user/caller-visible consolidate for a child `runId` / settle batch, **identical or equivalent completion replay** for the same key MUST be **silent** (no tools, no re-QC, no second final; host silent token when defined, e.g. OpenClaw `NO_REPLY`). Re-open only on new `runId`/batch, principal explicit reopen, or materially new evidence (new HEAD, new blocker class). Replay storms: at most one fail-loud note, then silent. Full MUST: `templates/agent-prompt-preamble.md` §11.5. Depth: `references/core-phase-5-6.md`. Orthogonal to empty settle ≠ done (#3044).\n\n### Dual stop — repair and monitor loops (#2442)\n\n! Multi-iteration swarm **repair** and **monitor** loops MUST carry dual stop: success (goal/AC/clean gate) **and** a failure/budget stop. Single-turn probes (one status check, one heartbeat read) are exempt. Principle: `main.md` `## Dual Stop Rule (#2442)`. Defaults and halt-report shape live in [`references/core-phase-4.md`](references/core-phase-4.md) (monitor / takeover) and [`references/core-ops.md`](references/core-ops.md) (prompts + anti-patterns).\n\n! Default failure envelope for repair/monitor class work (unless the operator or xBRIEF names a stricter one):\n- **max iterations:** 3 monitor repair actions (re-dispatch, takeover complete, re-trigger review) for the same leaf/PR failure class, **or**\n- **no-progress:** same error / same idle state **3+** times with no material worktree or review change (composes with Phase 4 \"stuck in an error loop\" takeover trigger). Same-fingerprint Greptile residual uses [`deft-directive-review-cycle/SKILL.md`](../deft-directive-review-cycle/SKILL.md) Dual stop — **Same-fingerprint stop**. **or**\n- **budget:** existing poll caps (`pr:watch` max-wait, Greptile service-error single retry + escalate) count as budget stops -- do not invent a second unbounded poll loop outside them.\n\n! On failure stop: halt automatic continuation; emit an operator-visible report (what was tried, what is missing, what human decision is needed). ⊗ Silent re-dispatch or infinite monitor continuation after the envelope is exhausted.\n\n! **Halt-report resume line (MUST, #3273 / #3448):** Terminal dual-stop / hard-stop / conf-residual halt reports MUST end with leftover class (A/B/C) + residual class + conf (if any) + resolved `#3095` floor + standing vs one-shot + PR URL (`leftover=` / `floor=` / `standing=`). One-shot phrases: **pursue residual** | **follow-up hard-stop** | **same as conf-hold** | **continue dual-stopped PR**. Standing phrases: **until floor or loop** | **until greptile meets policy** | **pursue residuals until told otherwise**. Pointer to § Operator follow-up after dual-stop / hard stop. Full template: [`references/core-phase-4.md`](references/core-phase-4.md).\n\n! Composes with minimal-subgraph repair guidance (#2439): keep repairs minimal **and** bounded by dual-stop -- minimal repair is not a license to thrash. Durable delivery/acceptance circuit-breaker: **#3143** `packages/core/src/delivery-attempt/` (`evaluatePreDispatch`, unit ledger). Docs: `docs/delivery-attempt.md`. Skill defaults remain behavioral; mechanical gate lives in core.\n\n### Operator follow-up after dual-stop / hard stop (#3273)\n\nOperator-initiated resume after dual-stop / hard stop / conf-hold — not automatic re-thrash. Depth (A/B/C leftover classes, standing vs one-shot, steps): [`references/core-phase-4.md`](references/core-phase-4.md) same section title. Portable consumer + maintainer (`task` / `deft` dual-invoke). Continue-until target is the **resolved `#3095` floor** (`task policy:show --field=minGreptileConfidence` / `deft policy:show --field=minGreptileConfidence`: typed project policy > framework dogfood **5** > consumer default **4**). ⊗ Hard-code 5/5. ⊗ Lower project policy to clear one PR.\n\n**Leftover classes (A/B/C, #3448):** **class A** named leftover on already-touched files = in-AC residual, auto-continue under standing until floor or same-fingerprint loop. **class B** new subsystem / AC fight = park or follow-up. **class C** score-only = document / same-as-conf-hold. Already-touched leftover is class A unless it needs a new ledger/protocol/story (#2881).\n\n**One-shot vs standing:** one-shot `pursue residual` = one pass then re-stop. Standing (`until floor or loop` / `until greptile meets policy` / `pursue residuals until told otherwise`) applies to **open cohort / ordered-plan units**, not only the last halted PR. Same-fingerprint stop: [`deft-directive-review-cycle/SKILL.md`](../deft-directive-review-cycle/SKILL.md) Dual stop (normative). `#2442` batch cap still applies.\n\nThin pointer: dual-invoke `pr:merge-ready` / `pr:watch`; spawn **one** residual worker or review-cycle owner per batch; document authorized conf floor for this PR only as human-merge/override trail (⊗ silent policy rewrite; `pr:merge-ready` still uses policy floor). ⊗ Unlimited auto-retry. ⊗ Parent self-implement (#2843).\n\n## Runtime Capability Detection (summary)\n\n! Before selecting a launch method, probe the environment. Full probe text: [`references/core-phase-3.md`](references/core-phase-3.md).\n\n1. ! **Probe for `start_agent` tool** — Warp orchestrated.\n2. ! **Probe for Warp environment** — `WARP_*` without `start_agent` → warp-manual.\n3. ! **Probe for the Cursor `Task` tool** — Tier 1; descriptor `cursor-composer` / `cursor-cloud-agent` (#1877). Require Cursor signals (`CURSOR_*` or Cursor-only Task surface) — not bare `Task` alone.\n4. ! **Probe for Claude Code** — Tier 1; descriptor `claude-code` (#3134). Claude-unique signals only: `Agent` (or `CreateAgent` / `SubagentStart`) with background / `run_in_background`, and/or `DEFT_PROBE_CLAUDE_CODE` / `DEFT_AGENT_RUNTIME=claude-code` / `CLAUDECODE`. ⊗ Misclassify as `cursor-composer` via bare `Task`.\n5. ! **Probe for the OpenClaw `sessions_spawn` tool** — Tier 1; descriptor `openclaw` (#2875). Do NOT misclassify as `grok-build` or `generic-terminal`.\n6. ! **Probe for `spawn_subagent` tool** — descriptor `grok-build`.\n7. ! **Select launch path automatically** — load the matching host adapter (route table). No static A/B/C menu.\n8. ! **Return a stable platform descriptor** for Phase 4/6: `warp-orchestrated`, `warp-manual`, `cursor-composer`, `cursor-cloud-agent`, `claude-code`, `openclaw`, `grok-build`, or `generic-terminal`.\n9. ? **Cloud escape hatch** — `oz agent run-cloud` only on explicit user request (host-generic).\n\n⊗ Present static launch options instead of detecting capabilities at runtime.\n⊗ Offer Warp-specific launch paths when not inside Warp.\n⊗ Classify Claude Code as `cursor-composer` / `generic-terminal` when Claude-unique signals are present (#3134).\n\n## Retained addressable sub-agents (#3158)\n\nNamed mode **beside** dispatch-and-collect. Canon: [`../../swarm/swarm.md`](../../swarm/swarm.md) `## Retained addressable sub-agents (#3158)`.\n\n| Mode | When | Mid-scope gate |\n|------|------|----------------|\n| **retained-child** (message-later / steer-mid-flight) | Host keeps a live, addressable child (`agent_id` / session name); parent can re-message or steer mid-flight | Single dispatch MAY pause for approval and continue the **same** child |\n| **dispatch-and-collect** (one-shot) | Host has no continue/resume; worker terminal on tool-loop exit | **Split-dispatch** mandatory (#954): Scope A → report → approve → Scope B |\n\n! After platform detect, read the loaded host adapter's **Retained / continue-by-id** note. Prefer continue-by-agent-id / resume-by-name / steerable mid-flight **only when that adapter documents support**.\n! When the host cannot retain: keep one-shot envelopes and split-dispatch mid-scope gates. Do not claim message-later semantics the platform cannot deliver.\n! Stance (#3164): retention is **orchestration only** — not mid-run constitution self-edit (managed AGENTS, pinned skills, policy).\n! Topology (#3155): retained children MUST obey nuclear-family A2A bounds (parent/sibling/child only).\n⊗ Force a second full dispatch on a retain-capable host solely because a mid-scope gate exists — re-message the live child instead.\n⊗ Invent retain / resume on hosts whose adapter marks one-shot only.\n\n## Phase overview\n\n| Phase | Goal | Depth |\n|-------|------|-------|\n| 0 Allocate | Queue cohort, readiness, approval | `core-phase-0.md` |\n| 1 Select | Confirm candidates, file-overlap | `core-phase-1-2.md` |\n| 2 Setup | Worktrees + prompt files | `core-phase-1-2.md` |\n| 3 Launch | Detect, preflight, **one** host spawn | `core-phase-3.md` + **one** `host-*.md` |\n| 4 Monitor | Heartbeats, takeover, no duplicate agents | `core-phase-4.md` (+ host notes) |\n| 5 Review | Greptile clean, gates, **next-phase tools** | `core-phase-5-6.md` |\n| 6 Close | Merge cascade, cohort sweep, cleanup | `core-phase-5-6.md` |\n\n! Follow phases in order. Depth files hold the operative MUST rules; this page is the dispatch card.\n\n## Effort estimate on dispatch (#1581)\n\n! When plan items carry optional `effort` (S/M/L/XL with time anchors in `vbrief/vbrief.md`), use them for sizing: S/M single-agent, L may need a dedicated agent, XL blocks dispatch until broken into S/M/L. Activate fails closed on XL. Depth: [`references/core-phase-0.md`](references/core-phase-0.md) Steps 2–3.\n! Plan-item effort is **post-planning** (confirms/corrects provisional intake estimates). It is **not** session-start ritual input; ceremony dial (#3214) starts rapid and escalates — do not block cold-start ritual on missing plan-item `effort`. Headless: no operator confirmation for size or stage transitions.\n\n## Critical anti-patterns (dispatch card)\n\n- ⊗ Load all host adapters “just in case” (#2928)\n- ⊗ Parallel OpenClaw `sessions_spawn` on shared repo root without worktrees (#2929)\n- ⊗ Prose-only phase handoff after cohort complete (“I will spawn…”) (#2934)\n- ⊗ Multi-sentence progress-only first response after leaf announce with zero tools / yield (#2943)\n- ⊗ N>2 near-identical assistant sentences with no tool_use / yield (FC14 / #3131 hard-stop)\n- ⊗ Treat thin DONE (no PR URL / merge evidence) as success (#2943)\n- ⊗ Rely on soft skill prose alone as the sole parent-hang mitigation (#3131)\n- ⊗ Second+ user-visible consolidate for the same child runId without new evidence (#3092)\n- ⊗ Assign overlapping files to multiple agents\n- ⊗ Dispatch or activate work that still has `plan.items[].effort: \"XL\"` without breakdown (#1581)\n- ⊗ Merge before Greptile exit condition (score > 3, no P0/P1)\n- ⊗ Skip Phase 0 approval before Phase 1\n- ⊗ Misclassify OpenClaw `sessions_spawn` as `grok-build` or `generic-terminal` (#2875)\n- ⊗ Misclassify Claude Code as `cursor-composer` / `generic-terminal` (#3134)\n- ⊗ Run multi-iteration repair/monitor loops without a failure stop or with silent continuation after the envelope is exhausted (#2442)\n- ⊗ Dual-stop/hard-stop halt without #3273 resume line (leftover class + resolved floor + standing vs one-shot), or unlimited residual auto-retry without new operator consent (#3273 / #3448)\n- ⊗ Hard-code 5/5 as the continue-until target, or park a class A already-touched leftover as a new story (#3448 / #2881 / #3095)\n- ⊗ Force a second full dispatch on a retain-capable host solely for a mid-scope gate, or invent retain on one-shot hosts (#3158)\n- ⊗ Use retained-child messaging for mid-run constitution self-edit (#3158 / #3164)\n- ⊗ Tight forge-outage retry / empty-commit thrash without a one-shot human report (#3422)\n\nFull anti-pattern list: [`references/core-ops.md`](references/core-ops.md).",
       "frontmatter_extra": null
     },
     {
@@ -341,7 +369,7 @@
       ],
       "path": "skills/deft-directive-triage/SKILL.md",
       "version": "0.1",
-      "body": "# Deft Directive Triage\n\nTriage-cache hygiene + \"what's next?\" work selection (ordered plan or ranked queue). Operates against the unified `.deft-cache/github-issue/` mirror (#883 Story 2) and the append-only `xbrief/.eval/candidates.jsonl` audit log (#845 Story 2); writes only via the canonical `task triage:*` verbs.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n## Platform Requirements\n\n! Requires **GitHub** as the SCM platform and the **GitHub CLI (`gh`)** authenticated against the active project's repo -- the cache surface (`task cache:fetch-all`) and the read-side gate (`task verify:cache-fresh`) both depend on it.\n\n## Deterministic Questions Contract\n\n! Every numbered-menu prompt rendered in this skill (Phase 2 candidate selection, Phase 3 per-item decision walk) ! MUST follow [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md): render the canonical numbered menu in chat unless the host UI visibly preserves numeric option labels and returns numeric selections or exact displayed option text. The final two numbered options are `Discuss` and `Back`, in that order, and the Discuss-pause semantic from the contract applies verbatim -- on `Discuss` the agent halts the in-progress sequence and resumes only on an explicit user signal.\n\n## Work selection fork (#2542 / #2402)\n\nDirective does not guess your mix: **ordered plan** (`task plan-sequence:*`) when you know the next units in order, or **ranked queue** (`task triage:queue`) when picking from the backlog. Labels bias the queue; they do not override an active plan.\n\n! Before Phase 2 on bare \"what's next?\", run `task plan-sequence:current`. Active sequence → that entry only; exhausted → fail closed. Explicit \"what's the queue?\" / \"build a cohort\" → Phase 2. See `commands.md` § Backlog Triage → Two paths.\n\n## Phase 0 -- Sync\n\n! Probe cache freshness before doing any classification or selection. Stale cache reads produce stale decisions; the gate is the contract.\n\n1. ! Run `task verify:cache-fresh` (D5 / #1127). Exit 0 -> proceed to Phase 1. Exit 1 (stale or blocked) -> refresh per the printed remediation. Exit 2 (no bootstrap) -> run `task triage:bootstrap` first. When the cache has zero entries, read paths auto-fetch from GitHub first (#2575).\n2. ~ Refresh path: `task cache:fetch-all -- --source=github-issue --repo OWNER/NAME` for an already-bootstrapped project; `task triage:bootstrap` for a first-time seed.\n3. ~ If `xbrief/active/*.xbrief.json` references are in play, run `task triage:refresh-active` to surface drift before the queue is rendered.\n4. ~ When the session one-liner carries `[scope-drift] N` (D14 / #1133), run `task triage:scope-drift` and choose subscribe / ignore before walking the queue.\n5. ⊗ Walk the queue against a stale cache -- the audit log will record decisions against bodies the operator never actually saw.\n\n## Phase 1 -- Classify\n\n! Inspect the auto-classification audit log so manually-decided items are not re-walked, and surface anomalies before the queue render.\n\n1. ! Run `task triage:classify --list` (D10 / #1129) to render effective rules and hold-markers.\n2. ! Walk recent `xbrief/.eval/candidates.jsonl` entries for anomalies (classifier disagreement, repeated defer, stale needs-ac); surface before Phase 2; do NOT auto-fix.\n3. ~ Scope widen/narrow via `task triage:scope --list` (D12 / #1131); edits belong in PROJECT-DEFINITION.\n4. ~ Label hygiene: recommend repo labels via `gh label list` when unlabeled; do not invent labels or block creation solely for missing labels.\n5. ⊗ Re-classify terminally decided items without operator approval -- supersession is `task triage:reset <N>` only.\n\n## Phase 2 -- Present\n\n! Apply the Work selection fork gate (#2542): when no ordered-plan is active, render `task triage:queue` before suggesting work (#1149). Active sequence yields to the ordered-plan entry (#2402).\n\n1. ! Run `task triage:queue --limit=N` (D11 / #1128) -- default `N=10`. Groups `[RESUME]` -> `[URGENT]` -> untriaged -> other; ranking via `plan.policy.triageRankingLabels[]`, tiebreak `updated_at` desc.\n2. ! For per-item detail, run `task triage:show <N>` (default) or `task triage:show --format=operator <N>` (#2890) -- cached payload, latest decision, audit timeline, active-xBRIEF flag; operator format is the pasteable Phase 3 brief backbone. Exit 0 on hit, 1 on cache miss (re-sync per Phase 0).\n3. ~ Present the ranked **queue listing** verbatim; do NOT silently re-rank, drop, or annotate the listing beyond the canonical renderer. This queue non-annotation rule does **not** forbid Phase 3 per-candidate operator briefs or leans (see Phase 3 / #2890).\n4. ⊗ Recommend a specific issue without `task triage:queue` first, or an issue absent from the queue without `task triage:show` to surface why.\n\n## Phase 3 -- Decide\n\n! Walk per-item decisions through the canonical `task triage:*` verbs (tasks own audit-log append / schema / `xbrief/proposed/` write).\n\n! **Operator brief (same turn as menu) (#2890 / #3116):** Before every per-item decision menu, present an operator brief in the **same operator-visible message/surface** as the menu, containing at least: **URL-first** lead (canonical issue URL as the first line for that item, or `#N title` + URL); labels (or explicit none); **current-state validity** (`still-open` | `partial` | `likely-shipped` | `needs-re-scope`) + one-line evidence (linked closed PR, code path, or \"no evidence of fix\"); 2–5 line problem/context summary; AC bullets or explicit \"thin body / no AC\"; agent **lean** + one-line why (Accept / Defer / Reject / Needs-AC / …). ~ Prefer `task triage:show --format=operator <N>` as the brief backbone (URL-first + validity placeholder); agent still owns validity verdict and lean. ⊗ Menu-only or chip-only Phase 3 turns without that brief. ⊗ Brief-only turn followed by a later chip/menu-only turn that does not restate the brief. ⊗ Body-only summary without validity check against current master, closed children, or linked PRs.\n\n! **Host structured-question adapter:** On chips / `ask_user` / similar UIs (e.g. OpenClaw `ask_user`), keep the prose brief in chat; structured options are **actions only** (Accept / Defer / Reject / Needs-AC / Mark duplicate / Discuss / Back). Option labels ≉ substitute for the brief.\n\nFor each candidate, render the canonical numbered action menu and dispatch:\n\n```\nWhat would you like to do with this candidate?\n  1. Accept         -- `task triage:accept -- --issue <N> --repo OWNER/NAME`\n  2. Reject         -- `task triage:reject -- --issue <N> --repo OWNER/NAME`\n  3. Defer          -- `task triage:defer -- --issue <N> --repo OWNER/NAME [--resume-on <event>]`\n  4. Needs-AC       -- `task triage:needs-ac -- --issue <N> --repo OWNER/NAME`\n  5. Mark duplicate -- `task triage:mark-duplicate -- --issue <N> --of <of-issue> --repo OWNER/NAME`\n  6. Discuss\n  7. Back\n```\n\n- ! Map user replies only to the displayed number (`1`-`7`) or exact displayed option text. ⊗ Do NOT infer from alphabetic host affordances or bare letters such as `d` / `b` unless those letters were visibly rendered as choices.\n- ! On `Discuss`, halt immediately, prompt `What would you like to discuss?`, resume only on explicit user signal. ⊗ Implicit resumption.\n- ! On `Back`, un-buffer prior selection and re-render its action menu only before a `task triage:*` dispatch; after dispatch use `task triage:reset`.\n- ~ Bulk: `task triage:bulk-{accept,reject,defer,needs-ac}`; results still flow through the audit log.\n- ⊗ Write to `xbrief/proposed/` directly -- only `task triage:accept` is authorised.\n- ~ **Accept → pending chain (#1136):** `task triage:accept` ingests into **`proposed/`**. To stage into WIP (`pending/`) in one operator action: `task triage:accept -- --issue <N> --repo OWNER/NAME --auto-promote` (WIP cap still enforced; use `--force` on the accept command for WIP override). Separately, promote an already-accepted proposed scope by issue: `task scope:promote -- --from-issue=<N> [--repo OWNER/NAME]` (gates on latest `candidates.jsonl` decision = `accept`; non-accept refuses unless `--force-no-cache`; no decision soft-warns, `--strict` fails). Path-based `task scope:promote -- <file>` remains ungated for refinement scaffolds.\n\n## Phase 4 -- Audit\n\n! Confirm the session's decisions landed coherently before exiting the skill.\n\n1. ! Run `task triage:audit --format=json` (D11 / #1128); optional `#1180` filters `--since` / `--action`. Transform with `jq` -- framework does not compute trends.\n2. ! Run `task triage:summary` (D2 / #1122) -- `[triage] N untriaged · S stale-defer · M in-flight · WIP X/Y [⚠] [· [scope-drift] N]`.\n3. ~ Non-zero `[scope-drift]` → surface `task triage:scope-drift` + subscribe/unsubscribe/ignore remediation; then `task triage:bootstrap -- --resume`.\n4. ~ Stale accept (no active xBRIEF ref) → re-ingest or `task triage:reset`.\n5. ⊗ Skip Phase 4 audit.\n6. ! Umbrella/epic status: REST comments → `## Current shape (as of pass-N)` (#2066 / #1152); never body alone.\n\n## Reversibility\n\n! Undo via `task triage:reset <N>` (Layer 5; history never deleted). ⊗ Edit/delete `xbrief/.eval/candidates.jsonl` to \"undo\".\n\n## Quarterly closed-entry archive vs TTL prune (#1137)\n\nLive walkers (`triage:queue`, scope-drift, bootstrap) scan `.deft-cache/github-issue/`. Closed issues can linger forever. Operators may run an **explicit, reversible** archive pass — never auto on bootstrap/session/check.\n\n| Tool | What it does |\n| --- | --- |\n| `task triage:cache-archive` | Move **closed** + aged (default 30d) entries → `.deft-cache/archived/github-issue/...` with `archive-meta.json`. Skips open lifecycle scopes. `--dry-run` first. |\n| `task triage:archive-list` / `task triage:restore-from-archive` | List / move back to live. |\n| `task cache:prune` | **TTL hard-delete** by `expires_at` — **not** reversible; **not** closed-state archive. |\n\n! Prefer archive for closed clutter; use prune only for expired TTL / cap eviction. ⊗ Wire archive into session-start or `task check`.\n\n## Anti-Patterns\n\n- ⊗ Recommend work without `task triage:queue` (#1149).\n- ⊗ Conclude \"nothing to do\" from folder scans or live GitHub alone (#2576).\n- ⊗ Stale-cache walk; reimplement audit/`proposed/` writes; treat defer/needs-ac as terminal; edit candidates.jsonl; menu-only Phase 3 without operator brief (#2890); body-only brief without URL-first or current-state validity (#3116).\n\n## EXIT\n\n! On opt-out: `deft-directive-triage complete -- exiting skill.` Chain: `deft-directive-refinement` (accepted items) · `deft-directive-swarm` (cohort) · `task cache:fetch-all` then re-enter. ⊗ Silent exit.\n\n## References\n\n- #1119 D6; #1128 D11 (`triage:queue` / `show` / `audit`); #2890 Phase 3 operator brief; #3116 validity + URL-first; #1122 / #1123 / #1127 / #1129 / #1131; #1136 (`scope:promote --from-issue` / `triage:accept --auto-promote`)\n- Siblings: `deft-directive-refinement`, `deft-directive-swarm`, `deft-directive-sync`\n",
+      "body": "# Deft Directive Triage\n\nTriage-cache hygiene + \"what's next?\" work selection (ordered plan or ranked queue). Operates against the unified `.deft-cache/github-issue/` mirror (#883 Story 2) and the append-only `xbrief/.eval/candidates.jsonl` audit log (#845 Story 2); writes only via the canonical `task triage:*` verbs.\n\nLegend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.\n\n## Platform Requirements\n\n! Requires **GitHub** as the SCM platform and the **GitHub CLI (`gh`)** authenticated against the active project's repo -- the cache surface (`task cache:fetch-all`) and the read-side gate (`task verify:cache-fresh`) both depend on it.\n\n## Deterministic Questions Contract\n\n! Every numbered-menu prompt rendered in this skill (Phase 2 candidate selection, Phase 3 per-item decision walk, post-Accept offer) ! MUST follow [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md): render the canonical numbered menu in chat unless the host UI visibly preserves numeric option labels and returns numeric selections or exact displayed option text. The final two numbered options are `Discuss` and `Back`, in that order, and the Discuss-pause semantic from the contract applies verbatim -- on `Discuss` the agent halts the in-progress sequence and resumes only on an explicit user signal.\n\n## Work selection fork (#2542 / #2402)\n\nDirective does not guess your mix: **ordered plan** (`task plan-sequence:*`) when you know the next units in order, or **ranked queue** (`task triage:queue`) when picking from the backlog. Labels bias the queue; they do not override an active plan.\n\n! Before Phase 2 on bare \"what's next?\", run `task plan-sequence:current`. Active sequence → that entry only; exhausted → fail closed. Explicit \"what's the queue?\" / \"build a cohort\" → Phase 2. See `commands.md` § Backlog Triage → Two paths.\n\n## Phase 0 -- Sync\n\n! Probe cache freshness before doing any classification or selection. Stale cache reads produce stale decisions; the gate is the contract.\n\n1. ! Run `task verify:cache-fresh` (D5 / #1127). Exit 0 -> proceed to Phase 1. Exit 1 (stale or blocked) -> refresh per the printed remediation. Exit 2 (no bootstrap) -> run `task triage:bootstrap` first. When the cache has zero entries, read paths auto-fetch from GitHub first (#2575).\n2. ~ Refresh path: `task cache:fetch-all -- --source=github-issue --repo OWNER/NAME` for an already-bootstrapped project; `task triage:bootstrap` for a first-time seed.\n3. ~ If `xbrief/active/*.xbrief.json` references are in play, run `task triage:refresh-active` to surface drift before the queue is rendered.\n4. ~ When the session one-liner carries `[scope-drift] N` (D14 / #1133), run `task triage:scope-drift` and choose subscribe / ignore before walking the queue.\n5. ⊗ Walk the queue against a stale cache -- the audit log will record decisions against bodies the operator never actually saw.\n\n## Phase 1 -- Classify\n\n! Inspect the auto-classification audit log so manually-decided items are not re-walked, and surface anomalies before the queue render.\n\n1. ! Run `task triage:classify --list` (D10 / #1129) to render effective rules and hold-markers.\n2. ! Walk recent `xbrief/.eval/candidates.jsonl` entries for anomalies (classifier disagreement, repeated defer, stale needs-ac); surface before Phase 2; do NOT auto-fix.\n3. ~ Scope widen/narrow via `task triage:scope --list` (D12 / #1131); edits belong in PROJECT-DEFINITION.\n4. ~ Label hygiene: recommend repo labels via `gh label list` when unlabeled; do not invent labels or block creation solely for missing labels.\n5. ⊗ Re-classify terminally decided items without operator approval -- supersession is `task triage:reset <N>` only.\n\n## Phase 2 -- Present\n\n! Apply the Work selection fork gate (#2542): when no ordered-plan is active, render `task triage:queue` before suggesting work (#1149). Active sequence yields to the ordered-plan entry (#2402).\n\n1. ! Run `task triage:queue --limit=N` (D11 / #1128) -- default `N=10`. Groups `[RESUME]` -> `[URGENT]` -> untriaged -> other; ranking via `plan.policy.triageRankingLabels[]`, tiebreak `updated_at` desc.\n2. ! For per-item detail, run `task triage:show <N>` (default) or `task triage:show --format=operator <N>` (#2890) -- cached payload, latest decision, audit timeline, active-xBRIEF flag; operator format is the pasteable Phase 3 brief backbone. Exit 0 on hit, 1 on cache miss (re-sync per Phase 0).\n3. ~ Present the ranked **queue listing** verbatim; do NOT silently re-rank, drop, or annotate the listing beyond the canonical renderer. This queue non-annotation rule does **not** forbid Phase 3 per-candidate operator briefs or leans (see Phase 3 / #2890).\n4. ⊗ Recommend a specific issue without `task triage:queue` first, or an issue absent from the queue without `task triage:show` to surface why.\n\n## Phase 3 -- Decide\n\n! Walk per-item decisions through the canonical `task triage:*` verbs (tasks own audit-log append / schema / `xbrief/proposed/` write).\n\n! **Operator brief (same turn as menu) (#2890 / #3116):** Before every per-item decision menu, present an operator brief in the **same operator-visible message/surface** as the menu, containing at least: **URL-first** lead (canonical issue URL as the first line for that item, or `#N title` + URL); labels (or explicit none); **current-state validity** (`still-open` | `partial` | `likely-shipped` | `needs-re-scope`) + one-line evidence (linked closed PR, code path, or \"no evidence of fix\"); 2–5 line problem/context summary; AC bullets or explicit \"thin body / no AC\"; agent **lean** + one-line why (Accept / Defer / Reject / Needs-AC / …). ~ Prefer `task triage:show --format=operator <N>` as the brief backbone (URL-first + validity placeholder); agent still owns validity verdict and lean. ⊗ Menu-only or chip-only Phase 3 turns without that brief. ⊗ Brief-only turn followed by a later chip/menu-only turn that does not restate the brief. ⊗ Body-only summary without validity check against current master, closed children, or linked PRs.\n\n! **Host structured-question adapter:** On chips / `ask_user` / similar UIs (e.g. OpenClaw `ask_user`), keep the prose brief in chat; structured options are **actions only** (Accept / Defer / Reject / Needs-AC / Mark duplicate / Discuss / Back). Option labels ≉ substitute for the brief.\n\nFor each candidate, render the canonical numbered action menu and dispatch:\n\n```\nWhat would you like to do with this candidate?\n  1. Accept         -- `task triage:accept -- --issue <N> --repo OWNER/NAME`\n  2. Reject         -- `task triage:reject -- --issue <N> --repo OWNER/NAME`\n  3. Defer          -- `task triage:defer -- --issue <N> --repo OWNER/NAME [--resume-on <event>]`\n  4. Needs-AC       -- `task triage:needs-ac -- --issue <N> --repo OWNER/NAME`\n  5. Mark duplicate -- `task triage:mark-duplicate -- --issue <N> --of <of-issue> --repo OWNER/NAME`\n  6. Discuss\n  7. Back\n```\n\n- ! Map user replies only to the displayed number (`1`-`7`) or exact displayed option text. ⊗ Do NOT infer from alphabetic host affordances or bare letters such as `d` / `b` unless those letters were visibly rendered as choices.\n- ! On `Discuss`, halt immediately, prompt `What would you like to discuss?`, resume only on explicit user signal. ⊗ Implicit resumption.\n- ! On `Back`, un-buffer prior selection and re-render its action menu only before a `task triage:*` dispatch; after dispatch use `task triage:reset`.\n- ~ Bulk: `task triage:bulk-{accept,reject,defer,needs-ac}`; results still flow through the audit log.\n- ⊗ Write to `xbrief/proposed/` directly -- only `task triage:accept` is authorised.\n- ~ **Accept → pending chain (#1136):** `task triage:accept` ingests into **`proposed/`**. To stage into WIP (`pending/`) in one operator action: `task triage:accept -- --issue <N> --repo OWNER/NAME --auto-promote` (WIP cap still enforced; use `--force` on the accept command for WIP override). Separately, promote an already-accepted proposed scope by issue: `task scope:promote -- --from-issue=<N> [--repo OWNER/NAME]` (gates on latest `candidates.jsonl` decision = `accept`; non-accept refuses unless `--force-no-cache`; no decision soft-warns, `--strict` fails). Path-based `task scope:promote -- <file>` remains ungated for refinement scaffolds.\n- ? **After Accept (#3708):** offer `deft-directive-design-critique`. Optional; same after `--auto-promote` (promote already happened). Decline writes nothing. Menu: 1. Run critique (existing ADR-005 path) 2. Skip 3. Discuss 4. Back. Back = Skip (do not re-open Accept; undo is `task triage:reset`).\n\n## Phase 4 -- Audit\n\n! Confirm the session's decisions landed coherently before exiting the skill.\n\n1. ! Run `task triage:audit --format=json` (D11 / #1128); optional `#1180` filters `--since` / `--action`. Transform with `jq` -- framework does not compute trends.\n2. ! Run `task triage:summary` (D2 / #1122) -- `[triage] N untriaged · S stale-defer · M in-flight · WIP X/Y [⚠] [· [scope-drift] N]`.\n3. ~ Non-zero `[scope-drift]` → surface `task triage:scope-drift` + subscribe/unsubscribe/ignore remediation; then `task triage:bootstrap -- --resume`.\n4. ~ Stale accept (no active xBRIEF ref) → re-ingest or `task triage:reset`.\n5. ⊗ Skip Phase 4 audit.\n6. ! Umbrella/epic status: REST comments → `## Current shape (as of pass-N)` (#2066 / #1152); never body alone.\n\n## Reversibility\n\n! Undo via `task triage:reset <N>` (Layer 5; history never deleted). ⊗ Edit/delete `xbrief/.eval/candidates.jsonl` to \"undo\".\n\n## Quarterly closed-entry archive vs TTL prune (#1137)\n\nLive walkers (`triage:queue`, scope-drift, bootstrap) scan `.deft-cache/github-issue/`. Closed issues can linger forever. Operators may run an **explicit, reversible** archive pass — never auto on bootstrap/session/check.\n\n| Tool | What it does |\n| --- | --- |\n| `task triage:cache-archive` | Move **closed** + aged (default 30d) entries → `.deft-cache/archived/github-issue/...` with `archive-meta.json`. Skips open lifecycle scopes. `--dry-run` first. |\n| `task triage:archive-list` / `task triage:restore-from-archive` | List / move back to live. |\n| `task cache:prune` | **TTL hard-delete** by `expires_at` — **not** reversible; **not** closed-state archive. |\n\n! Prefer archive for closed clutter; use prune only for expired TTL / cap eviction. ⊗ Wire archive into session-start or `task check`.\n\n## Anti-Patterns\n\n- ⊗ Recommend work without `task triage:queue` (#1149).\n- ⊗ Conclude \"nothing to do\" from folder scans or live GitHub alone (#2576).\n- ⊗ Stale-cache walk; reimplement audit/`proposed/` writes; treat defer/needs-ac as terminal; edit candidates.jsonl; menu-only Phase 3 without operator brief (#2890); body-only brief without URL-first or current-state validity (#3116).\n\n## EXIT\n\n! On opt-out: `deft-directive-triage complete -- exiting skill.` Chain: `deft-directive-refinement` (accepted items) · `deft-directive-swarm` (cohort) · `task cache:fetch-all` then re-enter. ⊗ Silent exit.\n\n## References\n\n- #1119 D6; #1128 D11 (`triage:queue` / `show` / `audit`); #2890 Phase 3 operator brief; #3116 validity + URL-first; #1122 / #1123 / #1127 / #1129 / #1131; #1136 (`scope:promote --from-issue` / `triage:accept --auto-promote`); #3708 (post-Accept design-critique offer)\n- Siblings: `deft-directive-refinement`, `deft-directive-swarm`, `deft-directive-sync`\n",
       "frontmatter_extra": "triggers:\n  - triage\n  - triage hygiene\n  - work the cache\n  - what's next\n  - whats next\n  - what should I work on\n  - queue\n  - build a cohort\n  - build cohort"
     },
     {