@sabaiway/agent-workflow-kit 1.45.1 → 1.47.0

package/CHANGELOG.md

@@ -4,6 +4,88 @@ Semantically versioned ([semver](https://semver.org)), newest first. The `versio
 is the current release. `upgrade` mode reads a project's `docs/ai/.workflow-version` and applies
 every `migrations/<version>-<slug>.md` newer than it, in semver order.
 
+## 1.47.0 — REPORT-FACTS train: live-fact report contract · batched ledger writer · version-sync wrapper lane · sandbox-lanes canon & bridge contract twins (AD-054)
+
+A **feature** release (ships with engine 1.17.0, memory 2.3.0, bridges 2.7.0/2.6.0 bundled) that
+bundles three top-of-queue items plus this session's own live prompt-defects into one train, all
+fixed kit-level:
+
+- **Report-facts contract (D1/D2).** A binding clause at the point of use: any claim a report makes
+  about the CURRENT host or session state — prompts fired, sandbox scope, whether a bypass was
+  needed, network reachability, approval counts — must trace to **live tool output** run **this
+  session**; with no live signal the claim is **omitted or explicitly marked unverified**; a
+  memory/handover snapshot is **context, never report facts**. The full clause lives in
+  `references/shared/report-footer.md` (single home); upgrade steps 4/8 and the recommendations
+  advisor carry one binding line each, pinned by the new `report-facts-contract.test.mjs`.
+- **Batched ledger writer (D3).** `review-ledger-write.mjs` gains a `batch` verb — one invocation
+  applies an ordered record/classify/override list through the SAME single-verb code paths (no forked
+  validator). Two passes: the whole envelope is validated structurally first with ZERO writes, then
+  ops apply sequentially and fail-fast on the first typed STOP with an honest partial-success report
+  (prior ops stay recorded, append-only). One writer call for a records stage instead of ~13.
+- **version-sync wrapper lane (D4).** `version-sync --bump` for a bridge now also rewrites the
+  line-anchored `AW_BRIDGE_VERSION` in `bin/*.sh` (closed one-anchor rule — every assignment counted,
+  so a shadowing malformed line is caught; a non-canonical anchor or a downgrade is refused with zero
+  writes), and the no-flag verify checks it across all four constants (each wrapper + its kit mirror).
+  The bridge version constant is now first-class — dogfooded on this very release.
+- **Bridge contract twins + codex-exec detection (D7).** Both bridge manifests gain a typed `notes[]`
+  (codex execute = the nested-sandbox limit; agy review = the pre-dispatch host-diff), rendered in the
+  `procedures` advisor and each wrapper `--help`, bidirectionally drift-guarded. `codex-exec.sh` now
+  detects the nested-sandbox failure class (a sandbox-mechanism token AND a permission/read-only
+  failure token together) and emits a stated recovery hint — route codex-exec OUTSIDE the harness
+  sandbox ON the observed failure, never a preemptive blanket. The velocity bridge-tier stays
+  REVIEW-wrappers-only; delegated execution keeps its human prompt.
+- **Canon twins (D5/D6).** The prompt-economy canon gains a writer-batch clause and two sandbox-lane
+  sentences (pre-dispatch host-diff + nested-sandbox honesty), rendered across `orchestration.md` §5,
+  the agent-rules lens (re-rendered into both templates), and the kit cost-lanes advisor.
+
+## 1.46.0 — Recommendations UX rework: verdict-first, shape-capped, user-language; sandbox-lane discoverability (REC-UX-REWORK, AD-053)
+
+A **feature** release (ships with engine 1.16.0, memory 2.2.0, bridges 2.6.0/2.5.0 bundled)
+reworking the upgrade Recommendations section after its first consumer-side report drew a
+readability verdict — the section now LEADS with an answer instead of a wall of caveats:
+
+- **Verdict-first render (D1).** Items carry a frozen two-class severity (`attention` — a
+  configured declaration broken/drifted/degrading/invalid; `optional` — an offer to enable an
+  unconfigured capability). The optimal state stays the byte-identical empty-state line; every
+  other state opens with ONE composed verdict line from frozen, doc-parity-bound templates
+  (`{K} item(s) need attention` / `nothing is broken` ONLY when nothing needs attention AND no
+  probe was skipped / `{N} optional recommendation(s), apply any you want` / `optimality NOT
+  attested — {M} probe check(s) skipped`). Items render attention-first with severity tags.
+- **Shape is contract (D2).** Every benefit string and static WHAT template lives in frozen
+  exported registries (`BENEFITS` + the new `WHATS`, per-site variants included) pinned by a
+  static gate: one line, 140-char cap, banned tokens (RISK/CAVEAT/IF-hedges/dates); dynamic parts
+  cap by truncation-with-count; `add()` backstops composed items into the stated-skip lane; skip
+  reasons normalize to one capped line. The first RED run enumerated 9 violators — all rewritten.
+- **Risk moved to the consent moment (D3).** Posture/risk prose lives in the mode doc's per-item
+  notes (closed, bidirectionally test-pinned via `RISK_NOTED_KEYS`); the apply lane is an explicit
+  informed-consent checkpoint: select → posture note inline → explicit confirm → run EXACTLY the
+  rendered one-liner.
+- **`network-allowlist` → `sandbox-lane` (D4, merges REC-SANDBOX-LANE).** The unknowable-condition
+  hedge is gone: the item surfaces the manifest-declared observed session-sandbox recipe
+  (`networkHosts` ∪ resolved `writableDirs`) for wired review wrappers and converges on a NEUTRAL
+  fingerprint acknowledgement (`agentWorkflow.sandboxLaneAck`, either settings scope; home-symbolic
+  normalization keeps a committed ack machine-portable; a changed recipe re-fires). Security keys
+  are never read as an ack and never recommended as a fix; the mode doc's sandbox-lanes section
+  routes per host class by a narrowest-scope ladder.
+- **User-language presentation (D5).** The paste-verbatim contract is retired: the agent PRESENTS
+  the section in the user's conversational language — every fact and count, nothing added or
+  dropped; commands/paths/hosts byte-exact; raw tool block on request (the AD-032 lane). A static
+  language-contract test pins the new tokens present and the retired phrases absent on every live
+  surface (both mode docs, README row, tool header, doc-parity comments).
+- **Manifests: `writableDirs` (D6).** New optional validated field — `{env, default}` entries
+  (validate `--strict`, fixtures ×4, kit mirrors re-synced); the advisor resolves at run time
+  mirroring the wrapper byte-semantics (non-empty env wins; empty ≡ unset; only `~`, `~/…`,
+  absolute forms ride as-given — anything else anchors to the project root).
+- **Prompt-economy render (D7).** The cost-lanes advisory (`procedures.mjs`) gains the
+  prompt-economy clause rendered from the engine canon (read-only fan-out on restricted-tool
+  vehicles only; one plain pipeline per call; capability-gated launcher guidance; the
+  quality/speed guard + honest limit), drift-guarded by one distinctive token per invariant on all
+  three surfaces.
+
+Bundled bridges: **codex-cli-bridge 2.6.0**, **antigravity-cli-bridge 2.5.0** — each manifest
+gains its `writableDirs` declaration (codex `{CODEX_HOME, ~/.codex}`; agy
+`{null, ~/.gemini/antigravity-cli}`); wrapper behavior unchanged.
+
 ## 1.45.1 — codex frontier pin moves to gpt-5.6-sol (bridge 2.5.0)
 
 A **patch** release (the kit surface is unchanged; the bundled `codex-cli-bridge` moves 2.4.0 →

package/README.md

@@ -238,9 +238,9 @@ file), or run the guarded `/agent-workflow-kit uninstall`.
 | `/agent-workflow-kit review-state` | any time | **read-only review-receipt checker** — makes "reviewed ≠ shipped" detectable: the bridge review wrappers append a receipt per successful review (into a file inside the git dir — never committable); this checks that every backend your configured `plan-execution.review` recipe names holds a **fresh, grounded receipt for the current uncommitted tree** (any later edit moves the fingerprint and stales the receipt; a review continuation never re-attests a folded tree). `--check` gives a gate exit code to declare in `docs/ai/gates.json` **by hand or via the consent-gated seeder** (preview → your explicit yes; never without consent). `--await [--timeout <s>]` (AD-049) BLOCKS until every recipe-named backend has receipted the current tree — the durable completion signal is the receipt, never a process event — so you wait for the bridges instead of hand-polling. Never writes, never commits, never runs a subscription CLI; it spawns read-only `git` queries to fingerprint the tree — and `git commit --no-verify` stays possible (discipline, not a sandbox). |
 | `/agent-workflow-kit sandbox-masks` | any time | **cosmetic exclude lane for sandbox device masks** — an OS sandbox (Claude Code) injects character-device masks into the work tree as untracked `git status` noise; the review domain already ignores them **by construction** (never-committable untracked classes — char/block devices, FIFOs, sockets — are excluded from the fingerprint, the assembled review payload, and the clean checks). This mode hides them from `git status` too: flagless = read-only probe (derives the CURRENT mask set from the unfiltered walk + lstat — never a frozen list — and revalidates fenced entries, loudly flagging one that became a real path); `--apply` = consent-gated FULL-BLOCK replace of its own fenced block in `git rev-parse --git-path info/exclude` (stale masks drop by construction; `--clear` always means REMOVE the block — it takes precedence over the derivation). Writes ONLY its fence — never `.gitignore`, never global config; symlinked/non-regular exclude paths and malformed fences fail closed. Watch note: a real file at an excluded path is silently skipped by bulk staging (`git add -A`/`git add .`) — delete the stale line first; the probe flags exactly this case. |
 | `/agent-workflow-kit grounding` | any time | **grounded-review facts assembler** — mechanizes populating `agy-review --facts @f`: slices your entry-point's **Hard Constraints** section verbatim (exactly one match, else a loud stop) and/or a plan's decision-bearing sections (`## Approach` + `## Verification` required, `## Decisions (locked)` when present; duplicates stop), under the same byte budget the agy wrapper enforces (minus `--reserve-bytes` for the artifact share), with a loud tail-trim on overflow. `--autonomy` (AD-044) appends the COMPUTED effective autonomy policy from the git-top `docs/ai/autonomy.json` (every red-line + per-activity level, stated source line; absent file → the computed defaults ARE the policy, exit 0; a malformed policy fails CLOSED, exit 1). `--ledger-summary` (AD-049) appends a COMPUTED review-ledger digest for the single in-flight segment (rounds · origins · classifications · verdicts · overrides — unrelated loops excluded), so the reviewer sees the loop's own history without hand-copying. Prints to stdout; `--out` writes **one scratch file only** — system-temp outside the repo ($TMPDIR / /tmp, rewritable) or a **fresh** gitignored in-repo path (create-only, exclusive write; an existing in-repo file, even gitignored, is refused — the `.env` clobber class); tracked, not-ignored-in-repo, other outside-repo, and symlink/non-regular destinations are all refused. Never commits, never runs a subscription CLI. |
-| `/agent-workflow-kit review-ledger` | any time | **review-round ledger** — turns the review-loop stop rule into a **computed** signal: record each plan-execution review round, its triage, and any recorded **overrides** (`oracle-change` lifts named tampered test files; `red-proof` waives the observed-red proof for exactly one `testId`; v4 adds **`size-cap`** — the exact sanctioned magnitude for a surface over the diff cap, segment-scoped — all loud, durable, auditable waivers, never silent) into a JSONL ledger inside the git dir (never committable), and read the stop decision (`converged > resolved-residual > triage-required > continue`) from the records — never from a remembered rule. **Since v4 every record carries `base` = the HEAD commit and the whole loop is SEGMENT-scoped (AD-048):** round numbering, the caps, and every tooth reset ONLY at a gated commit — a multiphase plan records fully while round 4 within one segment stays refused; `gate-run` records (minted by `gates --record`) make gates-before-review a computed precondition; the triage class **`refuted`** is the honest phantom-finding lane (grounds mandatory); `--telemetry` renders counts-only gate-efficacy data across all loops and both ledgers. `--status` replaces the hand-composed per-round tally; `record --from-receipts` (AD-049) DRAFTS the `backends[]` from the current-fingerprint receipts (verdict per backend, counts from the supplied findings) instead of hand-composing them — a recipe-named backend with no receipt is a loud stop; `--check` is a fail-closed gate exit code for `docs/ai/gates.json` (by hand or via the consent-gated seeder). A `fixable-bug` triage **requires its red→green `testId`** (v1..v3 records stay valid on read — old records never enter a segment). The writer refuses a round (past the hard-max, while a triage is pending, or lacking a grounded review receipt) and refuses an override outside its single in-flight loop. Honest residual: records are forgeable — self-discipline, not a security boundary. Never commits, never runs a subscription CLI. |
+| `/agent-workflow-kit review-ledger` | any time | **review-round ledger** — turns the review-loop stop rule into a **computed** signal: record each plan-execution review round, its triage, and any recorded **overrides** (`oracle-change` lifts named tampered test files; `red-proof` waives the observed-red proof for exactly one `testId`; v4 adds **`size-cap`** — the exact sanctioned magnitude for a surface over the diff cap, segment-scoped — all loud, durable, auditable waivers, never silent) into a JSONL ledger inside the git dir (never committable), and read the stop decision (`converged > resolved-residual > triage-required > continue`) from the records — never from a remembered rule. **Since v4 every record carries `base` = the HEAD commit and the whole loop is SEGMENT-scoped (AD-048):** round numbering, the caps, and every tooth reset ONLY at a gated commit — a multiphase plan records fully while round 4 within one segment stays refused; `gate-run` records (minted by `gates --record`) make gates-before-review a computed precondition; the triage class **`refuted`** is the honest phantom-finding lane (grounds mandatory); `--telemetry` renders counts-only gate-efficacy data across all loops and both ledgers. `--status` replaces the hand-composed per-round tally; `record --from-receipts` (AD-049) DRAFTS the `backends[]` from the current-fingerprint receipts (verdict per backend, counts from the supplied findings) instead of hand-composing them — a recipe-named backend with no receipt is a loud stop; a **`batch`** verb applies an ordered list of record/classify/override ops in ONE writer call (the prompt-economy lane — the whole envelope is validated structurally first with zero writes, then ops apply sequentially and fail-fast; prior ops stay recorded, append-only); `--check` is a fail-closed gate exit code for `docs/ai/gates.json` (by hand or via the consent-gated seeder). A `fixable-bug` triage **requires its red→green `testId`** (v1..v3 records stay valid on read — old records never enter a segment). The writer refuses a round (past the hard-max, while a triage is pending, or lacking a grounded review receipt) and refuses an override outside its single in-flight loop. Honest residual: records are forgeable — self-discipline, not a security boundary. Never commits, never runs a subscription CLI. |
 | `/agent-workflow-kit fold-completeness` | any time | **fold-completeness gate** — attests the review loop's folded fixes were proven the HONEST way (no fix theater): the runner executes your suite ONCE under `NODE_V8_COVERAGE`, checks every changed executable line is **executed**, probes every bound `testId` N times (`AW_FOLD_RERUNS`), records content hashes, and scans the test surface for tamper; the `--red` verb observes a test FAILING on the pre-fold tree — **BEFORE the fix** — and mints an **observed-red receipt**. The read-only checker (`--status` / `--check`) then requires, per bound test: the receipt, receipt-precedes-run order, N/N-green probes, and content **custody** (the green test is byte-identical to the one seen failing) — the receipt+custody half waivable for exactly one `testId` by a recorded `red-proof` override; mixed/timed-out probes are QUARANTINE (never converted, no override); **v3 records carry `base` and the proof is segment-scoped (AD-048)** — a committed phase's custody obligations close with its commit, and a receipt never crosses a commit boundary; tampered pre-existing test files fail closed unless covered by a recorded `oracle-change` override. Honest residuals: coverage proves **execution, not assertion**, and records are forgeable — self-discipline, not a security boundary. v1 scope is JS/V8 (pluggable via `AW_FOLD_BOUND_CMD`): changed TS/JSX fails closed, docs/config changes are listed but never block, and **no mutation testing ships**. Wire the gate by hand — the consent-gated seeder deliberately does not offer it yet (JS-only hold). Never commits, never runs a subscription CLI. |
-| `/agent-workflow-kit recommendations` | any time (every `upgrade` ends with it) | **read-only deployment advisor** (AD-044) — computes what in THIS deployment is configured sub-optimally (allowlist not seeded, autonomy render drifted, OS sandbox unavailable, gates undeclared, bridge friction, sandbox-mask clutter) and renders each item as **{what · one-line benefit · the exact consent-gated apply one-liner}**; the agent pastes the section **verbatim** and runs EXACTLY the rendered one-liners only on your yes. Renders **present-even-when-empty** (`no recommendations — flow optimal.`); a failed probe degrades to a stated skip line. Benefit lines are fact-true frozen data (the bridge-wrappers item claims velocity only; risk-bearing items state their risk inline); the network-allowlist item is **HAND-APPLY** — the kit never seeds `sandbox.network.allowedDomains` / `filesystem.allowWrite` (the hosts are documented per bridge in `capability.json` `networkHosts`). `--cwd` is required (the target project is explicit); never writes, never commits, never runs a subscription CLI. |
+| `/agent-workflow-kit recommendations` | any time (every `upgrade` ends with it) | **read-only deployment advisor** (AD-044) — computes what in THIS deployment is configured sub-optimally (allowlist not seeded, autonomy render drifted, OS sandbox unavailable, gates undeclared, bridge friction, sandbox-mask clutter, an unacknowledged sandbox recipe) and renders **verdict-first**: one composed verdict line (does anything need attention?), then each item as **{severity · what · one-line benefit · the exact consent-gated apply one-liner}**. The agent PRESENTS the section in the user's conversational language — every fact and count, nothing added or dropped; commands, paths, hosts and rule strings byte-exact; raw tool block on request — and runs EXACTLY the rendered one-liners only on your yes, surfacing each item's posture note first. Renders **present-even-when-empty** (`no recommendations — flow optimal.`); a failed probe degrades to a stated skip line. Registry strings are fact-true frozen one-line data (posture/risk notes live in the mode doc at the consent moment); the sandbox-lane item is **HAND-APPLY** — the kit never seeds `sandbox.network.allowedDomains` / `filesystem.allowWrite` (the recipe is documented per bridge in `capability.json` `networkHosts` + `writableDirs`; convergence is a neutral fingerprint acknowledgement, never a security key). `--cwd` is required (the target project is explicit); never writes, never commits, never runs a subscription CLI. |
 | `/agent-workflow-kit doc-parity` | any time | **read-only doc-parity lint** (AD-049) — kills the doc-drift class where a mode-contract doc silently lags a code constant (a `--check` doc still reading `300` after the diff cap moved to `400`): a **closed, exported registry** binds each live constant (review caps, schema versions, the ledger's own class/scope vocabulary, and the autonomy-doctor EXIT/status/trusted-dir contract) to the exact token its `references/modes/*.md` contract must carry, and asserts the CURRENT value renders into every bound file — a drifted doc, an unreadable file, or an absent token **fails closed**. The values are sourced from the live imports (never re-typed), so the lint can't itself go stale; adding a binding is adding a checked entry (closed-world, edit-safe). `--check` is a gate exit code for `docs/ai/gates.json`. Never writes, never commits, never runs a subscription CLI. |
 | `/agent-workflow-kit uninstall` | opt-in, any time | **guarded teardown** — the inverse of `init` / `setup`. Removes only what's **provably ours** (managed skill dirs + bridge wrappers; in a project, the hidden-mode git-ignore block it added + the pre-commit hook it installed); **never deletes** your `docs/ai` / `AGENTS.md` (prints the exact `rm` to run by hand) or your `.claude/settings.json` (prints an **edit** — remove the attribution key, review any velocity `permissions.*` — never an `rm`). Always `--dry-run` first; preflight-then-mutate; never commits. |
 | `/agent-workflow-kit velocity` | Claude Code · opt-in | **onboarding velocity profile** — seeds a fixed, audited **read-only** allowlist into `.claude/settings.json` so routine read-only commands stop idling on approval prompts while you're away; opt-in `acceptEdits`; plus a **read-only advisory** of likely project gate commands to add by hand. Writes **only** `.claude/settings.json` — **never** allowlists commit/push/publish, never writes `settings.local.json`, never commits. A seeded entry is a **trust posture, not a sandbox** (a runtime residual remains at the settings level — its guard ships as the opt-in `hook` command); a direct commit/push/publish still asks. `--dry-run` first. |

package/SKILL.md

@@ -3,7 +3,7 @@ name: agent-workflow-kit
 description: Deploy or upgrade a portable AI-agent memory-and-workflow system in any project. Use when the user wants to bootstrap `docs/ai/` + an entry-point `AGENTS.md` (+ `CLAUDE.md` alias) + cap/archive/index enforcement in a new or existing repo, set up the Memory Map and session protocols, install the docs-rotation pre-commit hook, or run `/agent-workflow-kit` / `/agent-workflow-kit upgrade`. Triggers on phrases like "set up the memory system", "deploy the AI workflow here", "bootstrap docs/ai", "upgrade the workflow".
 disable-model-invocation: true
 metadata:
-  version: '1.45.1'
+  version: '1.47.0'
 ---
 
 # agent-workflow-kit

package/bridges/antigravity-cli-bridge/SKILL.md

@@ -2,7 +2,7 @@
 name: antigravity-cli-bridge
 description: Delegate work to Google's Antigravity CLI (`agy`) — the successor to Gemini CLI — to reach Gemini, Claude, and GPT-OSS models under a Google AI Pro/Ultra subscription from the terminal. Use when the user wants to run a headless `agy` prompt, hand a focused task or second-opinion review to `agy`, install or authenticate Antigravity CLI, check or economise its quota/models, bridge project context into `agy`, set up a second delegated-execution backend beside Codex, or troubleshoot `agy` flags, models, auth, conversations, or its no-JSON headless behaviour.
 metadata:
-  version: '2.4.0'
+  version: '2.6.0'
 ---
 
 # antigravity-cli-bridge

package/bridges/antigravity-cli-bridge/bin/agy-review.sh

@@ -69,6 +69,11 @@ Grounding:
   --facts @f = the verified facts to review AGAINST; --decided @f = decisions
   already made, do NOT re-raise (anti-circling)
 
+Notes:
+  pre-dispatch host-diff: before the FIRST dispatch of this bridge, diff its declared networkHosts
+  against the live sandbox allow-list — a missing host is surfaced to the maintainer BEFORE
+  dispatching, never fired into a known prompt
+
 Round-2 / resume:
   agy-review --continue [--decided @f] [--focus "…"]
   agy-review --conversation <id> [--decided @f] [--focus "…"]
@@ -194,7 +199,7 @@ DEFAULT_AGY_REVIEW_MODEL="Gemini 3.1 Pro (High)"
 # Review-receipt identity (AD-038). AW_BRIDGE_VERSION mirrors this bridge's SKILL.md/capability.json
 # version (drift-guarded by agy-review.test.mjs against capability.json).
 AW_RECEIPT_BACKEND="agy"
-AW_BRIDGE_VERSION="2.4.0"
+AW_BRIDGE_VERSION="2.6.0"
 # `-` not `:-` so an EXPLICIT empty AGY_MODEL= survives (drop --model, use settings.json — agy.sh:52).
 AGY_MODEL="${AGY_MODEL-$DEFAULT_AGY_REVIEW_MODEL}"
 # Frontier review models. ANY model is allowed; a sub-frontier one only earns a soft, silenceable warning.

package/bridges/antigravity-cli-bridge/bin/agy-review.test.mjs

@@ -550,6 +550,12 @@ describe('agy-review.sh — --help contract (manifest-pinned)', () => {
     assert.equal(norm(helpSection(help, 'Grounding:').join(' ')), norm(REVIEW_CONTRACT.grounding));
   });
 
+  it('Notes renders the manifest contract.notes verbatim (a typed contract key that MUST surface)', () => {
+    const help = runHelp('--help').stdout;
+    assert.ok(REVIEW_CONTRACT.notes.length > 0, 'manifest notes must be non-empty');
+    assert.equal(norm(helpSection(help, 'Notes:').join(' ')), norm(REVIEW_CONTRACT.notes.join(' ')));
+  });
+
   it('Round-2 / resume set-EQUALS the manifest continue descriptors', () => {
     const help = runHelp('--help').stdout;
     const got = helpSection(help, 'Round-2 / resume:').filter((l) => l.startsWith('agy-review')).map(norm);

package/bridges/antigravity-cli-bridge/capability.json

@@ -3,7 +3,7 @@
   "schema": 1,
   "name": "antigravity-cli-bridge",
   "kind": "execution-backend",
-  "version": "2.4.0",
+  "version": "2.6.0",
   "provides": ["review", "probe"],
   "roles": {
     "review": {
@@ -28,7 +28,10 @@
           "agy-review --continue [--decided @f] [--focus \"…\"]",
           "agy-review --conversation <id> [--decided @f] [--focus \"…\"]"
         ],
-        "receipt": "side effect — a successful review appends one JSON receipt line to <git dir>/agent-workflow-review-receipts.jsonl (AW_REVIEW_RECEIPTS overrides; plan/diff outside a git tree: warn + skip unless overridden): fingerprint = sha256 over the canonical uncommitted-state payload (staged diff + unstaged diff + untracked-not-ignored contents — the review-payload domain; never-committable untracked paths — character/block devices, FIFOs, sockets — are excluded from the domain entirely, untracked symlinks/directories ride as name-only notes) in code mode, the artifact-file sha256 in plan/diff mode; verdict recorded verbatim from the mandated '### Verdict' section (SHIP / SHIP WITH NITS / REWORK); grounded = whether a NON-EMPTY --facts payload was supplied (an empty payload records grounded:false — fail-closed, the state gate rejects it), factsHash = sha256 of the facts payload; a continuation receipt is fresh:false (informational-only — it cannot attest the folded tree); a write failure warns, never fails the review"
+        "receipt": "side effect — a successful review appends one JSON receipt line to <git dir>/agent-workflow-review-receipts.jsonl (AW_REVIEW_RECEIPTS overrides; plan/diff outside a git tree: warn + skip unless overridden): fingerprint = sha256 over the canonical uncommitted-state payload (staged diff + unstaged diff + untracked-not-ignored contents — the review-payload domain; never-committable untracked paths — character/block devices, FIFOs, sockets — are excluded from the domain entirely, untracked symlinks/directories ride as name-only notes) in code mode, the artifact-file sha256 in plan/diff mode; verdict recorded verbatim from the mandated '### Verdict' section (SHIP / SHIP WITH NITS / REWORK); grounded = whether a NON-EMPTY --facts payload was supplied (an empty payload records grounded:false — fail-closed, the state gate rejects it), factsHash = sha256 of the facts payload; a continuation receipt is fresh:false (informational-only — it cannot attest the folded tree); a write failure warns, never fails the review",
+        "notes": [
+          "pre-dispatch host-diff: before the FIRST dispatch of this bridge, diff its declared networkHosts against the live sandbox allow-list — a missing host is surfaced to the maintainer BEFORE dispatching, never fired into a known prompt"
+        ]
       }
     },
     "probe": { "cmd": "agy-run", "source": "bin/agy.sh", "output": "advisory" }
@@ -50,6 +53,7 @@
     }
   ],
   "networkHosts": ["*.googleapis.com", "accounts.google.com", "antigravity-unleash.goog", "lh3.googleusercontent.com"],
+  "writableDirs": [{ "env": null, "default": "~/.gemini/antigravity-cli" }],
   "detect": {
     "installed": {
       "env": "ANTIGRAVITY_CLI_BRIDGE_DIR",

package/bridges/codex-cli-bridge/SKILL.md

@@ -2,7 +2,7 @@
 name: codex-cli-bridge
 description: Delegate work to the OpenAI Codex CLI (`codex`) under a ChatGPT subscription — run plan/instruction EXECUTION in a sandboxed workspace, or get a read-only ADVISORY review of a plan or working-tree diff — as a second delegated-execution backend beside Antigravity. Use when the user wants to hand a bounded coding task or plan to `codex exec`, get a second-opinion review from codex, install or authenticate Codex CLI, understand its sandbox/network/approval policy, drive codex efficiently from the main agent (exec vs review, resume, the commit boundary), bridge project context (`AGENTS.md`) into codex, or troubleshoot codex flags, models, auth, or its no-TTY headless behaviour.
 metadata:
-  version: '2.5.0'
+  version: '2.7.0'
 ---
 
 # codex-cli-bridge

package/bridges/codex-cli-bridge/bin/codex-exec.sh

@@ -67,6 +67,12 @@ Guarded passthrough after '--':
   blocked always: -c* --config* -s* --sandbox* --dangerously-bypass-approvals-and-sandbox --dangerously-bypass-hook-trust --full-auto --oss --local-provider* -p* --profile* -m* --model* -o* --output-last-message* --json* --color* --output-schema* --ephemeral*
   relaxed only under CODEX_PROBE=1: --add-dir* -C* --cd* --skip-git-repo-check --ignore-rules --enable* --disable*
 
+Notes:
+  nested-sandbox limit: codex-exec ships its OWN OS sandbox (bwrap workspace-write) and cannot run
+  nested inside a harness sandbox (the FS turns read-only) — route it OUTSIDE the harness sandbox
+  (excludedCommands / a per-run consented bypass) on the OBSERVED bwrap/EPERM failure, never a
+  preemptive blanket
+
 Settings file (KEY=VALUE, parsed never sourced; env wins over file, file wins over built-in default):
   ${XDG_CONFIG_HOME:-~/.config}/agent-workflow/bridge-settings.conf
   CODEX_SERVICE_TIER — service tier: 'priority' (Fast — ~1.5x speed at a 2.5x credit rate on gpt-5.6-sol); a consented SPEND knob, default off (standard tier)
@@ -557,6 +563,20 @@ fi
 if [[ $rc -ne 0 ]]; then
   echo "error: codex exec failed (exit $rc). Last lines of the run trace:" >&2
   tail -n 40 "$trace" >&2
+  # Nested-sandbox detection: codex ships its OWN OS sandbox (bwrap); run nested inside a harness
+  # sandbox the FS is read-only and codex's own sandbox setup fails. Fire the STATED recovery hint
+  # only on a COMBINATION — a sandbox MECHANISM token AND a permission/read-only FAILURE token in the
+  # trace — so a lone 'bwrap' banner, or a lone 'permission denied' from unrelated code, is NOT enough
+  # (never a preemptive blanket). grep is line-oriented, so a plain alternation stays within a line —
+  # the old `[^\n]*` between the two halves was wrong twice over (it excluded the letter 'n', and grep
+  # never spans lines anyway), so the split into two `-q` passes both fixes it and states the intent.
+  if grep -qiE 'bwrap|landlock|user namespace|pivot_root|unshare|seccomp' "$trace" 2>/dev/null \
+     && grep -qiE 'read-only file system|erofs|operation not permitted|permission denied|eperm' "$trace" 2>/dev/null; then
+    echo "hint: this looks like a NESTED-SANDBOX failure — codex-exec ships its own OS sandbox (bwrap)," >&2
+    echo "      which cannot run nested inside a harness sandbox (the FS is read-only). Route codex-exec" >&2
+    echo "      OUTSIDE the harness sandbox: add it to the harness sandbox excludedCommands, or dispatch" >&2
+    echo "      this one run via a per-run consented bypass. Do NOT blanket-disable the sandbox." >&2
+  fi
   exit $rc
 fi
 

package/bridges/codex-cli-bridge/bin/codex-exec.test.mjs

@@ -21,6 +21,7 @@ const FAKE_CODEX = [
   '#!/usr/bin/env bash',
   'set -u',
   'if [[ "${1:-}" == "login" ]]; then echo "${CODEX_FAKE_LOGIN:-Logged in using ChatGPT}"; exit 0; fi',
+  'if [[ -n "${CODEX_FAKE_STDERR:-}" ]]; then echo "$CODEX_FAKE_STDERR" >&2; fi',
   ': "${CODEX_FAKE_ARGV:=/dev/null}"',
   ': "${CODEX_FAKE_ENV:=/dev/null}"',
   ': "${CODEX_FAKE_STDIN:=/dev/null}"',
@@ -274,6 +275,49 @@ describe('codex-exec.sh — clean output + session capture (1.2)', () => {
     assert.equal(r.status, 7);
     assert.match(r.stderr, /codex exec failed \(exit 7\)/);
     assert.match(r.stderr, /thread\.started/, 'failure should surface the trace tail');
+    assert.doesNotMatch(r.stderr, /NESTED-SANDBOX/, 'a plain failure (no bwrap signature) never triggers the hint');
+  });
+
+  it('on a NESTED-SANDBOX failure (bwrap/read-only trace) surfaces the stated recovery hint', () => {
+    const sb = makeSandbox();
+    const r = run(sb, { env: { CODEX_FAKE_EXIT: '1', CODEX_FAKE_STDERR: 'bwrap: setting up sandbox: mkdir /newroot: Read-only file system' } });
+    rmSync(sb.root, { recursive: true, force: true });
+    assert.equal(r.status, 1);
+    assert.match(r.stderr, /NESTED-SANDBOX/, 'names the failure class');
+    assert.match(r.stderr, /excludedCommands|per-run consented bypass/, 'states the recovery route');
+    assert.match(r.stderr, /Do NOT blanket-disable/, 'warns against a preemptive blanket');
+  });
+
+  it('a NON-nested codex failure does NOT emit the nested-sandbox hint (no false positive)', () => {
+    const sb = makeSandbox();
+    const r = run(sb, { env: { CODEX_FAKE_EXIT: '3', CODEX_FAKE_STDERR: 'model error: rate limited, try again later' } });
+    rmSync(sb.root, { recursive: true, force: true });
+    assert.equal(r.status, 3);
+    assert.doesNotMatch(r.stderr, /NESTED-SANDBOX/, 'a generic failure never triggers the hint');
+  });
+
+  it('#6 fold: a mechanism+failure trace whose message contains the letter n (mkdir /newroot) still fires — the old [^\\n]* wrongly excluded n', () => {
+    const sb = makeSandbox();
+    const r = run(sb, { env: { CODEX_FAKE_EXIT: '1', CODEX_FAKE_STDERR: 'bwrap: mkdir /newroot: operation not permitted' } });
+    rmSync(sb.root, { recursive: true, force: true });
+    assert.equal(r.status, 1);
+    assert.match(r.stderr, /NESTED-SANDBOX/, 'bwrap (mechanism) + operation not permitted (failure) fire even through n-bearing words');
+  });
+
+  it('#6 fold: a LONE mechanism token (a bwrap banner, no failure) does NOT fire — a combination is required', () => {
+    const sb = makeSandbox();
+    const r = run(sb, { env: { CODEX_FAKE_EXIT: '2', CODEX_FAKE_STDERR: 'bwrap version 0.11.0' } });
+    rmSync(sb.root, { recursive: true, force: true });
+    assert.equal(r.status, 2);
+    assert.doesNotMatch(r.stderr, /NESTED-SANDBOX/, 'a mechanism token without a permission/read-only failure is not nested-sandbox proof');
+  });
+
+  it('#6 fold: a LONE failure token (permission denied, no sandbox mechanism) does NOT fire', () => {
+    const sb = makeSandbox();
+    const r = run(sb, { env: { CODEX_FAKE_EXIT: '2', CODEX_FAKE_STDERR: 'curl: (7) permission denied' } });
+    rmSync(sb.root, { recursive: true, force: true });
+    assert.equal(r.status, 2);
+    assert.doesNotMatch(r.stderr, /NESTED-SANDBOX/, 'a permission failure from unrelated code is not nested-sandbox proof');
   });
 
   it('warns (never silently) when the session sidecar cannot be written', () => {
@@ -734,6 +778,12 @@ describe('codex-exec.sh — --help contract (manifest-pinned)', () => {
     setEq(tier('relaxed only under CODEX_PROBE=1:'), EXEC_CONTRACT.passthrough.probeRelaxed, 'help tier-2 ⟷ manifest probeRelaxed');
   });
 
+  it('Notes renders the manifest contract.notes verbatim (a typed contract key that MUST surface)', () => {
+    const help = runHelp('--help').stdout;
+    assert.ok(EXEC_CONTRACT.notes.length > 0, 'manifest notes must be non-empty');
+    assert.equal(norm(helpSection(help, 'Notes:').join(' ')), norm(EXEC_CONTRACT.notes.join(' ')));
+  });
+
   it('--help after the -- separator is passthrough payload, never intercepted', () => {
     const sb = makeSandbox();
     const r = run(sb, { args: ['-', '--', '--help'], input: 'go' });

package/bridges/codex-cli-bridge/bin/codex-review.sh

@@ -172,7 +172,7 @@ DEFAULT_CODEX_EFFORT="xhigh"
 # Review-receipt identity (AD-038). AW_BRIDGE_VERSION mirrors this bridge's SKILL.md/capability.json
 # version (drift-guarded by codex-review.test.mjs against capability.json).
 AW_RECEIPT_BACKEND="codex"
-AW_BRIDGE_VERSION="2.5.0"
+AW_BRIDGE_VERSION="2.7.0"
 CODEX_MODEL="${CODEX_MODEL:-$DEFAULT_CODEX_MODEL}"
 CODEX_EFFORT="${CODEX_EFFORT:-$DEFAULT_CODEX_EFFORT}"
 # Generous hard cap for a slow xhigh review (subscription latency varies).

package/bridges/codex-cli-bridge/capability.json

@@ -3,7 +3,7 @@
   "schema": 1,
   "name": "codex-cli-bridge",
   "kind": "execution-backend",
-  "version": "2.5.0",
+  "version": "2.7.0",
   "provides": ["execute", "review"],
   "roles": {
     "execute": {
@@ -24,7 +24,10 @@
           "policy": "guarded",
           "blocked": ["-c*", "--config*", "-s*", "--sandbox*", "--dangerously-bypass-approvals-and-sandbox", "--dangerously-bypass-hook-trust", "--full-auto", "--oss", "--local-provider*", "-p*", "--profile*", "-m*", "--model*", "-o*", "--output-last-message*", "--json*", "--color*", "--output-schema*", "--ephemeral*"],
           "probeRelaxed": ["--add-dir*", "-C*", "--cd*", "--skip-git-repo-check", "--ignore-rules", "--enable*", "--disable*"]
-        }
+        },
+        "notes": [
+          "nested-sandbox limit: codex-exec ships its OWN OS sandbox (bwrap workspace-write) and cannot run nested inside a harness sandbox (the FS turns read-only) — route it OUTSIDE the harness sandbox (excludedCommands / a per-run consented bypass) on the OBSERVED bwrap/EPERM failure, never a preemptive blanket"
+        ]
       }
     },
     "review": {
@@ -72,6 +75,7 @@
     }
   ],
   "networkHosts": ["chatgpt.com", "*.chatgpt.com"],
+  "writableDirs": [{ "env": "CODEX_HOME", "default": "~/.codex" }],
   "detect": {
     "installed": {
       "env": "CODEX_CLI_BRIDGE_DIR",

package/capability.json

@@ -3,7 +3,7 @@
   "schema": 1,
   "name": "agent-workflow-kit",
   "kind": "composition-root",
-  "version": "1.45.1",
+  "version": "1.47.0",
   "provides": [],
   "roles": {},
   "detect": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sabaiway/agent-workflow-kit",
-  "version": "1.45.1",
+  "version": "1.47.0",
   "description": "Portable, cross-agent memory & workflow for AI coding agents — Claude Code, Codex, Cursor, Devin Desktop. One command deploys an AGENTS.md entry point + docs/ai context with cap/archive/index enforcement into any repo.",
   "keywords": [
     "ai-agents",

package/references/modes/recommendations.md

@@ -1,14 +1,34 @@
 ### Mode: recommendations
 
-The **read-only deployment advisor** — the deterministic section every `upgrade` run ends with, also invocable on its own. It computes what in THIS deployment is configured sub-optimally (allowlist not seeded, autonomy render drifted, sandbox unavailable, gates undeclared, bridge friction, sandbox-mask clutter) and renders each item as **{what is sub-optimal · the benefit in ONE plain line · the exact consent-gated apply one-liner}**. The tool computes; **you paste the section VERBATIM** (the `composeStatusLine` precedent) — you compose nothing factual.
+Requires: ${CLAUDE_SKILL_DIR}/references/shared/report-footer.md
+
+The **read-only deployment advisor** — the deterministic section every `upgrade` run ends with, also invocable on its own. It computes what in THIS deployment is configured sub-optimally (allowlist not seeded, autonomy render drifted, sandbox unavailable, gates undeclared, bridge friction, sandbox-mask clutter, an unacknowledged sandbox recipe) and renders **verdict-first**: one composed verdict line, then each item as **{severity · what is sub-optimal · the benefit in ONE plain line · the exact consent-gated apply one-liner}**. The tool computes deterministic English DATA; **you PRESENT the section in the user's conversational language** — every fact, count and item from the tool, nothing added or dropped; commands, paths, hosts and rule strings stay **byte-exact**; show the raw tool block on request (the AD-032 report-contract lane — the tool cannot know the dialogue language, so the language rendering is your presentation layer).
+
+**Live host/session facts are tool-composed only.** Every fact this section states about the current
+host or session — prompts fired, sandbox scope, whether a bypass was needed, network reachability,
+approval counts — is **live tool output** from **this session** (the tool computed it on this run); a
+memory/handover snapshot is **context, never report facts**, and a claim with no live signal is
+**omitted or explicitly marked unverified**, never asserted from recollection. Full clause: *Live
+host/session facts* in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md`.
 
 Run `node ${CLAUDE_SKILL_DIR}/tools/recommendations.mjs --cwd <project-root> [--json]`:
 
 1. **`--cwd` is REQUIRED** — the target project is explicit, never inferred from the shell's current directory (a subdirectory invocation still advises on the named root).
-2. **Paste the whole rendered section verbatim**, starting at its `## Recommendations (agent-workflow)` header. It renders **present-even-when-empty**: with everything optimal the body is exactly `no recommendations — flow optimal.` A failed probe renders as a stated `⚠ skipped item …` line — never a crash, never a fabricated item.
-3. **The apply-through-agent lane (consent-first):** after pasting, OFFER to apply; the user picks items in plain language; you run **EXACTLY the rendered one-liners — no improvisation** (each writer keeps its own consent semantics: previews, `--apply` flags, refusals). An item marked **HAND-APPLY** (the network-allowlist item) is **never run by you and never written by the kit** — the user pastes it by hand if they accept the stated risk; the hosts come from each bridge's `capability.json` `networkHosts` (the single documentation source).
-4. Benefit lines are frozen tool data, fact-true: the dual velocity+security wording (`safer — blast radius bounded by the OS sandbox, not human attention`) rides ONLY the items with a real security delta (the autonomy render, the sandbox provisioning); the bridge-wrappers item claims **velocity only**, and risk-bearing items state their risk in the same line.
+2. **Verdict first (present-even-when-empty, opening at the `## Recommendations (agent-workflow)` header).** With everything optimal the body is exactly `no recommendations — flow optimal.` — the empty-state line ALONE is the verdict, zero added lines. Every other state opens the body with ONE verdict line composed from the frozen templates: `{K} item(s) need attention` leads when any item's severity is `attention` (a CONFIGURED declaration that is broken, drifted, degrading or invalid — the deployment needs review); `{N} optional recommendation(s), apply any you want` covers the `optional` class (offers to enable an unconfigured capability), led by `nothing is broken` ONLY when no item needs attention AND no probe check was skipped (a skipped probe could hide an attention-class problem — the claim never overreaches); `optimality NOT attested — {M} probe check(s) skipped` is appended last whenever probe checks were skipped. (The `(s)` invariant form IS the pinned pluralization — no singular/plural branching.) Items render attention-first, each tagged `needs attention:` / `optional:`. A failed probe renders as a stated `⚠ skipped item …` line — never a crash, never a fabricated item.
+3. **The apply-through-agent lane — an explicit informed-consent checkpoint:** after presenting, OFFER to apply; the user selects items in plain language; for each selected item you **surface its posture note inline** where one exists (the per-item notes below cover exactly the risk-marked keys; for `sandbox-lane` the note INCLUDES the sandbox-lanes ladder — present the whole ladder inline at the consent moment, never as a bare pointer). A note-less item's apply is a consent-gated WRITER that carries its own posture surface — relay that writer's preview/notice output before confirming. The user **explicitly confirms**, and **only then** you run **EXACTLY the rendered one-liner — no improvisation** (each writer keeps its own consent semantics: previews, `--apply` flags, refusals). An item marked **HAND-APPLY** is **never run by you and never written by the kit** — hand the user its rendered line together with its posture note.
+4. Registry strings (benefits + item texts) are frozen tool data, fact-true, ONE line under the pinned shape cap — posture/risk detail lives in the notes below at the consent moment, never inline in the overview. The dual velocity+security wording (`safer — blast radius bounded by the OS sandbox, not human attention`) rides ONLY the items with a real security delta (the autonomy render, the sandbox provisioning); the bridge-wrappers item claims **velocity only**.
+
+**Per-item posture notes (the consent moment — surface BEFORE running or handing over the apply):**
+
+- `agy-adddir` — enabling the add-dir offload re-enables the Issue-001 stall risk (the wrapper's hard timeout bounds it); with the knob off an oversized agy code review refuses instead. Risk profile: availability only, no security delta.
+- `sandbox-lane` — surface this note TOGETHER with the sandbox-lanes ladder below (the ladder IS the practical half of the note — inline, never a pointer). Pure DISCOVERABILITY: it surfaces the manifest-declared observed session-sandbox recipe (egress hosts ∪ resolved writable state dirs — `networkHosts` ∪ `writableDirs` of the wired bridges' `capability.json`, the single documentation source) and converges on a NEUTRAL fingerprint acknowledgement (`"agentWorkflow": { "sandboxLaneAck": … }`, either settings scope; a changed recipe re-fires the item). It never claims the settings security keys take effect on any host class, never recommends writing them, and the kit never seeds `sandbox.network.allowedDomains` / `sandbox.filesystem.allowWrite` (bridge council 2026-07-11, both backends concur: a network pre-allow widens egress for EVERY sandboxed command; a write allowance on CLI state dirs would expose credential dirs). Posture history: an IDE-managed session sandbox was live-observed (2026-07-11/12) ignoring hand-applied settings security keys in BOTH scopes, and codex needs a writable HOME (EROFS `~/.codex` in-sandbox); whether a session's sandbox honors the settings keys is runtime-unknowable from the advisor (a denial-only signal) — which is exactly why the item states only detectable facts and no zero-prompt promise on any host class.
+
+**Sandbox lanes (what to DO with the `sandbox-lane` recipe, per host class):**
+
+- **Settings-native sandbox** (the harness reads the `.claude/settings.json` sandbox keys): nothing beyond the `--bridge-tier` wiring — the tier's `excludedCommands` already routes the wrappers OUTSIDE the sandbox, so they never consult `allowedDomains`/`allowWrite`. Record the ack once the tier is confirmed.
+- **Harness-managed sandbox** (an IDE/session-imposed sandbox that ignores the settings keys) — a NARROWEST-SCOPE ladder: (1) prefer wrapper/command-SCOPED sandbox rules where the harness offers them (only the review wrappers gain the egress + state-dir writes); (2) a SESSION-scoped allowance (the manifest hosts + the resolved state dirs for the whole session) is an INFORMED WIDENING — it carries the same blast-radius class the settings security keys were rejected for (every sandboxed command in the session gains that egress and those writable credential dirs), acceptable only as the maintainer's deliberate choice for a review-heavy session; (3) else the per-run consented bypass. Record the ack once a lane is chosen — choosing the bypass, or consciously declining, also counts.
+- Either way the recipe is **observed-minimal, honestly incomplete** — a blocked host names itself at run time; extend by hand and re-ack (the fingerprint moves with the recipe, not with your extensions).
 
-**Invariants:** read-only (never writes, never commits, never runs a subscription CLI) · `--cwd` required · present-even-when-empty · probe failures degrade to stated skip lines · apply one-liners are cwd-independent (absolute tool paths + a pinned `--cwd`; the sandbox-provision item pins via a `cd <root> &&` prefix — the doctor reads its cwd; the ONE exception is the `set-autonomy` item, a conversational skill invocation explicitly labeled *run IN the target project*) · the kit never seeds `sandbox.network.allowedDomains` / `sandbox.filesystem.allowWrite` (hand-apply territory, risk stated).
+**Invariants:** read-only (never writes, never commits, never runs a subscription CLI) · `--cwd` required · present-even-when-empty · verdict-first from frozen templates · probe failures degrade to stated skip lines · apply one-liners are cwd-independent (absolute tool paths + a pinned `--cwd`; the sandbox-provision item pins via a `cd <root> &&` prefix — the doctor reads its cwd; the ONE exception is the `set-autonomy` item, a conversational skill invocation explicitly labeled *run IN the target project*) · the kit never seeds `sandbox.network.allowedDomains` / `sandbox.filesystem.allowWrite` (hand-apply territory; the sandbox-lane convergence is a neutral acknowledgement, never a security key).
 
 **Exit codes:** `0` report rendered (items or the empty state); `1` error (e.g. `--cwd` is not a directory); `2` usage.

package/references/modes/review-ledger.md

@@ -12,11 +12,12 @@ The review-round **LEDGER** (DEBT-REVIEW-CAP / AD-045) — it turns the prose re
    - `--json` → the structured state + decision.
    - **`--telemetry`** → read-only COUNTS across ALL loops and BOTH ledgers (never combined with the other flags — a mixed-mode gate cmd would silently pass): rounds/segments per loop, finding-origin totals, classification distribution (incl. `refuted`), per-backend verdict + divergence-round counts, override usage by scope, gate-run counts (quality-green / red results by gate id), fold runs, observed-red receipts, quarantined probes. Counts only — which gates earn their keep stays the maintainer's judgment.
 
-2. **Writer** — `node ${CLAUDE_SKILL_DIR}/tools/review-ledger-write.mjs record|classify|override --json '<payload>'` (the SOLE writer, over the shared `atomic-write` core):
+2. **Writer** — `node ${CLAUDE_SKILL_DIR}/tools/review-ledger-write.mjs record|classify|override|batch --json '<payload>'` (the SOLE writer, over the shared `atomic-write` core):
    - `record` appends one round — `{ loop, round, origins, backends, findings }` (activity defaults to `plan-execution`). **The teeth (Decision 5 + AD-048, all per SEGMENT):** it REFUSES (typed STOP) to append a round WHILE `decideStop` on the segment's records is `triage-required` (an UNCLASSIFIED surviving blocking finding at/after the cap); refuses ANY round beyond the **hard-max ceiling of 3 within one segment** unconditionally (the counter reopens only at the next gated commit); refuses while a blocking finding of the segment's previous round **VANISHED unclassified** (present means present-as-blocking — a downgrade to minor does not survive; a pending `escalate` never clears; `refuted` is the honest phantom lane); refuses while the changed source surface exceeds the **diff-size cap** (`AW_REVIEW_DIFF_CAP`, default 400 new-side lines of assessable + unsupported SOURCE — tests and out-of-domain never count, pure deletions are free) without a recorded segment `size-cap` override; and refuses without a **quality-green gate-run** at the current fingerprint (`run-gates --record` — gates-before-review is computed, not remembered; a `--only` subset or a tree-changed run never satisfies; red PROCESS gates — the kit's own `--check` loop gates — never block). **Integrity binding (Decision 7):** each NON-degraded backend needs a grounded **code** receipt (from `codex-review code` / `agy-review code --facts @f`) for the current tree — a round cannot be recorded for a tree no bridge reviewed. **`--from-receipts`** (BUGFREE-3 / AD-049) DRAFTS the `backends[]` from those receipts instead of hand-composing them: each recipe-named backend's verdict comes from its fresh grounded code receipt and its counts are computed from the supplied `findings` (`origins` / `findings` stay explicit input); a recipe-named backend with no receipt is a LOUD stop — the draft never invents one (supply it explicitly as a degraded backend if the bridge really is down).
    - `classify` appends one triage — each surviving blocking finding of a SEGMENT round classified `fixable-bug` / `inherent-layer-residual` / `escalate` / **`refuted`** (v4 — the honest lane for a phantom finding, refuted against code: a MANDATORY non-empty `note` cites the grounds; never silently dropped, never folded). **A `fixable-bug` REQUIRES a `testId`** (M2/AD-046, schema v2) — the red→green test that pins the fold, formatted `<test-file>#<test-name-pattern>` (a `#` separator, both halves non-empty; no file-suffix rule); `inherent-layer-residual` / `escalate` may omit it. The writer validates the FORMAT only. **This is what BREAKS the deadlock:** once every surviving blocking finding is classified, `record` permits the next round (a `fixable-bug` classification lets the fix round run — no deadlock).
    - `override` appends one override record (schema v3, BUGFREE-1/AD-047) — the LOUD, durable waiver the **fold-completeness** gate consumes, `{ loop, round, scope, reason }` plus the per-scope payload (EXACT — a stray key is refused): scope **`oracle-change`** → `files[]`, the repo-relative pre-existing test files whose tamper flag it lifts (a fix diff that deliberately rewrote test expectations); scope **`red-proof`** → `testId`, the ONE bound test whose observed-red receipt + custody it waives (a red genuinely unestablishable pre-fold, or a custody file legitimately edited post-fix); scope **`size-cap`** (v4) → `sanctionedLines`, the EXACT changed-surface magnitude the waiver sanctions — **segment-scoped** (it dies at the next commit; a grown surface needs a fresh recorded sanction). Teeth: schema validation, fail-closed ledger read, round-sequence integrity, and the loop must be the SINGLE in-flight plan. QUARANTINE (a flaky/timed-out probe) has NO override lane. Overrides never enter `decideStop` — the two v3 scopes are fold-completeness inputs; `size-cap` is a writer-tooth input.
    - **`gate-run` records (v4, kind `gate-run`)** are minted by `run-gates --record` through the writer's `recordGateRun` API (the runner never opens the ledger itself) — the D5 green-baseline receipt: the FULL declaration + exactly what ran + the tree fingerprint BEFORE and AFTER the run, segment-framed with NO round number, minted only inside the single in-flight loop. A red run records honestly (telemetry fuel); **quality-green** (every declared NON-process gate green, tree unchanged under the run) is judged at read time. Revert-first beyond this is not mechanically observable at this layer — it ships as protocol + telemetry visibility (consecutive red gate-runs), stated plainly.
+   - **`batch`** applies an ordered list of `record` / `classify` / `override` operations in ONE invocation — the prompt-economy lane for a records stage (WRITER-BURST-BATCH: one writer call, not one per op). The payload is `{ operations: [ { verb, …that verb's payload } ] }` (a `record` op may carry `fromReceipts: true`); every op rides the SAME per-verb teeth (no forked validator), so N batched ops are record-equivalent to the same N single invocations. **Two passes:** the whole envelope is validated STRUCTURALLY first with ZERO writes (a malformed envelope stops before any op runs), then ops apply sequentially and **fail-fast** on the first typed STOP — the ops already applied stay recorded (append-only, no rollback) and the STOP names the failing op index + the applied count; **resume by re-running the REMAINING ops**.
 
 **The computed stop (`decideStop`, precedence `converged > resolved-residual > triage-required > continue`).** Machine fields only (counts, `class`, `accepted`, `fingerprint`), never free-text:
 - **converged** — every recipe-named backend present, **non-degraded, at 0 blockers + 0 majors** in the latest round, at the current tree fingerprint. **"Surviving blocking finding" = a blocker OR a major** (a minor never forces triage).

package/references/modes/upgrade.md

@@ -58,10 +58,11 @@ Requires: ${CLAUDE_SKILL_DIR}/references/shared/report-footer.md · ${CLAUDE_SKI
 4. **Equal-head exit — a real successful-exit report, not a bare stop.** If the stamp **equals** the head, the lineage is up to date — but step 3 (the stamp-independent reconciles) ran first and may have changed things, so this is a proper exit report, not a no-op:
    - **Report step 3's outcome in plain language** — for **each** pointer (workflow-methodology, orchestration-recipes and autonomy-policy) whether it was *added*, was *already present* (nothing changed), or was *skipped* (the soft-skip from step 3, with its reason — over the line limit / engine too old / the autonomy pointer's anchor absent); whether the `docs/ai/orchestration.json` config was *seeded* (created from the template), had its onboarding note *refreshed*, was *already current*, or carried a *customized note that was preserved* (a user edit is never clobbered); whether the `docs/ai/gates.json` gate declaration was *seeded* or was *already present* (preserved byte-for-byte); whether the `docs/ai/verification-profile.json` profile was *seeded* or was *already present* (preserved byte-for-byte); whether the `docs/ai/autonomy.json` declaration was *seeded* (the sparse defaults-equivalent note) or was *already present* (preserved byte-for-byte); whether the enforcement-script ensure *added* the `archive-decisions` pair to `scripts/`, found it *already present*, or found an *old ADR layout — migration instructed*; the **placed-bridge refresh** outcome — paste the tool's per-bridge lines verbatim (they are already plain: *refreshed* / *already current* / *skipped — not placed* / *could not refresh* + recovery); the **agent-rules lens** outcome (*refreshed* / *already current* / *custom edit preserved + note* / *file absent* / *engine too old* / *over the line cap*); the **bridge-settings reconcile** outcome (paste the tool's line verbatim); and, for a hidden deployment, whether the hidden-mode footprint was *moved to project-local*, was *already project-local* (nothing changed), or needed a question (ambiguous visibility / a leftover machine-wide block). Plain wording only — never the reconcile/slot/anchor/marker terms (the never-leak-kit-internals Gotcha — `${CLAUDE_SKILL_DIR}/references/shared/deploy-tail.md`).
    - **Never surface the structure number on this exit.** Whatever step 3 did, do **not** recite the `docs/ai` structure version, the internal versioning vocabulary, or the two-axes note here — the number is inert on an equal-head exit; it belongs to *Version disclosure* in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md` (shown at the never-downgrade STOP, the explicit status view, or on an explicit ask). Frame the success itself per the final bullet: if step 3 changed anything, say **what changed** in plain human terms; only a pure zero-diff no-op is *settings already current — no update needed*.
-   - **Render the mandatory Recommendations section — on this exit too, BEFORE the footer.** Run `node ${CLAUDE_SKILL_DIR}/tools/recommendations.mjs --cwd <project-root>` and paste its output VERBATIM from the `## Recommendations (agent-workflow)` header (present-even-when-empty — with everything optimal the body is exactly `no recommendations — flow optimal.`). Then OFFER the consent-gated applies: the user picks items in plain language and you run EXACTLY the rendered one-liners (a HAND-APPLY item is never run by you) — the full lane in `${CLAUDE_SKILL_DIR}/references/modes/recommendations.md`. Pinned order on this exit: Recommendations block → optional applies → report footer → the commit ask (the advisor/apply lane never lands after the commit ask).
+   - **Render the mandatory Recommendations section — on this exit too, BEFORE the footer.** Run `node ${CLAUDE_SKILL_DIR}/tools/recommendations.mjs --cwd <project-root>` and PRESENT its output — from the `## Recommendations (agent-workflow)` header — in the user's conversational language: every fact, count and item from the tool, nothing added or dropped; commands, paths, hosts and rule strings byte-exact; show the raw tool block on request. The section is present-even-when-empty (with everything optimal the body is exactly `no recommendations — flow optimal.`) and VERDICT-FIRST — the composed verdict line renders from the frozen templates `{K} item(s) need attention` / `nothing is broken` / `{N} optional recommendation(s), apply any you want` / `optimality NOT attested — {M} probe check(s) skipped`. Then OFFER the consent-gated applies: the user picks items in plain language; surface each picked item's posture note, get the explicit confirm, then run EXACTLY the rendered one-liners (a HAND-APPLY item is never run by you) — the full lane in `${CLAUDE_SKILL_DIR}/references/modes/recommendations.md`. Pinned order on this exit: Recommendations block → optional applies → report footer → the commit ask (the advisor/apply lane never lands after the commit ask).
+   - **Live host/session facts are tool-composed only.** Any claim this report makes about the current host or session state — prompts fired, sandbox scope, whether a bypass was needed, network reachability, approval counts — must trace to **live tool output** from **this session** (the lines you just composed, or a probe you ran this run); a memory/handover snapshot is **context, never report facts**, and a claim with no live signal is **omitted or explicitly marked unverified** — never asserted from recollection. Full clause: *Live host/session facts* in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md`.
    - **Print the report footer** in the canonical order (version block → one-line backend-status line → welcome mat — the shared contracts in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md`; rendered from the helpers, same host-can't-run skip-with-reason). The welcome mat closes on **one** caveat-aware next step (a behind member first, else `setup` / `recipes` / `velocity` / `agents` / `hook`).
    - **Then ask before committing — never auto-commit.** If step 3 added the slot (or anything else changed), report it and ask. If step 3 was a pure zero-diff no-op and nothing else changed, give the plain **settings already current — no update needed** message (the *Success state* contract in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md`) and still print the read-only version block (installed package versions) + backend line — but **no `docs/ai` structure version and no two-axes note** (nothing changed, so the number is inert here).
 5. Show the relevant `${CLAUDE_SKILL_DIR}/CHANGELOG.md` diff (entries newer than the project's stamp).
 6. **Collect the migration answers FIRST, then apply.** If `AGENTS.md` is missing BOTH the *Communication language* and *Attribution* blocks — i.e. both blocks are missing (a pre-1.1.0 deployment) — ask the two questions as ONE structured multi-question prompt; record each answer individually, write nothing until ALL are answered, and carry the answers into the migrations below: a migration whose answer was already collected never re-asks (its own "Ask the user" step is the standalone fallback); a single missing block keeps its single ask (step 7). Then apply `${CLAUDE_SKILL_DIR}/migrations/<version>-<slug>.md` in **semver order**, only those newer than the project's stamp. Migrations are **idempotent** — safe to re-run.
 7. Reconcile drift: add any kernel files/scripts the project is missing; never clobber project-authored content (their `decisions.md`, `known_issues.md`, page specs stay). Any user question a migration raises follows the same rule as bootstrap — **structured multiple-choice where supported** (`AskUserQuestion` in Claude Code), otherwise prose. If `AGENTS.md` has no *Communication language* block (pre-1.1.0 deployment), **ask the user their conversational language** and insert the block — see `migrations/1.1.0-communication-language.md`. If it has no *Attribution* block (pre-1.2.0 deployment), **ask whether the agent may attribute work to itself / AI** and insert the block (defaulting to `off`) — see `migrations/1.2.0-agent-attribution.md`. (An answer already collected by the step-6 batched prompt is carried in — never re-asked here.)
-8. Re-stamp `docs/ai/.workflow-version` to the **deployment-lineage head** (`2.0.0`, not the package version — mechanics unchanged: the atomic write to the stamp file). In the report, **describe what the upgrade changed in plain human terms** — which parts of their `docs/ai` are now different (the migrations that ran), plus the step-3 **placed-bridge refresh** lines (pasted verbatim), the step-3 **agent-rules lens** outcome (same outcome set as step 4), the step-3 **bridge-settings reconcile** outcome, and the step-3 **autonomy-declaration ensure** outcome (*seeded* / *already present, preserved*) — rather than reciting a version number; **omit the raw structure number**, and do **not** print the two-axes note here (it belongs to *Version disclosure* in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md`, on demand only). Then **render the mandatory Recommendations section**: run `node ${CLAUDE_SKILL_DIR}/tools/recommendations.mjs --cwd <project-root>`, paste its output VERBATIM from the `## Recommendations (agent-workflow)` header (present-even-when-empty: `no recommendations — flow optimal.`), and OFFER the consent-gated applies (run EXACTLY the rendered one-liners; a HAND-APPLY item is never run by you — `${CLAUDE_SKILL_DIR}/references/modes/recommendations.md`). Then **print the report footer** in the canonical order (version block → one-line backend-status line → welcome mat — the shared contracts in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md`; rendered from the helpers, same host-can't-run skip-with-reason; the welcome mat closes on one caveat-aware next step). Then **ask before committing** — the pinned order on this exit is: Recommendations block → optional applies → report footer → the commit ask.
+8. Re-stamp `docs/ai/.workflow-version` to the **deployment-lineage head** (`2.0.0`, not the package version — mechanics unchanged: the atomic write to the stamp file). In the report, **describe what the upgrade changed in plain human terms** — which parts of their `docs/ai` are now different (the migrations that ran), plus the step-3 **placed-bridge refresh** lines (pasted verbatim), the step-3 **agent-rules lens** outcome (same outcome set as step 4), the step-3 **bridge-settings reconcile** outcome, and the step-3 **autonomy-declaration ensure** outcome (*seeded* / *already present, preserved*) — rather than reciting a version number; **omit the raw structure number**, and do **not** print the two-axes note here (it belongs to *Version disclosure* in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md`, on demand only). Then **render the mandatory Recommendations section**: run `node ${CLAUDE_SKILL_DIR}/tools/recommendations.mjs --cwd <project-root>` and PRESENT its output — from the `## Recommendations (agent-workflow)` header — in the user's conversational language (every fact, count and item, nothing added or dropped; commands, paths, hosts and rule strings byte-exact; raw tool block on request; present-even-when-empty: `no recommendations — flow optimal.`), then OFFER the consent-gated applies (per picked item: posture note → explicit confirm → run EXACTLY the rendered one-liner; a HAND-APPLY item is never run by you — `${CLAUDE_SKILL_DIR}/references/modes/recommendations.md`). **Every current host/session claim in this report is tool-composed only** — prompts fired, sandbox scope, whether a bypass was needed, network reachability and approval counts must trace to **live tool output** from **this session**, a memory/handover snapshot is **context, never report facts**, and an unbacked claim is **omitted or explicitly marked unverified** (full clause: *Live host/session facts* in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md`). Then **print the report footer** in the canonical order (version block → one-line backend-status line → welcome mat — the shared contracts in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md`; rendered from the helpers, same host-can't-run skip-with-reason; the welcome mat closes on one caveat-aware next step). Then **ask before committing** — the pinned order on this exit is: Recommendations block → optional applies → report footer → the commit ask.

package/references/modes/velocity.md

@@ -31,7 +31,7 @@ Honesty notes: tier entries get **NO PreToolUse-hook residual coverage** — the
 
 **Invariants:** creates `.claude/` if absent and writes **only** `.claude/settings.json` (no other file); **never** allowlists commit/push/publish; **never** writes `settings.local.json`; never commits; opt-in `acceptEdits`, never silent.
 
-**The `--bridge-tier` (own opt-in, AD-044).** Seeds what a promptless council review run needs — BOTH surfaces: `permissions.allow` prefix rules AND the wrapper names in `sandbox.excludedCommands` (the harness runs an excluded command OUTSIDE the sandbox — the wrappers need network — so a plain allowlisted invocation triggers no sandbox-bypass approval). Both land in the **project** `.claude/settings.json` — the file this writer owns; an exclusion placed only in `settings.local.json` was live-observed NOT to route the command outside the sandbox (2026-07-11: the wrapper then starts sandboxed and dies on a read-only HOME + a network prompt), so hand-wiring the local file is not a working substitute for this tier. **Honesty note:** a session whose sandbox is imposed by the harness runtime itself (e.g. an IDE-managed session sandbox) may ignore settings-level exclusions entirely — there the wrappers need the session-level sandbox config (or a per-run consented bypass); the tier's seeded posture is correct for the settings-native sandbox and simply prompts again elsewhere (fail-safe, never a silent widening). Each bridge's observed egress hosts are declared in its `capability.json` `networkHosts` — the single documentation source (observed-minimal — a blocked host names itself at run time; read the manifests, this doc deliberately retypes no host list). The kit **never seeds** `sandbox.network.allowedDomains` or `sandbox.filesystem.allowWrite` (bridge council 2026-07-11, both backends concur): a network pre-allow widens egress for EVERY sandboxed command, and a write allowance on CLI state dirs (`~/.codex`, `~/.gemini/…`) would make credential dirs writable to every sandboxed command. Per-bridge picture under a harness-managed sandbox (live-observed 2026-07-11/12): an IDE-managed session sandbox ignores hand-applied `sandbox.network.allowedDomains` / `sandbox.filesystem.allowWrite` in BOTH settings scopes — its own per-host network consents govern egress; the durable zero-prompt lanes there are the session/host sandbox config (hosts from `networkHosts` + the CLI state-dir writes) or the per-run consented bypass. codex additionally needs a writable HOME (EROFS `~/.codex`); note the apex-vs-wildcard nuance — an apex domain is NOT covered by its `*.`-wildcard form, so the manifests carry both forms where observed (the blocked host names itself at run time). The upgrade Recommendations advisor renders exactly this as a HAND-APPLY item with the risk stated (`${CLAUDE_SKILL_DIR}/references/modes/recommendations.md`). Membership is the FROZEN review-wrapper constant, **never** the execution/probe wrappers (`codex-exec`, `agy-run` keep their human prompt — delegated execution is not covered by this consent), and only the **`code` review mode** — a `plan`/`diff` invocation takes a file argument that can point OUTSIDE the repo, so those modes keep their prompt; each wrapper entry derives ONLY when its bridge is **placed on PATH** (an absent bridge is a stated skip). The seeded byte-forms (this list IS the documented-invocation source for the bridge tier):
+**The `--bridge-tier` (own opt-in, AD-044).** Seeds what a promptless council review run needs — BOTH surfaces: `permissions.allow` prefix rules AND the wrapper names in `sandbox.excludedCommands` (the harness runs an excluded command OUTSIDE the sandbox — the wrappers need network — so a plain allowlisted invocation triggers no sandbox-bypass approval). Both land in the **project** `.claude/settings.json` — the file this writer owns; an exclusion placed only in `settings.local.json` was live-observed NOT to route the command outside the sandbox (2026-07-11: the wrapper then starts sandboxed and dies on a read-only HOME + a network prompt), so hand-wiring the local file is not a working substitute for this tier. **Honesty note:** a session whose sandbox is imposed by the harness runtime itself (e.g. an IDE-managed session sandbox) may ignore settings-level exclusions entirely — there the wrappers need the session-level sandbox config (or a per-run consented bypass); the tier's seeded posture is correct for the settings-native sandbox and simply prompts again elsewhere (fail-safe, never a silent widening). Each bridge's observed egress hosts are declared in its `capability.json` `networkHosts` — the single documentation source (observed-minimal — a blocked host names itself at run time; read the manifests, this doc deliberately retypes no host list). The kit **never seeds** `sandbox.network.allowedDomains` or `sandbox.filesystem.allowWrite` (bridge council 2026-07-11, both backends concur): a network pre-allow widens egress for EVERY sandboxed command, and a write allowance on CLI state dirs (`~/.codex`, `~/.gemini/…`) would make credential dirs writable to every sandboxed command. Per-bridge picture under a harness-managed sandbox (live-observed 2026-07-11/12): an IDE-managed session sandbox ignores hand-applied `sandbox.network.allowedDomains` / `sandbox.filesystem.allowWrite` in BOTH settings scopes — its own per-host network consents govern egress; the durable zero-prompt lanes there are the session/host sandbox config (hosts from `networkHosts` + the CLI state-dir writes) or the per-run consented bypass. codex additionally needs a writable HOME (EROFS `~/.codex`); note the apex-vs-wildcard nuance — an apex domain is NOT covered by its `*.`-wildcard form, so the manifests carry both forms where observed (the blocked host names itself at run time). The upgrade Recommendations advisor surfaces exactly this recipe (hosts ∪ resolved `writableDirs`) as the HAND-APPLY `sandbox-lane` discoverability item — converging on a neutral fingerprint acknowledgement, with the posture notes at the consent moment (`${CLAUDE_SKILL_DIR}/references/modes/recommendations.md`). Membership is the FROZEN review-wrapper constant, **never** the execution/probe wrappers (`codex-exec`, `agy-run` keep their human prompt — delegated execution is not covered by this consent; codex-exec's nested-sandbox recovery is the canon's observed-failure lane, not a preemptive tier seed), and only the **`code` review mode** — a `plan`/`diff` invocation takes a file argument that can point OUTSIDE the repo, so those modes keep their prompt; each wrapper entry derives ONLY when its bridge is **placed on PATH** (an absent bridge is a stated skip). The seeded byte-forms (this list IS the documented-invocation source for the bridge tier):
 
 - `Bash(codex-review code:*)` — the code-mode prefix, args wildcard; plus `codex-review` in `sandbox.excludedCommands`
 - `Bash(agy-review code:*)` — the code-mode prefix, args wildcard; plus `agy-review` in `sandbox.excludedCommands`

package/references/shared/report-footer.md

@@ -125,3 +125,17 @@ token. Pair it with **one plain-language line** telling the two axes apart, on d
 
 **Never** print this two-axes line on a successful equal-head exit — only at the STOP, the status view,
 or on an explicit ask.
+
+### Live host/session facts — tool-composed only
+
+Any claim a report makes about the **current host or session state** — whether a permission prompt
+fired, what the session sandbox allows or blocks, whether a bypass was needed, which network hosts
+are reachable, how many approvals happened — must trace to **live tool output** produced **this
+session**: a status / recipe / recommendations line the composer emitted on this run, or a probe you
+ran and observed this session. It is never asserted from recollection. A memory or handover note is
+**context, never report facts** — it records what was true when written, not the live state, and is
+never the source of a current-state claim. When no live signal backs such a claim, the claim is
+**omitted or explicitly marked unverified** — never stated as fact and never back-filled from a
+snapshot. This binds **every** report surface (the bootstrap / upgrade exits, the recommendations
+advisor, any ad-hoc status summary); the mode files carry a one-line pointer to this clause, never
+their own copy of it.

package/references/templates/agent_rules.md

@@ -76,7 +76,7 @@ Apply these when authoring a plan, reviewing, folding a finding, or editing code
 - **Per-round emission.** Every review round emits **{round N · finding-origin tally · per-backend verdict}** so the crossover is a computed, visible signal, not a remembered rule.
 - **Recipe fidelity.** Council runs every backend the recipe names, **every round**; silently dropping a ready backend for quota/convenience is a forbidden downgrade — an unavailable backend is a LOUD, stated degrade, never a quiet drop.
 - **ExitPlanMode ≠ execute.** A harness "approved — start coding" prompt authorizes the PLAN only; this methodology overrides it. Continue into execution only as a DELIBERATE transition after the plan + cold-start prompt exist, never an implicit slide.
-- **Cost lanes.** Route every step to the **cheapest adequate executor** — L0 deterministic script (the batched gate matrix over `gates.json`, the rotation `--check`s) · L1 cheap subagent (extraction/drafting only; the orchestrator verifies) · L2 subscription bridge · L3 frontier judgment. A step with **no named guardrail does not move down** a lane, and the **red lines never move down** (council review models · real code · ADR/handover/changelog-entry wording · persuasive copy · go/no-go · the approval asks). Own-error repair: salvage recorded state first (L0/L1, batched), never frontier re-derivation.
+- **Cost lanes.** Route every step to the **cheapest adequate executor** — L0 deterministic script (the batched gate matrix over `gates.json`, the rotation `--check`s) · L1 cheap subagent (extraction/drafting only; the orchestrator verifies) · L2 subscription bridge · L3 frontier judgment. A step with **no named guardrail does not move down** a lane, and the **red lines never move down** (council review models · real code · ADR/handover/changelog-entry wording · persuasive copy · go/no-go · the approval asks). Own-error repair: salvage recorded state first (L0/L1, batched), never frontier re-derivation. **Prompt economy:** read-only fan-out (research/sweeps/extraction) runs ONLY on restricted-tool vehicles — a full-tool subagent for read-only work is a forbidden lane downgrade (invisible prompt-flood + blast radius), and a subagent is never told to shell out for facts obtainable read-only; the orchestrator's own shell form is ONE plain pipeline per call (a `;`/`&&` chain or env-prefixed invocation never matches a prefix allow rule); a fan-out launcher that gates per call yields to the agent-spawn lane — capability-gated: without restricted-tool vehicles (generic full-tool spawning does not count), read-only research stays in the orchestrator's own context, never a vehicle mandate a host cannot satisfy. Judgment, code, synthesis stay at the frontier lane (a task that genuinely runs/writes keeps a full-tool subagent); honest limit: no deterministic gate classifies a dispatch — canon at the point of use + placed vehicles + the retro loop. **Writer economy:** a stage's repeated WRITER commands batch into ONE invocation — the review-ledger triad rides one batched write, other stage writers combine via one launcher per stage; never one writer call at a time (each write is its own prompt).
 
 ---