devrites 6.0.2 → 6.0.4

package/pack/.claude/skills/devrites-lib/reference/standards/windows.md

@@ -1,7 +1,9 @@
 # Windows — the deferral ledger
 
 > Applies when: a change introduces a deferral marker (TODO, FIXME, XXX, HACK,
-> a skipped test, a stub body) or `windows.md` waivers are authored or judged.
+> a skipped or focused test, a stub body), lowers the bar (a checker
+> suppression, an empty catch, a deleted test file, stripped assertions), or
+> `windows.md` waivers are authored or judged.
 
 `windows.md` is the broken-windows ledger. A review finding can describe a new
 `TODO`, a skipped test, or a stubbed body; this artifact makes the register
@@ -24,7 +26,8 @@ Optional until a marker is introduced: a feature with no new markers needs no
   that marker. Five new TODOs in one file need five rows — a blanket row
   cannot cover them.
 - `marker token` is the literal marker the checker reported (`TODO`, `t.Skip(`,
-  `NotImplementedError`, `panic("TODO`, …).
+  `NotImplementedError`, `panic("TODO`, `it.only(`, `eslint-disable`, `noqa`,
+  `nolint`, `#nosec`, `empty-catch`, `deleted-test`, `removed-assertion`, …).
 - `reason` must be non-empty and should name the follow-up owner or slice; a
   row with an empty reason warns and waives nothing.
 - Rows never suppress coverage — they explain it. Reviewers still judge
@@ -39,8 +42,13 @@ devrites-engine check windows <slug> [--worktree|--staged|--base <ref>]
 Exit `0` when no marker is introduced or every hit is waived; `3` when any
 introduced marker lacks a waiver or the workspace/ledger is unreadable; `2`
 on usage errors. It parses the unified diff (`-U0`), treats untracked files as
-wholly new in `--worktree`, and ignores binary files, deletions, and
+wholly new in `--worktree`, and ignores binary files, non-test deletions, and
 `.devrites/` paths; `--staged` and `--base` cover the tracked diff only.
+Removals are file-level hits: a deleted test file is `deleted-test`, and a test
+file that remains but loses assertion lines on net is `removed-assertion`
+(moving an assertion within the file is not a loss; a git-detected rename is
+not a deletion). Loosened thresholds have no deterministic signal and stay a
+review judgment ([`code-review.md`](code-review.md) § Bar integrity).
 
 ## Reviewer posture
 

package/pack/.claude/skills/devrites-lib/reference/workspace-artifact-schema.md

@@ -64,7 +64,7 @@ accept safe legacy basenames. Ordinary phases never rename them.
 | `review.md` | reconciled Review verdict: `## Spec` and `## Code review` accounts, deferred-finding labels/actions, drift | 240 lines |
 | `seal.md` | seal preflight, exact reviewer roster accounts, GO/NO-GO verdict and disclosures | 200 lines |
 | `ai-spec.md` | model/RAG/agent/eval/LLM-output scope for AI surfaces | 160 lines |
-| `windows.md` | deferral-marker waiver ledger: one `- path | marker | reason` row per introduced marker; `check windows` fails on unwaived hits | 120 lines |
+| `windows.md` | deferral/bar-lowering waiver ledger: one `- path | marker | reason` row per introduced marker; `check windows` fails on unwaived hits | 120 lines |
 | `notes.md` | `NOTE-###` anchored notes — rationale/warnings bound to a verbatim quote in one repository file; `note check` regrades anchors and drift blocks seal | 160 lines |
 
 For visual pairs load only matching [playbooks](visual-playbooks/index.md); use
@@ -230,7 +230,10 @@ Done condition: <checkable, exhaustive completion criterion>
 `depends_on` is the machine-readable mirror of `Dependencies`; keep the sets
 identical and cycle-free. `Gate`, `SLA`, and `Checkpoint` are required for HITL
 slices; use `none` when they do not apply. Complexity above 3 triggers reslicing
-unless the stated reason makes the boundary irreducible.
+unless the stated reason makes the boundary irreducible. A Writer allowlist of 12+
+files prints an engine `ADVISORY size:` line (`check task-graph`, `check slice`;
+never blocking): split it acceptance-preserving, or add `Size rationale:` naming
+the inseparable capability.
 
 ## Read next by phase
 

package/pack/.claude/skills/rite-build/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "[--parallel N] [slice number or name]"
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/agents.md","rite-build/reference/phase-contract.md","rite-build/reference/one-slice-cycle.md","rite-build/reference/wright-dispatch.md","rite-build/reference/checkpoint.md","rite-build/reference/spec-drift-guard.md","rite-build/reference/output.md","rite-build/reference/anti-patterns.md"],"triggers":{"afk":["rite-build/reference/afk-discipline.md","devrites-lib/reference/standards/afk-hitl.md","rite-build/reference/checkpoint-protocol.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"coding":["devrites-lib/reference/standards/coding-style.md"],"debug-recovery":["devrites-lib/reference/standards/debug-recovery.md"],"dod":["devrites-lib/reference/standards/definition-of-done.md"],"errors":["devrites-lib/reference/standards/error-handling.md"],"frontend":["rite-build/reference/frontend-trigger.md"],"parallel":["rite-build/reference/parallel-batch.md"],"patterns":["devrites-lib/reference/standards/patterns.md"],"principles":["devrites-lib/reference/standards/principles.md"],"security":["devrites-lib/reference/standards/security.md"],"tdd":["rite-build/reference/tdd.md","devrites-lib/reference/standards/testing.md"],"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md","strategy.md"],"workspaceByRole":{"code-reviewer":["spec.md","plan.md","tasks.md","test-plan.md","architecture.md","decisions.md","state.md"],"doubt-reviewer":["spec.md","plan.md","tasks.md","state.md","decisions.md"],"slice-wright":["brief.md","spec.md","architecture.md","plan.md","tasks.md","test-plan.md","state.md","decisions.md","assumptions.md","questions.md"],"test-analyst":["spec.md","tasks.md","test-plan.md","state.md"]}} -->
+<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/agents.md","rite-build/reference/phase-contract.md","rite-build/reference/one-slice-cycle.md","rite-build/reference/wright-dispatch.md","rite-build/reference/checkpoint.md","rite-build/reference/spec-drift-guard.md","rite-build/reference/output.md","rite-build/reference/anti-patterns.md"],"rootOnly":["rite-build/reference/phase-contract.md","rite-build/reference/wright-dispatch.md","rite-build/reference/checkpoint.md","rite-build/reference/output.md","rite-build/reference/afk-discipline.md","rite-build/reference/checkpoint-protocol.md","rite-build/reference/parallel-batch.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/workflow-artifacts.md"],"triggers":{"afk":["rite-build/reference/afk-discipline.md","devrites-lib/reference/standards/afk-hitl.md","rite-build/reference/checkpoint-protocol.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"coding":["devrites-lib/reference/standards/coding-style.md"],"debug-recovery":["devrites-lib/reference/standards/debug-recovery.md"],"dod":["devrites-lib/reference/standards/definition-of-done.md"],"errors":["devrites-lib/reference/standards/error-handling.md"],"frontend":["rite-build/reference/frontend-trigger.md"],"parallel":["rite-build/reference/parallel-batch.md"],"patterns":["devrites-lib/reference/standards/patterns.md"],"principles":["devrites-lib/reference/standards/principles.md"],"security":["devrites-lib/reference/standards/security.md"],"tdd":["rite-build/reference/tdd.md","devrites-lib/reference/standards/testing.md"],"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md","strategy.md"],"workspaceByRole":{"code-reviewer":["spec.md","plan.md","tasks.md","test-plan.md","architecture.md","decisions.md","state.md"],"doubt-reviewer":["spec.md","plan.md","tasks.md","state.md","decisions.md"],"slice-wright":["brief.md","spec.md","architecture.md","plan.md","tasks.md","test-plan.md","state.md","decisions.md","assumptions.md","questions.md"],"test-analyst":["spec.md","tasks.md","test-plan.md","state.md"]}} -->
 > Read-set manifest: `devrites-engine context <slug> --phase build` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 

package/pack/.claude/skills/rite-build/reference/afk-discipline.md

@@ -9,7 +9,9 @@ contract for the sentinel schema, defaults, gate ceiling, and mutable-counter
 ownership. This file owns only Build's dispatch, charging, and red-path behavior.
 
 Rules: green before `built`; hard `max_slices` cap; gates before the action they
-control; irreversible work (destructive/auth/public API) always pauses.
+control; irreversible work (destructive/auth/public API) always pauses; a tick
+never ends with an open or sealed wave — wait for its returns or
+`dispatch abandon --reason`.
 
 ## Iteration cap
 

package/pack/.claude/skills/rite-build/reference/one-slice-cycle.md

@@ -21,8 +21,9 @@ DISPATCH  → hand the slice contract to devrites-slice-wright (fresh context).
 (DOUBT)   → orchestrator, on return: devrites-doubt each non-trivial decision the wright stood up
             — dispatch the initial read-only reviews of distinct decisions in parallel
             (independent claims, fresh contexts); wright fixes stay serial — writers share files
-PROVE     → root: required build/browser/E2E, then returned-diff/path review; fail-on-red
-            (red/gap → repair wright, then re-review/re-prove; do not commit yet)
+PROVE     → root, concurrent with the reviews on the same frozen candidate:
+            required build/browser/E2E, then returned-diff/path recheck; fail-on-red
+            (red/gap → repair wright, then re-review and re-prove; do not commit yet)
 RECORD    → orchestrator: after green verification, update state.md/evidence.md and
             upsert the authoritative candidate manifest from the actual scoped diff
 (CHECKPOINT) → only now, with review+proof green: local WIP(<slug>): <imperative summary>

package/pack/.claude/skills/rite-build/reference/output.md

@@ -9,7 +9,7 @@ Evidence: acceptance met; tests <cmd> → pass; browser <summary|n/a>; drift <no
 Open: <none|blockers|questions>
 Next: /rite-build
 Record: .devrites/work/<slug>/evidence.md
-↻ Hygiene: /clear between slices; /rite-handoff if away > a few hours
+↻ Hygiene: /clear between slices (none in `orient` `inflight_waves`); /rite-handoff if away > a few hours
 ```
 
 **All built:**

package/pack/.claude/skills/rite-build/reference/parallel-batch.md

@@ -94,13 +94,15 @@ Lease: `batch_id`, `created_at`, `base_sha`, `n`,
    <id>`; a malformed contract is dropped from the batch and recorded as a
    gap, not dispatched.
 2. Write lease; freeze `B=HEAD`; `parallel create` worktrees.
-3. Dispatch ≤10 wrights in parallel (cwd=worktree; allowlist; prove `HEAD==B`).
+3. Dispatch ≤10 wrights in parallel (cwd=worktree; allowlist; prove `HEAD==B`;
+   one `--slice` per sibling on the wave).
 4. Inspect each returned path list, cumulative diff from `B`, transfer identity,
    and required result fields against the immutable contract. Reject malformed,
    stale, or out-of-scope work. Apply
    [independent Build review](phase-contract.md#independent-build-review): first
-   full inventory, then bounded owning-role rechecks after repairs. Gap or
-   Critical/Important → `gap`; else approved proof → `green|red|gap`.
+   full inventory, then bounded owning-role rechecks after repairs. Run approved
+   proof in the same window as that review. Gap or Critical/Important → `gap`;
+   else proof → `green|red|gap`.
    Reviewer fan-out for a batch is itself batched under
    [`parallel-dispatch.md`](../../devrites-lib/reference/parallel-dispatch.md#scale-limits)
    (≈4 concurrent read-only reviewers, 8 only with disjoint paths), and `max_agents`

package/pack/.claude/skills/rite-build/reference/phase-contract.md

@@ -14,6 +14,8 @@ Spec Drift Guard still applies.
    `Implementation readiness: READY`, current `Readiness inputs SHA-256`, exact
    required accounts, ID/meaning traceability and green proof preflight.
    Run `devrites-engine check readiness <slug>`; any miss/nonzero blocks.
+   Non-empty `orient` `inflight_waves` is reconciled first: `dispatch return` each
+   role whose account is in hand, else `dispatch abandon --reason` and re-dispatch.
 2. **Select.** Pick the lowest pending slice whose `depends_on` are all built, using
    `orient` `task_graph.slices` plus the `state.md` built list — never by scanning
    `tasks.md`; then `observe slice` it. Restate its goal, ACs, exclusions and exact paths. Include
@@ -33,11 +35,13 @@ Spec Drift Guard still applies.
    spending review. Then compare returned paths and `git diff --name-only` with the
    contract for semantics diff-scope cannot judge (stale/partial/malformed work;
    preserved user work). Restoration uses the bounded wright.
-5. **Review.** Apply [Independent Build review](#independent-build-review).
+5. **Review.** Apply [Independent Build review](#independent-build-review). Run step 6
+   proof in the same window on the same frozen candidate; both gate step 7, and a
+   repair or source-mutating proof voids both.
    Missing verdicts, principle breaches and open Critical/Important block acceptance.
 6. **Prove.** Against the frozen pre-slice candidate inspect
    test hunks for deletion, skipping/focus, tautology, or weaker expectations.
-   Use step 5's exact test-analyst account; missing/adverse criterion verdict is
+   Wait for step 5's exact test-analyst account; missing/adverse criterion verdict is
    Critical. Run only `test-plan.md` repository/CI commands, record output, recheck
    `git diff --name-only`. Missing/weakened/red/source-mutating proof cannot pass.
    Pre-existing/environment-specific claims need a predating same-command,
@@ -70,7 +74,7 @@ inventory: one full-diff `devrites-code-reviewer`, one `devrites-test-analyst`,
 and one exact `devrites-doubt-reviewer` per stood decision that meets
 `devrites-doubt` § When to use (boundary, data model, auth, public API, migration,
 user flow, assumption tests cannot prove); other stood decisions are recorded in
-`decisions.md` without dispatch. Dispatch fresh,
+`decisions.md` without dispatch. Bundles take `--slice <SLICE-ID>`. Dispatch fresh,
 read-only under [`parallel-dispatch.md`](../../devrites-lib/reference/parallel-dispatch.md).
 Wait for every required account to become terminal; missing/gap needs a valid result.
 Fold supported in-scope Critical/Important findings by cause into one inventory.

package/pack/.claude/skills/rite-build/reference/spec-drift-guard.md

@@ -22,7 +22,9 @@ phases. Never silently code against a known-wrong plan.
 4. Local repair that preserves behavior/scope/architecture/data/UX/security/migration?
      YES, active-slice technical/tool failure → log it and use Build's bounded debug
        recovery. Do not ask for retry authorization and do not re-plan unless the
-       durable remaining-work instructions are wrong.
+       durable remaining-work instructions are wrong. A Workflow Artifact byte fix
+       that keeps every admission row is this case: `OFFLINE_RECOVERY`, then
+       `/rite-vet`'s bytes-only recheck — never `/rite-plan repair`.
      YES, durable plan is wrong → run the batch sweep below, log every
        violation, save the caller's return cursor, then invoke `/rite-plan repair` and `/rite-vet` inline
        without a question — ONE folded repair for all open entries, ONE

package/pack/.claude/skills/rite-build/reference/wright-dispatch.md

@@ -55,8 +55,9 @@ worktrees stay forbidden.
 2. Include goal, verbatim acceptance, exclusions, context,
    `test-plan.md` proof commands, applicable standards, and the exact
    `WIP(<slug>):` subject (no slice id). Build the wright's read-set with
-   `devrites-engine context <slug> --phase build --role slice-wright --trigger <set>`
-   and hand it the bundle path; evaluate each trigger condition and pass those
+   `devrites-engine context <slug> --phase build --role slice-wright --slice <SLICE-ID> --trigger <set>`
+   and hand it the bundle path (over-budget artifacts arrive as anchor indexes;
+   read owning sections live). Evaluate each trigger condition and pass those
    that fire (TDD slice → `tdd`, AFK run → `afk`, UI work → `frontend`, …).
    The command prints `unselected=[...]`; an omitted applicable trigger is a gap.
    For each triggered
@@ -80,8 +81,14 @@ is never a task path; see [Workflow Artifact admission](../../devrites-lib/refer
 Ask the host
 for the exact writer in fresh context and wait. Track it through the
 launch barrier — `devrites-engine dispatch <slug> open --phase build --wave
-<slice-id> --role slice-wright`, then `start` with the host handle, `seal`, and
-`return` on completion (auto-records dispatch/return metrics). Use
+<slice-id> --role slice-wright --slice <SLICE-ID>`, then `start` with the host handle, `seal`, and
+`return` on completion (auto-records dispatch/return metrics). Every 5 wright
+rounds on one slice, `open` blocks for a reslice review: propose an
+acceptance-preserving split (`root_no_change_analysis` → `FOLD` per
+[acceptance-preserving-reslice](../../devrites-lib/reference/standards/acceptance-preserving-reslice.md);
+open findings move to the new slice owning their paths), or record
+`## <DRIFT-ID> — <SLICE-ID> reslice review` with why no smaller split exists and
+reopen with `--reslice-review <DRIFT-ID>`. Use
 at most one writer across all linked worktrees for this workspace. Never run two
 writers in one worktree, run isolated and same-worktree writers concurrently, or
 substitute a generic agent. Opt-in `/rite-build --parallel N` fans out only under
@@ -106,17 +113,24 @@ TTL is crash recovery, not normal cleanup.
    Reject a result that omits any required key — the bookkeeping arrays count
    whether empty or filled — or adds a path. Root never widens scope or edits
    source.
-2. Inspect the test diff for deletion, skipping, focus markers, or loosened
+2. Run `devrites-engine check windows <slug>` on the wright's diff (`--worktree`
+   in the same tree; `--base <B> --cwd <worktree>` for a parallel transfer
+   commit). Each unwaived hit is repaired through the bounded wright or gets a
+   reasoned `windows.md` row before review; never waive to reach green. Then
+   inspect the test diff for deletion, skipping, focus markers, or loosened
    assertions. Dedicated test analysis treats weakening as Critical.
    Confirm a test for a data/integration/topology risk can actually exhibit that risk;
    mocks that erase it and one-root proof offered for another root are unproven.
 3. Apply [independent Build review](phase-contract.md#independent-build-review)
-   before proof. Human choices return; technical failures follow
+   and, in the same window, run only repository proof already approved by
+   `test-plan.md` against the same frozen candidate; neither waits for the
+   other. Human choices return; technical failures follow
    [the canonical retry contract](../../devrites-lib/reference/standards/afk-hitl.md#retry-cap-no-progress-loops-and-self-resolve).
    Derive accounting from recorded reproductions, corrections, and decisive rechecks.
-4. Run only repository proof already approved by `test-plan.md`, then inspect
-   `git diff --name-only` again in case a proof tool changed source.
-   **Do not land on control until review and proof are green.** Isolated
+4. After proof, inspect `git diff --name-only` again in case a proof tool changed
+   source; a change rejects that candidate and voids the concurrent review. A
+   repair wright voids both; rerun both on the new candidate.
+   **Do not land on control until review and proof are both green.** Isolated
    `transfer_commit` stays on the worker branch; same-worktree diffs stay
    uncommitted. Serial: [`checkpoint.md`](checkpoint.md), then host may remove the
    worktree. Parallel: `record-green` only; land with `parallel integrate

package/pack/.claude/skills/rite-define/SKILL.md

@@ -158,7 +158,8 @@ Pull these via `Read` when shaping the plan:
    acceptance, and names/prose agree. Missing, duplicate, contradictory, or
    meaning-changing mappings block. Then run
    `devrites-engine check task-graph <slug>`; a malformed dependency graph blocks
-   before Vet rather than spending a reviewer context on invalid tasks.
+   before Vet rather than spending a reviewer context on invalid tasks. Resolve each
+   `ADVISORY size:` line now (split, or `Size rationale:`); it never blocks.
 7. **Readiness gate** (`plan-template.md`): require CLEAR coverage; complete acceptance,
    wiring, shared-contract proof, applicable outputs, and rollback; risk-first acyclic order;
    justified deviations; and every horizon item present, with blockers resolved, planning

package/pack/.claude/skills/rite-plan/SKILL.md

@@ -79,7 +79,8 @@ Before classifying any Reslice, read `.claude/skills/devrites-lib/reference/stan
      `/rite-spec`, and stop.
    See [replan-and-repair](reference/replan-and-repair.md) for each mode's steps.
 2a. **Draft fresh.** Dispatch `devrites-plan-drafter` in `repair` mode with frozen mode,
-   affected artifacts, settled contract, and failure/drift. Await one atomic, read-only
+   affected artifacts, settled contract, and failure/drift; a slice-bound repair
+   builds its bundle with `--slice <SLICE-ID>` per affected slice. Await one atomic, read-only
    the drafter's `candidate_files` bundle; human choices return separately.
    When the observed failure is missing or ambiguous consumptive-action evidence,
    require the drafter to apply [`one-shot-actions.md`](../devrites-lib/reference/standards/one-shot-actions.md) and return the bounded

package/pack/.claude/skills/rite-pressure-test/SKILL.md

@@ -18,7 +18,8 @@ first and write only workspace/ticket artifacts.
 - Search `decisions.md`, accepted ADRs, and relevant archives for rejected directions;
   revive one only with evidence that answers its recorded reason, citing both.
 - Generate 3-5 different shapes, including obvious, smaller, and different-boundary/data/
-  flow options. Use named lenses— inversion, constraint removal, audience shift, 10×, or
+  flow options, plus a **do-nothing baseline** (cost of not building) that every option
+  must beat. Use named lenses— inversion, constraint removal, audience shift, 10×, or
   expert practice—without padding. Borrow analogous mechanisms, not branding.
 - For each, name concrete entities/flows/surfaces, optimization, rough cost, and main risk.
 
@@ -27,7 +28,9 @@ first and write only workspace/ticket artifacts.
 - Weigh options against the goal, constraints, and existing codebase conventions.
 - Prefer felt pain over nice-to-have. Rank differentiation: new capability > 10× gain >
   new audience > new context > better UX > cheaper; do not dress a vitamin as a painkiller.
-- Recommend one, with the reason and the key trade-off accepted.
+- Recommend one, with the reason and the key trade-off accepted. When no option beats
+  the do-nothing baseline, recommend **Kill**: record the reason in `decisions.md` and
+  do not route to `/rite-spec`.
 - Note what would change the recommendation (the decision's hinge).
 
 ## Premise evidence floor
@@ -65,7 +68,7 @@ Done: pressure test complete for <goal>.
 Changed: workspace only
 Evidence: options compared <n>; recommendation <option>; hinge <condition>; premises <supported/assumption/refuted + sources>
 Open: <none | unresolved premise and resolving evidence>
-Next: <when supported: /rite-spec <feature>; when Hold: none — requires <resolving evidence>>
+Next: <when supported: /rite-spec <feature>; when Hold: none — requires <resolving evidence>; when Kill: none — not building: <reason>>
 Record: <investigation-map.md path | questions.md id (Hold) | not applicable>
 ↻ Hygiene: /clear before starting the lifecycle
 ```

package/pack/.claude/skills/rite-vet/SKILL.md

@@ -171,7 +171,15 @@ plan declares a root-authored executable workflow file, read
    `devrites-engine gates lint <slug> --strict` and resolve every finding before
    READY; the readiness check refuses a missing or malformed ledger but does not
    replace this oracle-quality gate.
-7. **Narrow recheck after edits.** Dispatch the exact plan reviewer once per
+7. **Narrow recheck after edits.** A slice-bound recheck builds its bundle and
+   opens its wave with `--slice <SLICE-ID>` per affected slice (every 5 rechecks
+   per slice need a reslice review, as in Build). **Workflow Artifact bytes-only:**
+   after `OFFLINE_RECOVERY`, a correction leaving every admission/`WA-*` row
+   unchanged records `Workflow Artifact reviewed identity: <re-preflight identity
+   digest>` below the admission block; when `check drift` reports only
+   `reviewed-identity-only`, the reviewer is one fresh `devrites-code-reviewer` on
+   the prior-source→re-preflight diff against those rows (no drafter or plan
+   reviewer); green proceeds to step 8. Otherwise dispatch the exact plan reviewer once per
    fold — one dispatch covering every open fingerprint, preserving
    per correction/fingerprint accounting (each checked individually with its
    accepted findings, changed paths/criteria, new identity, and recorded delta

package/pack/.claude/skills/rite-vet/reference/review-axes.md

@@ -27,7 +27,8 @@ Before implementation review, check for work beyond the settled spec.
    [feature ceiling](../../rite-plan/reference/slicing.md#feature-ceiling-split-an-epic-never-override-the-budget)
    (over-budget `tasks.md`/`plan.md` from slice or AC count) is a scope finding, not a
    `Budget override`: route to `/rite-plan course-correct` (`MVP cut`) with the
-   continuation sequence named; do not vet the whole epic.
+   continuation sequence named; do not vet the whole epic. An `ADVISORY size:`
+   slice without `Size rationale:` is a non-blocking Suggestion to split it.
 4. **Built-in check.** For each new pattern/infra/concurrency approach, invoke
    `devrites-source-driven` inline to verify current framework/runtime support and cite it. Custom
    work where a built-in suffices is a scope-reduction finding.
@@ -195,7 +196,10 @@ Use standard `AskUserQuestion`:
    recovery owner, test, handling, and user-visible/silent result. No test + no handling +
    silent = **Critical** (`artifacts.md`).
 4. **Dependency safety:** verify graph/order and shared file/state/contract/lock/port/queue/env
-   conflicts. Correct the plan; native host scheduling needs no lane artifact.
+   conflicts. Each `Dependencies` edge must genuinely gate its slice (consumes an
+   output, interface, or state the predecessor produces); remove an ordering-only
+   edge, since it silently shrinks the parallel set. Correct the plan; native host
+   scheduling needs no lane artifact.
 5. **Build-entry preflight:** commands/cwds, tools, package state, parser/browser smoke,
    prerequisites, and provenance ([`artifacts.md`](artifacts.md)).
 6. **Implementation readiness:** goal-backward coverage, wiring, dependency simulation,

package/pack/generated/claude/agents/devrites-slice-wright.md

@@ -120,7 +120,10 @@ unclear boundary is underspecified: return `Escalation` without proceeding.
    new fingerprint. At the limit return the gate and repro. `Escalation` is only for product/irreversible choices
    or human-only access; technical failure is a blocker.
    Before handoff, inspect your cumulative slice diff against the contract and
-   scenario matrix, including correction-affected adjacent variants. Fix supported
+   scenario matrix, including correction-affected adjacent variants, then against
+   the reviewers' own checks: [code review § What to check](../skills/devrites-lib/reference/standards/code-review.md#what-to-check-tests-first)
+   and test analysis (each acceptance criterion has a test that fails without the
+   change; no assertion-free, tautological, or mock-asserting test). Fix supported
    in-scope gaps together, rerun affected proof, and report remaining gaps. Self-check
    never replaces independent review; green tests do not prove all possible cases.
 5. **TRANSFER when isolated.** After green writer-safe proof, verify the diff again,
@@ -138,7 +141,9 @@ Stay inside the exact project-relative paths listed in the dispatch task.
 return an `Escalation`** when:
 - the slice is **underspecified**, the **plan looks wrong**, or requirements, code,
   and tests conflict;
-- the slice needs a **new dependency** or a **second design system**;
+- the slice needs a **new dependency** or a **second design system**, or a planned
+  package fails to install or resolve (report the failure; never retry under a
+  similar or alternative package name);
 - the work requires an unapproved product/security-policy choice, public API break,
   external-service contract change, destructive live migration, or filesystem
   destruction outside the workspace. A path allowlist alone does not approve those

package/pack/generated/claude/skills/devrites-debug-recovery/reference/hypotheses.md

@@ -3,6 +3,12 @@
 Generate **3-5 ranked hypotheses** *before* testing any of them.
 Single-hypothesis generation anchors on the first plausible idea.
 
+**Check past root causes first.** Search `.devrites/archive/*/evidence.md` with
+native file search for the failure's error text, symbol, and file names. A hit
+whose recorded correct hypothesis matches enters the ranked list with its
+recurrence noted; it is still tested, never assumed. No archive or no hit →
+skip silently.
+
 Each hypothesis must be **falsifiable**: state the prediction it makes.
 
 > Format: *"If <X> is the cause, then <changing Y> will make the failure

package/pack/generated/claude/skills/devrites-lib/reference/parallel-dispatch.md

@@ -36,6 +36,7 @@ If the candidate diff has no matching surfaces, record
 2. Build each reviewer's read-set once with
    `devrites-engine context <slug> --phase <p> --role <role> --trigger <set>` and
    hand the bundle path as the packet's source list instead of a file roster.
+   Build roles add `--slice <SLICE-ID>` (slice-scoped, slice-named bundle).
    Evaluate the skill's trigger conditions and pass each that fires — a role's
    Trigger column maps to manifest names: `security-auditor` → `security`,
    `frontend-reviewer` → `ui`/`frontend`, `performance-reviewer` → `performance`.

package/pack/generated/claude/skills/devrites-lib/reference/standards/README.md

@@ -59,7 +59,7 @@ topic's owner.
 | `architecture-health.md` | An audit needs a whole-codebase structural score from a code index — coupling, cohesion, cycles, god files, orphans, depth. |
 | `assumption-checkpoints.md` | Scope generalizes an existing boundary: a second case, a newly optional field, or a constant turned parameter. |
 | `debug-recovery.md` | Waiting on async readiness (server start, job completion, browser signal) needs a bounded condition-based poll. |
-| `windows.md` | A deferral marker (TODO/FIXME/skipped test/stub) is introduced or waived — the `check windows` ledger and grammar. |
+| `windows.md` | A deferral or bar-lowering marker (TODO/FIXME/skipped test/stub/suppression/removed test) is introduced or waived — the `check windows` ledger and grammar. |
 | `glossary.md` | A DevRites term is unclear; resolve it once here instead of inferring. |
 
 The table is a load trigger, not an exemption. [`core.md` § Rule summary](core.md#rule-summary-load-the-full-file-when-in-scope)

package/pack/generated/claude/skills/devrites-lib/reference/standards/afk-hitl.md

@@ -357,6 +357,8 @@ access, safety and irreversible-action boundaries independently stop work.
   renaming/splitting an unchanged cause does not. Suggestion/Nit/FYI cannot extend
   recovery. Initial discovery and expected test-first RED are not corrections;
   total rounds, re-batches and distinct-finding counts never exhaust recovery.
+  Every 5 Build wright rounds on one slice, the next first needs a reslice review
+  ([`wright-dispatch.md`](../../../rite-build/reference/wright-dispatch.md#run)).
 - **Rechecks are scoped; late findings never reopen the round.** *Late* applies only
   from a phase's **second** review pass (Vet 1b, Build's recheck after the first repair,
   Review step 7); an initial pass has no late findings and every supported finding is

package/pack/generated/claude/skills/devrites-lib/reference/standards/code-review.md

@@ -30,6 +30,9 @@ If it does not, do not merge it.
    no justification), stripped assertions, deleted or skipped tests, and new
    unimplemented stubs or `throw`-only placeholders. Each names what it lowers and
    needs a recorded reason in the diff or `decisions.md`; unexplained is a finding.
+   `devrites-engine check windows` flags the mechanical subset (suppressions,
+   skip/focus, stubs, empty catch, deleted tests, stripped assertions) against
+   `windows.md` waivers; loosened thresholds remain this sweep's judgment.
 3. **Correctness:** logic, edge cases, error paths, race conditions, wrong assumptions. For branching or boundary changes, run the [`edge-case trace`](edge-case-trace.md): relevant probe classes, fixed-set siblings, real wiring, negative intent, and deletion contracts with an evidence disposition.
 4. **Readability:** names, function size, control flow, intent obvious without the author.
 5. **Architecture:** right seam, coupling/cohesion, fits existing patterns, no premature

package/pack/generated/claude/skills/devrites-lib/reference/standards/glossary.md

@@ -35,6 +35,6 @@
 | Standards | The rule files in this directory; `core.md` is always-on, the rest load on trigger (`README.md` table). |
 | Transfer commit | The isolated wright's local unpushed `WIP(<slug>):` transport commit; never the control-branch checkpoint. |
 | Trigger | A named conditional read-set in a `loads:` manifest (e.g. `tdd`, `applicability`, `ui`); engine fails closed on unknown names. |
-| Windows ledger | `windows.md`: one waiver row per deferral marker the change introduces; `check windows` fails on unwaived hits. [`windows.md`](windows.md). |
+| Windows ledger | `windows.md`: one waiver row per deferral or bar-lowering marker the change introduces; `check windows` fails on unwaived hits. [`windows.md`](windows.md). |
 | Workflow Artifact | A Vet-ready, root-authored executable file under `.devrites/work/<slug>/`; [`workflow-artifacts.md`](workflow-artifacts.md). |
 | Wright | `devrites-slice-wright`: the sole product source/test writer under a path-bounded contract. |

package/pack/generated/claude/skills/devrites-lib/reference/standards/security.md

@@ -96,6 +96,7 @@ On any security-relevant error: deny, roll back; never default to allow or half-
 - Install reproducibly from a committed lockfile (`npm ci` / frozen); never resolving installs in CI. Hand-editing lockfiles bypasses review.
 - Distrust install scripts (`postinstall` runs arbitrary code) — review before adding; prefer `--ignore-scripts`.
 - Typosquats are a delivery vector: confirm exact name/publisher, not install success.
+  After a failed install, never try a similarly named package; report the failure.
 - A CI/release change names the SLSA build provenance level it claims and where the build runs; a claimed level with no verified provenance attestation is `cannot_verify`, not a pass.
 
 ## Trust boundary (three tiers)

package/pack/generated/claude/skills/devrites-lib/reference/standards/windows.md

@@ -1,7 +1,9 @@
 # Windows — the deferral ledger
 
 > Applies when: a change introduces a deferral marker (TODO, FIXME, XXX, HACK,
-> a skipped test, a stub body) or `windows.md` waivers are authored or judged.
+> a skipped or focused test, a stub body), lowers the bar (a checker
+> suppression, an empty catch, a deleted test file, stripped assertions), or
+> `windows.md` waivers are authored or judged.
 
 `windows.md` is the broken-windows ledger. A review finding can describe a new
 `TODO`, a skipped test, or a stubbed body; this artifact makes the register
@@ -24,7 +26,8 @@ Optional until a marker is introduced: a feature with no new markers needs no
   that marker. Five new TODOs in one file need five rows — a blanket row
   cannot cover them.
 - `marker token` is the literal marker the checker reported (`TODO`, `t.Skip(`,
-  `NotImplementedError`, `panic("TODO`, …).
+  `NotImplementedError`, `panic("TODO`, `it.only(`, `eslint-disable`, `noqa`,
+  `nolint`, `#nosec`, `empty-catch`, `deleted-test`, `removed-assertion`, …).
 - `reason` must be non-empty and should name the follow-up owner or slice; a
   row with an empty reason warns and waives nothing.
 - Rows never suppress coverage — they explain it. Reviewers still judge
@@ -39,8 +42,13 @@ devrites-engine check windows <slug> [--worktree|--staged|--base <ref>]
 Exit `0` when no marker is introduced or every hit is waived; `3` when any
 introduced marker lacks a waiver or the workspace/ledger is unreadable; `2`
 on usage errors. It parses the unified diff (`-U0`), treats untracked files as
-wholly new in `--worktree`, and ignores binary files, deletions, and
+wholly new in `--worktree`, and ignores binary files, non-test deletions, and
 `.devrites/` paths; `--staged` and `--base` cover the tracked diff only.
+Removals are file-level hits: a deleted test file is `deleted-test`, and a test
+file that remains but loses assertion lines on net is `removed-assertion`
+(moving an assertion within the file is not a loss; a git-detected rename is
+not a deletion). Loosened thresholds have no deterministic signal and stay a
+review judgment ([`code-review.md`](code-review.md) § Bar integrity).
 
 ## Reviewer posture
 

package/pack/generated/claude/skills/devrites-lib/reference/workspace-artifact-schema.md

@@ -64,7 +64,7 @@ accept safe legacy basenames. Ordinary phases never rename them.
 | `review.md` | reconciled Review verdict: `## Spec` and `## Code review` accounts, deferred-finding labels/actions, drift | 240 lines |
 | `seal.md` | seal preflight, exact reviewer roster accounts, GO/NO-GO verdict and disclosures | 200 lines |
 | `ai-spec.md` | model/RAG/agent/eval/LLM-output scope for AI surfaces | 160 lines |
-| `windows.md` | deferral-marker waiver ledger: one `- path | marker | reason` row per introduced marker; `check windows` fails on unwaived hits | 120 lines |
+| `windows.md` | deferral/bar-lowering waiver ledger: one `- path | marker | reason` row per introduced marker; `check windows` fails on unwaived hits | 120 lines |
 | `notes.md` | `NOTE-###` anchored notes — rationale/warnings bound to a verbatim quote in one repository file; `note check` regrades anchors and drift blocks seal | 160 lines |
 
 For visual pairs load only matching [playbooks](visual-playbooks/index.md); use
@@ -230,7 +230,10 @@ Done condition: <checkable, exhaustive completion criterion>
 `depends_on` is the machine-readable mirror of `Dependencies`; keep the sets
 identical and cycle-free. `Gate`, `SLA`, and `Checkpoint` are required for HITL
 slices; use `none` when they do not apply. Complexity above 3 triggers reslicing
-unless the stated reason makes the boundary irreducible.
+unless the stated reason makes the boundary irreducible. A Writer allowlist of 12+
+files prints an engine `ADVISORY size:` line (`check task-graph`, `check slice`;
+never blocking): split it acceptance-preserving, or add `Size rationale:` naming
+the inseparable capability.
 
 ## Read next by phase
 

package/pack/generated/claude/skills/rite-build/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "[--parallel N] [slice number or name]"
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/agents.md","rite-build/reference/phase-contract.md","rite-build/reference/one-slice-cycle.md","rite-build/reference/wright-dispatch.md","rite-build/reference/checkpoint.md","rite-build/reference/spec-drift-guard.md","rite-build/reference/output.md","rite-build/reference/anti-patterns.md"],"triggers":{"afk":["rite-build/reference/afk-discipline.md","devrites-lib/reference/standards/afk-hitl.md","rite-build/reference/checkpoint-protocol.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"coding":["devrites-lib/reference/standards/coding-style.md"],"debug-recovery":["devrites-lib/reference/standards/debug-recovery.md"],"dod":["devrites-lib/reference/standards/definition-of-done.md"],"errors":["devrites-lib/reference/standards/error-handling.md"],"frontend":["rite-build/reference/frontend-trigger.md"],"parallel":["rite-build/reference/parallel-batch.md"],"patterns":["devrites-lib/reference/standards/patterns.md"],"principles":["devrites-lib/reference/standards/principles.md"],"security":["devrites-lib/reference/standards/security.md"],"tdd":["rite-build/reference/tdd.md","devrites-lib/reference/standards/testing.md"],"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md","strategy.md"],"workspaceByRole":{"code-reviewer":["spec.md","plan.md","tasks.md","test-plan.md","architecture.md","decisions.md","state.md"],"doubt-reviewer":["spec.md","plan.md","tasks.md","state.md","decisions.md"],"slice-wright":["brief.md","spec.md","architecture.md","plan.md","tasks.md","test-plan.md","state.md","decisions.md","assumptions.md","questions.md"],"test-analyst":["spec.md","tasks.md","test-plan.md","state.md"]}} -->
+<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/agents.md","rite-build/reference/phase-contract.md","rite-build/reference/one-slice-cycle.md","rite-build/reference/wright-dispatch.md","rite-build/reference/checkpoint.md","rite-build/reference/spec-drift-guard.md","rite-build/reference/output.md","rite-build/reference/anti-patterns.md"],"rootOnly":["rite-build/reference/phase-contract.md","rite-build/reference/wright-dispatch.md","rite-build/reference/checkpoint.md","rite-build/reference/output.md","rite-build/reference/afk-discipline.md","rite-build/reference/checkpoint-protocol.md","rite-build/reference/parallel-batch.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/workflow-artifacts.md"],"triggers":{"afk":["rite-build/reference/afk-discipline.md","devrites-lib/reference/standards/afk-hitl.md","rite-build/reference/checkpoint-protocol.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"coding":["devrites-lib/reference/standards/coding-style.md"],"debug-recovery":["devrites-lib/reference/standards/debug-recovery.md"],"dod":["devrites-lib/reference/standards/definition-of-done.md"],"errors":["devrites-lib/reference/standards/error-handling.md"],"frontend":["rite-build/reference/frontend-trigger.md"],"parallel":["rite-build/reference/parallel-batch.md"],"patterns":["devrites-lib/reference/standards/patterns.md"],"principles":["devrites-lib/reference/standards/principles.md"],"security":["devrites-lib/reference/standards/security.md"],"tdd":["rite-build/reference/tdd.md","devrites-lib/reference/standards/testing.md"],"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md","strategy.md"],"workspaceByRole":{"code-reviewer":["spec.md","plan.md","tasks.md","test-plan.md","architecture.md","decisions.md","state.md"],"doubt-reviewer":["spec.md","plan.md","tasks.md","state.md","decisions.md"],"slice-wright":["brief.md","spec.md","architecture.md","plan.md","tasks.md","test-plan.md","state.md","decisions.md","assumptions.md","questions.md"],"test-analyst":["spec.md","tasks.md","test-plan.md","state.md"]}} -->
 > Read-set manifest: `devrites-engine context <slug> --phase build` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 

package/pack/generated/claude/skills/rite-build/reference/afk-discipline.md

@@ -9,7 +9,9 @@ contract for the sentinel schema, defaults, gate ceiling, and mutable-counter
 ownership. This file owns only Build's dispatch, charging, and red-path behavior.
 
 Rules: green before `built`; hard `max_slices` cap; gates before the action they
-control; irreversible work (destructive/auth/public API) always pauses.
+control; irreversible work (destructive/auth/public API) always pauses; a tick
+never ends with an open or sealed wave — wait for its returns or
+`dispatch abandon --reason`.
 
 ## Iteration cap
 

package/pack/generated/claude/skills/rite-build/reference/one-slice-cycle.md

@@ -21,8 +21,9 @@ DISPATCH  → hand the slice contract to devrites-slice-wright (fresh context).
 (DOUBT)   → orchestrator, on return: devrites-doubt each non-trivial decision the wright stood up
             — dispatch the initial read-only reviews of distinct decisions in parallel
             (independent claims, fresh contexts); wright fixes stay serial — writers share files
-PROVE     → root: required build/browser/E2E, then returned-diff/path review; fail-on-red
-            (red/gap → repair wright, then re-review/re-prove; do not commit yet)
+PROVE     → root, concurrent with the reviews on the same frozen candidate:
+            required build/browser/E2E, then returned-diff/path recheck; fail-on-red
+            (red/gap → repair wright, then re-review and re-prove; do not commit yet)
 RECORD    → orchestrator: after green verification, update state.md/evidence.md and
             upsert the authoritative candidate manifest from the actual scoped diff
 (CHECKPOINT) → only now, with review+proof green: local WIP(<slug>): <imperative summary>

package/pack/generated/claude/skills/rite-build/reference/output.md

@@ -9,7 +9,7 @@ Evidence: acceptance met; tests <cmd> → pass; browser <summary|n/a>; drift <no
 Open: <none|blockers|questions>
 Next: /rite-build
 Record: .devrites/work/<slug>/evidence.md
-↻ Hygiene: /clear between slices; /rite-handoff if away > a few hours
+↻ Hygiene: /clear between slices (none in `orient` `inflight_waves`); /rite-handoff if away > a few hours
 ```
 
 **All built:**

package/pack/generated/claude/skills/rite-build/reference/parallel-batch.md

@@ -94,13 +94,15 @@ Lease: `batch_id`, `created_at`, `base_sha`, `n`,
    <id>`; a malformed contract is dropped from the batch and recorded as a
    gap, not dispatched.
 2. Write lease; freeze `B=HEAD`; `parallel create` worktrees.
-3. Dispatch ≤10 wrights in parallel (cwd=worktree; allowlist; prove `HEAD==B`).
+3. Dispatch ≤10 wrights in parallel (cwd=worktree; allowlist; prove `HEAD==B`;
+   one `--slice` per sibling on the wave).
 4. Inspect each returned path list, cumulative diff from `B`, transfer identity,
    and required result fields against the immutable contract. Reject malformed,
    stale, or out-of-scope work. Apply
    [independent Build review](phase-contract.md#independent-build-review): first
-   full inventory, then bounded owning-role rechecks after repairs. Gap or
-   Critical/Important → `gap`; else approved proof → `green|red|gap`.
+   full inventory, then bounded owning-role rechecks after repairs. Run approved
+   proof in the same window as that review. Gap or Critical/Important → `gap`;
+   else proof → `green|red|gap`.
    Reviewer fan-out for a batch is itself batched under
    [`parallel-dispatch.md`](../../devrites-lib/reference/parallel-dispatch.md#scale-limits)
    (≈4 concurrent read-only reviewers, 8 only with disjoint paths), and `max_agents`