devrites 6.1.1 → 6.1.3

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

@@ -76,7 +76,8 @@ test changes.
    command, cwd, prerequisites, exit, and sanitized
    decisive output, plus the test selector, runner counts
    (collected/ran/passed/failed/skipped), and attempt number with first-attempt
-   outcome; output and exit come from one execution. Run relevant suite plus build/typecheck/lint. Recheck the
+   outcome; output and exit come from one execution. Run relevant suite plus build/typecheck/lint,
+   concurrently when they share no build directory, port, or lock. Recheck the
    candidate and require identical digest/no source mutation. Reject substituted
    commands, malformed manifests, zero-test/skipped/filtered behavioral claims,
    exit-status-only claims, status-masking forms, and source drift. A retry-only
@@ -109,7 +110,7 @@ test changes.
    described screenshots, console/network, interaction, target comparisons, and
    every required state. Material mismatch fails.
 7. **Independent validation.** Fresh read-only `devrites-proof-runner` and
-   `devrites-spec-reviewer` judge the same candidate/commands/evidence/acceptance map.
+   `devrites-spec-reviewer`, in one parallel wave, judge the same candidate/commands/evidence/acceptance map.
    Neither runs commands; reject missing/stale, invented-ID, label-only or self-attested reports.
 8. **Map proof.** Reconcile verdicts under [acceptance-proof.md](reference/acceptance-proof.md).
    Every criterion/scenario/interaction/key link needs discriminating evidence or a

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

@@ -79,7 +79,8 @@ Pull these via `Read` when the diff demands them:
    reviewer's brief without severity) and ends in `review.md` with its own label and
    action tag — never silently dropped. Hand each lane reviewer the
    `devrites-engine recall --paths <its touched paths>` pointers as prior context, not findings.
-2. **Review tests first:** do they prove the acceptance criteria? Missing,
+2. **Review tests first** while the step-3 cohort runs — launch it first; this
+   root pass needs none of its output: do they prove the acceptance criteria? Missing,
    weak, or wrong tests are the first findings.
    **Completion:** every acceptance criterion maps to a proven test or a labeled finding.
 3. **Review spec and code separately in parallel.** A change can pass
@@ -100,6 +101,10 @@ Pull these via `Read` when the diff demands them:
        (scope creep / drift), (c) criteria implemented incorrectly. Quote the spec
        line per finding. If the spec is missing or unreadable, report `Review gap:
        missing spec` and do not infer requirements from the diff."
+     - **Seal roles** → `devrites-test-analyst`, plus `devrites-doubt-reviewer` per
+       stood decision and `devrites-devex-reviewer` when triggered, join this cohort on
+       the same digest. Their findings join step 7's single correction, and Seal cites
+       their unchanged same-candidate accounts instead of re-dispatching them.
      - **Code-review axis** → `devrites-code-reviewer`: "Apply your full documented
        discipline (tests-first, correctness, readability, architecture, maintainability,
        standards) on the feature workspace + diff. Cite file:line; skip tooling-enforced

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

@@ -61,8 +61,8 @@ Follow [`reference/phase-contract.md`](reference/phase-contract.md)
 
 1. read workspace and final diff;
 2. recheck the canonical candidate/bindings and approved repository/CI proof;
-3. admit valid Spec/Code accounts; dispatch remaining required exact roles under
-   `../devrites-lib/reference/parallel-dispatch.md` on the same frozen candidate,
+3. admit every valid same-candidate Review account; dispatch remaining required exact roles under
+   `../devrites-lib/reference/parallel-dispatch.md` in one wave, proof-runner included, on the same frozen candidate,
    code review through its § Engineering lanes;
 4. reconcile their read-only verdicts against source and immutable evidence;
 5. draft GO/NO-GO `seal.md` with acceptance, tests, decisions, and seven roster accounts plus proof-runner and doubt-reviewer

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

@@ -13,12 +13,18 @@
    candidate check afterward and require the identical digest and no source
    mutation. Capture command, cwd, exit, decisive output, and identity.
    Missing/red/mismatched blocks; unavailable is `cannot_verify`, never pass.
+Steps 3–6 share one dispatch wave: launch every role they still need
+(proof-runner, test-analyst, doubt-reviewer, roster) together, admit valid
+same-candidate Review accounts instead, and do the root work of steps 4–6 while
+the wave runs.
+
 3. **Judge acceptance.** Dispatch exact `devrites-proof-runner` on immutable
    proof; admit valid same-candidate `devrites-spec-reviewer` evidence from Review
    or dispatch that exact reviewer. Reconcile every
    AC/REQ/scenario/key link by ID and meaning; missing/stale/self-attested/mismatched is NO-GO.
 4. **Judge tests.** Diff baseline/candidate tests for deletion, skip/focus,
-   tautology, or weakening; dispatch exact `devrites-test-analyst`. Missing or
+   tautology, or weakening; admit the same-candidate `devrites-test-analyst` account
+   from Review or dispatch that exact analyst. Missing or
    adverse account, or green tests not asserting mapped behavior, is Critical.
 5. **Resolve gates.** Open blocking/escalating/validating questions and drift
    block. Each stood decision needs a reconciled exact `devrites-doubt-reviewer` verdict.

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

@@ -5,7 +5,7 @@ argument-hint: "[slug] [--cross-model] [--full]"
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/parallel-dispatch.md","devrites-lib/reference/standards/gates.md","rite-vet/reference/review-axes.md","rite-vet/reference/artifacts.md","rite-vet/reference/depth.md","rite-vet/reference/eng-lenses.md","rite-vet/reference/anti-patterns.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"assumption-delta":["devrites-lib/reference/standards/assumption-checkpoints.md"],"cross-model":["rite-vet/reference/cross-model.md"],"devex":["devrites-lib/reference/standards/developer-experience.md"],"dod":["devrites-lib/reference/standards/definition-of-done.md"],"elicitation":["devrites-lib/reference/standards/elicitation.md"],"errors":["devrites-lib/reference/standards/error-handling.md"],"grammar":["devrites-lib/reference/standards/spec-grammar.md"],"one-shot":["devrites-lib/reference/standards/one-shot-actions.md"],"performance":["devrites-lib/reference/standards/performance.md"],"principles":["devrites-lib/reference/standards/principles.md"],"reslice":["devrites-lib/reference/standards/acceptance-preserving-reslice.md"],"testing":["devrites-lib/reference/standards/testing.md"],"workflow":["devrites-lib/reference/standards/development-workflow.md"],"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"],"yagni":["devrites-lib/reference/standards/patterns.md","devrites-lib/reference/standards/coding-style.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","strategy.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md"],"workspaceByRole":{"devex-reviewer":["spec.md","plan.md","tasks.md","decisions.md","state.md"],"plan-reviewer":["spec.md","plan.md","tasks.md","test-plan.md","decision-coverage.md","architecture.md","decisions.md","state.md"],"strategy-reviewer":["brief.md","spec.md","plan.md","decisions.md","decision-coverage.md","strategy.md","state.md"]}} -->
+<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/parallel-dispatch.md","devrites-lib/reference/standards/gates.md","rite-vet/reference/review-axes.md","rite-vet/reference/artifacts.md","rite-vet/reference/depth.md","rite-vet/reference/eng-lenses.md","rite-vet/reference/anti-patterns.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"assumption-delta":["devrites-lib/reference/standards/assumption-checkpoints.md"],"cross-model":["rite-vet/reference/cross-model.md"],"devex":["devrites-lib/reference/standards/developer-experience.md"],"dod":["devrites-lib/reference/standards/definition-of-done.md"],"elicitation":["devrites-lib/reference/standards/elicitation.md"],"errors":["devrites-lib/reference/standards/error-handling.md"],"grammar":["devrites-lib/reference/standards/spec-grammar.md"],"one-shot":["devrites-lib/reference/standards/one-shot-actions.md"],"performance":["devrites-lib/reference/standards/performance.md"],"principles":["devrites-lib/reference/standards/principles.md"],"reslice":["devrites-lib/reference/standards/acceptance-preserving-reslice.md"],"testing":["devrites-lib/reference/standards/testing.md"],"workflow":["devrites-lib/reference/standards/development-workflow.md"],"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"],"yagni":["devrites-lib/reference/standards/patterns.md","devrites-lib/reference/standards/coding-style.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","strategy.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md"],"rootOnly":["devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/elicitation.md"],"workspaceByRole":{"doubt-reviewer":["spec.md","architecture.md","plan.md","tasks.md","test-plan.md","decisions.md","state.md"],"devex-reviewer":["spec.md","plan.md","tasks.md","decisions.md","state.md"],"plan-reviewer":["spec.md","plan.md","tasks.md","test-plan.md","decision-coverage.md","architecture.md","decisions.md","state.md"],"strategy-reviewer":["brief.md","spec.md","plan.md","decisions.md","decision-coverage.md","strategy.md","state.md"]}} -->
 > Read-set manifest: `devrites-engine context <slug> --phase vet` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
@@ -83,7 +83,9 @@ plan declares a root-authored executable workflow file, read
    Temper — in
    parallel under `../devrites-lib/reference/parallel-dispatch.md`; they are
    independent read-only passes on one frozen candidate. Missing
-   required account blocks.
+   required account blocks. Run root steps 2–4, including step 3's preflight
+   commands, on the same frozen candidate while the wave is out; reconcile the
+   accounts when they return.
 1b. **Recovery recheck.** Require valid return cursor, accepted prior finding,
    exact fingerprint/reproduction, repaired candidate identity, changed
    paths/criteria, affected drift/evidence, and the recorded delta self-check.
@@ -106,8 +108,8 @@ plan declares a root-authored executable workflow file, read
    marked as a refinement of an already-pinned clause; the recheck may re-raise
    it only by naming a concrete failure path the declaration omits. A
    `new_failure_mode` finding is never residual-eligible. A fold whose
-   findings are all Suggestion-or-lower rechecks mechanically at the
-   materialization gate — anchors applied, mirrors consistent, invariants
+   findings are all `mechanism` kind or Suggestion-or-lower rechecks mechanically at the
+   materialization gate — anchors applied (a clean `state apply-bundle`), mirrors consistent, invariants
    pass — without a dispatched reviewer; sub-Important findings already
    cannot keep recovery open. Reconcile
    shared artifact/readiness gates, then enter step 8 or the next repair.
@@ -140,7 +142,9 @@ plan declares a root-authored executable workflow file, read
    ownership. The plan's `Shared contract proof` names one reused boundary
    artifact plus two consuming tests for every changed API/event/schema/provider-
    consumer seam, or an explicit no-impact statement. Missing, one-sided,
-   duplicated-contract, vague, or non-consuming proof fails closed.
+   duplicated-contract, vague, or non-consuming proof fails closed. Each slice
+   names a fast writer-safe check its wright can run; proof reachable only through
+   root-owned full gates is a `mechanism` finding.
 
    Technical gaps are `NEEDS REPLAN` and Plan repair — each finding marks
    itself `new_failure_mode` or names the already-pinned clause/fingerprint

package/pack/.claude/skills/rite-vet/reference/artifacts.md

@@ -101,6 +101,14 @@ From /rite-vet on <iso>. Runner + conventions: <detected framework + command>.
 Link any disposable parser fixture. Preflight values are planning evidence, not post-build proof;
 Prove recaptures the observed command, candidate identity, and result.
 
+## Feature gates
+| Gate | Command | Cwd | Expected |
+|---|---|---|---|
+| <full suite / workspace lint / audit> | <exact command> | <path> | <exit/output> |
+
+Whole-repository rows only: Build runs them per landing
+([tiers](../../rite-build/reference/phase-contract.md#proof-tiers)), Prove on the final candidate.
+
 Commands in this durable artifact are portable repository commands: no RTK or local shell
 aliases, user-specific absolute paths, or temporary proof trees. Evidence records
 the command actually executed.

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

@@ -28,7 +28,7 @@ Before implementation review, check for work beyond the settled spec.
    (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. An `ADVISORY size:`
-   slice without `Size rationale:` is a non-blocking Suggestion to split it.
+   or `hub:` line without its rationale is a non-blocking Suggestion to split or seam 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.

package/pack/generated/claude/agents/devrites-plan-drafter.md

@@ -21,7 +21,8 @@ seams supplied by the orchestrator.
   planning artifacts while preserving settled intent.
 
 Reuse existing seams and dependencies before proposing new ones. Build vertical
-slices in dependency order. Map every REQ and AC to a slice and executable proof,
+slices in dependency order; put a hub file's shared edit in one seam slice
+([slicing.md](../skills/rite-plan/reference/slicing.md#slice-independence)). Map every REQ and AC to a slice and executable proof,
 name rollback and failure paths; keep acceptance-changing proposals separate. Durable
 proof commands must be portable repository commands, never host-local wrappers,
 user-specific absolute paths, or temporary proof trees.
@@ -75,10 +76,13 @@ Return this result:
 
 ```yaml
 mode: define | repair
+base_hashes: {}  # <path>: sha256 of the bytes you read, for every replace/patch target
 candidate_files:
   - path: <requested canonical target>
     operation: create | replace | patch
-    content: <complete candidate or exact bounded delta>
+    content: <complete file; create/replace only>
+    hunks: [] # patch only: {id, old_text, new_text}; old_text byte-exact, unique in the pinned file
+retired_ids: [] # tracked IDs (AC/REQ/HZN/SLICE/DEC/...) the delta removes on purpose
 acceptance_map: []
 dependency_order: []
 technical_decisions: []
@@ -88,7 +92,13 @@ applicability_disposition: []
 self_attack_exposures: []
 ```
 
-The root validates the cross-file bundle and persists accepted content.
+The root saves the bundle as JSON and applies it with `devrites-engine state
+apply-bundle <slug> <bundle.json>`, which refuses a stale pin, a missing,
+duplicate, or overlapping `old_text`, an unlisted vanished ID, a new task-graph
+problem, new budget overshoot, or a new dated delta section, and writes nothing on refusal. Pin each
+`base_hashes` entry with `shasum -a 256` (or `sha256sum`) on the exact file you
+read, and prefer short anchored hunks to whole-file `replace`. Patch the owning
+clause in place; never add a dated delta section beside superseded text.
 
 ## Tools / read-write mode
 

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

@@ -103,7 +103,11 @@ unclear boundary is underspecified: return `Escalation` without proceeding.
      that source in the result. Never invent an API.
    - **No process residue.** Do not put `SLICE-###`, slice numbers, or "this slice"
      in product source, tests, comments, or filenames.
-4. **VERIFY (fail-on-red).** Run writer-safe tests/types/lint. Report required
+4. **VERIFY (fail-on-red).** Run writer-safe tests/types/lint: `Tests/proof` plus
+   tests of changed code; `## Feature gates` rows are root-owned. Writer-safe means
+   local and non-consumptive — syntax/type/lint, unit and self-check suites, and a
+   narrow smoke of the changed path — never only a syntax check; contract text
+   cannot strip it. Report required
    build/browser/E2E as `not-run` (root-owned, artifact-producing gates), and only
    when the exact command, cwd, and prerequisites already appear in the unchanged
    vetted `test-plan.md`; never synthesize or rewrite a root command. Root runs

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

@@ -4,7 +4,9 @@ Host dispatch; DevRites governs.
 
 ## Roster
 
-Review: Spec/Code plus triggered frontend/security/performance; Seal: all applicable roles.
+Review: Spec/Code, triggered frontend/security/performance, and the seal roles that can
+judge the frozen digest (test-analyst, doubt, devex); Seal: all applicable roles, citing
+same-candidate Review accounts.
 
 | Reviewer | Fires | Trigger |
 |---|---|---|
@@ -74,8 +76,10 @@ If the candidate diff has no matching surfaces, record
    and dedupe by evidence/root cause. Account for all seven (and, in `seal.md`, `devrites-proof-runner` and `devrites-doubt-reviewer`) in
    `review.md`/`seal.md`, each [engineering lane](#engineering-lanes) separately:
    `Outcome:` plus admitted account, or
-   `Not-applicable: <inspected-scope reason>`. Spec/Code may cite valid unchanged
-   `review.md` under [evidence validity](candidate-integrity.md#evidence-validity); persist no dispatch telemetry.
+   `Not-applicable: <inspected-scope reason>`. Seal cites, rather than re-dispatches, any
+   role `review.md` admitted on the identical candidate under
+   [evidence validity](candidate-integrity.md#evidence-validity); a changed digest or newly
+   triggered surface needs a fresh account. Persist no dispatch telemetry.
 7. Missing profile, null/failure, or malformed output is a `gap`; never
    infer approval or substitute inline review.
 
@@ -127,7 +131,8 @@ child's handle, path/resource ownership and capacity reservation until the
 native host confirms a terminal state and returned work has been reconciled.
 Query or wait on that handle; do not replace the child, release its slot, or
 reuse its resources while it may still run. If terminal state cannot be
-established, record a gap and retain ownership. A result classification alone
+established, record a gap and retain ownership; for a child launched by an earlier
+session, the claim proof below settles it. A result classification alone
 does not prove host termination.
 
 On resume (compaction or a new session), run `devrites-engine dispatch <slug>
@@ -135,7 +140,11 @@ status`, `parallel status`, and `claim list --all` before any dispatch. A read-o
 wave whose handles this session cannot query: `abandon` it, record each unreturned
 role `gap`, and re-dispatch fresh on the current digest; its late returns are
 `stale`. A writer keeps its claim and lease — no relaunch on those paths until the
-claim is released or its holder is proven terminal. A wright that never returned an
+claim is released or its holder is proven terminal. For an unqueryable writer,
+`claim list --all` showing its claim `released` or `dead` (the engine proved the
+holding session exited on this host) is that proof: `abandon` the wave, record the
+role `gap`, claim the paths, and re-dispatch without waiting on the launching
+session. `live` or `expired` stays held. A wright that never returned an
 admitted result leaves unadmitted bytes: task-path changes since its pre-dispatch
 `git diff --name-only` baseline are never cited as built nor discarded, and are
 named in the re-dispatch contract; changes outside task paths stop for the human

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

@@ -223,8 +223,9 @@ project/decision docs, and authoritative dependency sources; make and record rev
 implementation/test choices. Ask only about product, scope, acceptance, architecture policy,
 irreversible risk, or human-only access/action.
 
-Objective test/build/tool failure runs bounded `devrites-debug-recovery`; fix it or record a
-technical blocker. Never ask permission for another attempt, test, parser repair, or probe.
+Objective test/build/tool failure runs bounded `devrites-debug-recovery`; fix it, or escalate and
+park it under the [retry contract](#retry-cap-no-progress-loops-and-self-resolve). Never ask
+permission for another attempt, test, parser repair, or probe.
 Close decisions at the earliest informed phase: product in spec, coverage in clarify,
 scope/risk in temper, architecture/dependencies in define, and proof/toolchain in vet. Build
 keeps only unavailable-pre-code or mandatory action-time checkpoints.
@@ -375,6 +376,14 @@ access, safety and irreversible-action boundaries independently stop work.
   closes every deferred row with a labeled verdict; Seal blocks on any without one.
   **Failing case:** round 4 finds three Important items on clauses untouched since
   round 1 and dispatches another repair.
+- **Recovery findings need a discriminator; recovery scope stays frozen.** While a
+  fingerprint is in recovery, a new Important finding keeps it open or opens another
+  only with an executed reproduction or a quoted AC/INV/PROH/accepted-DEC line whose
+  observable outcome fails; root turns it into a control the next wright must pass.
+  A static counterexample against plan-invented hardening goes to the Review trail or
+  `## Deferred findings` (Review gives it a verdict; Seal blocks without one). A
+  Critical with a concrete failure path always opens a fingerprint. A correction adds
+  no proof site or mechanism its fingerprint's closure does not need. No reviewer is skipped.
 - **Separate consumptive authority from recovery.** Spent one-shot authorization
   blocks another execution, not offline recovery. Retained evidence starts caller-owned
   diagnosis/correction immediately; the next consumptive execution needs fresh authority.
@@ -388,13 +397,19 @@ access, safety and irreversible-action boundaries independently stop work.
   the fingerprint's current *strategy*, not the work. Record that strategy and its
   attempts under `## Dead ends`, then the controlling caller escalates inline in the
   same invocation: re-diagnose from the reproduction and dead ends, take the first
-  class below that still has an untried strategy, run `/rite-plan repair` plus
-  narrow Vet for it, and resume with a fresh three-attempt budget. Classes, in order:
-  (1) **shared root cause**: fix the owner every failing path routes through and
-  enforce it across all callers instead of another local guard; (2) **boundary
-  redesign**: acceptance-preserving reslice or redesign of the failing seam;
-  (3) **diagnostic amplification**: add discriminating probes or fixtures, then
-  correct from that evidence. A recorded strategy, or a rewording of one, never
+  class below that still has an untried strategy, and resume with a fresh
+  three-attempt budget. Re-plan only when the strategy must change a planning
+  input (writer allowlist, interface or contract, slice topology, or a
+  `test-plan.md` proof row): run `/rite-plan repair` plus narrow Vet for it. A
+  strategy that fits the vetted plan, with `devrites-engine check readiness <slug>`
+  still passing, goes straight to the wright with the dead ends in its contract;
+  Build's review and proof still gate it. Classes, in order, cheapest evidence
+  before costliest change: (1) **shared root cause**: fix the owner every failing
+  path routes through and enforce it across all callers instead of another local
+  guard; (2) **diagnostic amplification**: add discriminating probes or fixtures,
+  then correct from that evidence (last for a consumptive action, whose attempt
+  needs fresh authorization); (3) **boundary redesign**: acceptance-preserving
+  reslice or redesign of the failing seam, built on that evidence. A recorded strategy, or a rewording of one, never
   repeats. Escalation never weakens tests, validators or acceptance. Each
   fingerprint gets at most three escalations per activation; record each in
   `drift.md` with its class and strategy.

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

@@ -62,7 +62,9 @@ a human plus an agent) can share one working tree. Before a same-tree writer
 starts, it records an advisory claim — `devrites-engine claim add --session
 <id> <paths>` — retains the returned `<claim-id>`, then checks the same paths
 with `devrites-engine claim check --session <id> <paths>`; a held claim from a
-live foreign session is a stop-and-report, not a merge-later problem. On every
+live foreign session is never merged later or overridden. Unattended, skip only
+work that needs those paths, run independent work, and re-check `claim list --all`
+before stopping; stop and report the holder only when nothing independent remains. On every
 host-confirmed terminal path after `add` ([unknown outcomes keep it](../parallel-dispatch.md#cancellation-and-terminal-reconciliation)) — return,
 rejected result, stop, or a launch refused with no handle — run
 `devrites-engine claim release --session <id> --id <claim-id>`. Claims expire
@@ -73,7 +75,9 @@ Claims cover product paths only; root-authored `.devrites/**` files use
 Expiry is not proof the holder stopped: size `claim add --ttl <minutes>` to the
 expected write (engine max 240) and re-add before it lapses; before writing, also
 read `claim list --all` — a foreign `expired` claim on overlapping paths whose
-session is not proven terminal counts as held (stop and report). **Failing case:**
+session is not proven terminal counts as held (stop and report). `dead` (engine-proven
+exited holder) or `released` is terminal: reconcile per
+[§ Cancellation](../parallel-dispatch.md#cancellation-and-terminal-reconciliation). **Failing case:**
 session B's `claim check` passes at minute 35 over session A's still-running wright.
 
 ## Independence

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

@@ -163,6 +163,9 @@ A skill that stops without doing this leaves the workspace incomplete.
 
 Long contexts degrade reasoning quality. Act on context at **50-70% used, not 95%**.
 
+Read the engine `context` bundle once per phase instead of re-reading the files it
+contains; after compaction re-read the bundle, not its sources.
+
 Every rite names the single resume command on its action line; a `↻ Hygiene:` footer
 advises `/clear`, `/compact`, or `/rite-handoff` and never a competing command. Full phase-by-phase guidance:
 [`context-hygiene.md`](context-hygiene.md).

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

@@ -124,6 +124,9 @@ an error because the runner can never execute it.
   (an invariant the output must always satisfy) over example (one concrete
   input/output case). An example-shaped oracle on a property-shaped outcome is
   a weak gate — reviewers flag it even when it passes.
+- One CHECK, one oracle: never chain another artifact's self-test before the
+  AC's oracle with `&&` — give the self-test its own gate, so a red self-test
+  never hides the AC's own result.
 - When an outcome becomes impossible, `gates abandon` it and route the
   handoff — never delete the row to make the ledger pass.
 - The gate set is the coverage denominator: it never shrinks to reach

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

@@ -250,6 +250,13 @@ Dismiss an irrelevant case with a reason; silently omitting an applicable case i
 - A flaky test is a broken test. Isolate and fix it immediately; don't paper over it with
   retries or `sleep`. **Failing case:** a known-flaky test is left with retries so the
   suite is paper-green at Prove/Seal → NO-GO.
+- **A diagnostic rerun is allowed, never proof.** Rerun a timing-shaped failure on
+  the unchanged candidate to classify it flaky or deterministic before a repair;
+  record it as diagnostic, never as a pass.
+- **Attributable RED.** A negative control or mutant counts RED only on a positive
+  marker from the targeted assertion; a setup, construction, or observation failure
+  is never credited as RED. Prove the classifier with an injected setup failure
+  that must stay uncredited.
 - **A retry-only pass is `flaky`, never green.** A pass earned by rerun on an unchanged
   candidate digest (no admitted correction between attempts), or by a runner retry
   setting, is `flaky`: record every attempt with the first attempt's outcome. It never

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

@@ -326,12 +326,16 @@ Epoch starts 1. `FAILED` records preimages/cleanup/epoch/fingerprint/reason/
 boundary/route/no-progress count. Resolved fingerprints close; a different
 invariant gets a distinct fingerprint. Handoff death resumes its retry epoch with
 prior rows immutable. `WA-OP-011/012` enforce independent fingerprint/epoch caps
-and terminal source cleanup. Exhaustion records:
+and terminal source cleanup. Exhaustion closes this admission, not the work:
+the controlling caller escalates it under the
+[retry contract](afk-hitl.md#retry-cap-no-progress-loops-and-self-resolve)
+through `PLAN_VET_REPAIR`, and a re-vetted changed design re-admits under a new
+identity with fresh epochs. A fully escalated fingerprint parks. Exhaustion records:
 
 ```text
-status=blocked
+status=running
 exhaustion_cause=<same-fingerprint-count|total-epoch-limit>
-next_action=none — technical recovery exhausted; requires new evidence or changed failure conditions
+next_action=/rite-plan repair <slug> — escalate exhausted workflow attempt
 ```
 
 The journal, evidence section, and observer retain that cause; epoch exhaustion
@@ -343,7 +347,7 @@ Precedence: busy owner; safety/access/approval gate; completed historical; activ
 journal; `CLEANED`; missing/stale authority; stale writer evidence; current
 admission. `PROVED|CLEANING` resumes cleanup; install-through-`PROVING`, rollback,
 or failure cleanup routes offline; retryable `FAILED` routes correction/retry;
-`EXHAUSTED` blocks; `PREPARING|PREPARED` resumes only with current authority.
+`EXHAUSTED` escalates; `PREPARING|PREPARED` resumes only with current authority.
 There is no actor-history migration or backfill.
 
 |Route|Owner|Exact action|Durable state/status/next action|Cursor/output|
@@ -356,7 +360,7 @@ There is no actor-history migration or backfill.
 | `VERIFY_EXISTING`|controlling root|verify `CLEANED`, targets, proof, and product separation; do not reinstall|restore saved return phase/action|no retry/slice/action budget|
 | `NO_BACKFILL`|controlling root|no action|completed state unchanged|no new output|
 | `WAIT_ACTIVE_OWNER`|non-owner|no write; stop invocation|shared state unchanged|fixed owner-busy diagnostic|
-| `BLOCKED_EXHAUSTED`|controlling root|no attempt 4|blocked with exact exhausted next action|fixed exhausted diagnostic|
+| `BLOCKED_EXHAUSTED`|controlling root|no attempt 4 on this admission; escalate through `PLAN_VET_REPAIR` or park per retry contract|`status=running`, exact exhausted `next_action`; parked keeps the parked-recovery action|fixed exhausted diagnostic; no intermediate reply|
 | `BLOCKED_GATE`|controlling root|follow existing safety/access/approval gate|gate-owned state|gate output; never reinterpret as retry|
 
 |Scenario ID|Trigger|Exact route / action|Durable consequence|Forbidden behavior|
@@ -422,7 +426,7 @@ pairs remain injective for actionable seams.
 | `devrites-debug-recovery/SKILL.md`|durable active failure or ambiguous admitted state|`OFFLINE_RECOVERY`; correct offline, re-preflight, narrow Vet, retry only under cap|saved caller or exact Plan/Vet route|
 | `rite-autocomplete/SKILL.md`|lifecycle cursor encounters admitted set or resumable journal|invoke classifier; execute returned route internally|saved phase/action; zero intermediate reply|
 | `rite-autocomplete/reference/loop.md`|loop tick sees Workflow Artifact trigger/state|invoke classifier once under owner lock; no actor-history migration|same loop cursor; no budget charge for verify/rerun|
-| `rite-autocomplete/reference/stop-conditions.md`|classifier returns owner-busy, exhausted, or existing hard gate|stop on exact `WAIT_ACTIVE_OWNER`, `BLOCKED_EXHAUSTED`, or `BLOCKED_GATE` result|unchanged cursor plus fixed route-owned output|
+| `rite-autocomplete/reference/stop-conditions.md`|classifier returns owner-busy, exhausted, or existing hard gate|escalate `BLOCKED_EXHAUSTED`; on `WAIT_ACTIVE_OWNER` run independent work and recheck; stop on exact `BLOCKED_GATE` result|unchanged cursor plus fixed route-owned output|
 | `rite-build/SKILL.md`|Vet-ready admitted bytes require root authorship outside product wright|`ROOT_TRANSACTION`; root writes only admitted `.devrites/**` targets|saved Build slice cursor; wright product allowlist unchanged|
 | `rite-build/reference/phase-contract.md`|Build gate enters or resumes transaction|invoke canonical operation table; reconcile exact result|same slice/checkpoint cursor or Plan/Vet route|
 | `rite-prove/SKILL.md`|Prove consumes installed Workflow Artifact or `CLEANED` rerun|`VERIFY_EXISTING` or admitted proof path ending `PROVE_AND_RETURN`|saved Prove cursor; stop before real action|

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

@@ -237,7 +237,7 @@ slices; use `none` when they do not apply. Complexity above 3 triggers reslicing
 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.
+the inseparable capability; `ADVISORY hub:` takes a seam slice or `Serial rationale:`.
 
 ## Read next by phase
 

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

@@ -108,8 +108,8 @@ executable controller/harness/bundle bytes or a missing writer, read
    `/rite-review` → `/rite-seal`. Read and execute each skill; durable files, not
    chat, carry state. Apply the mutable post-vet budget before first Build.
    Build runs the largest eligible path-disjoint batch (cap: this invocation's
-   `--parallel N`, else sentinel `max_parallel`, else 10) and recomputes after
-   every completed round until no pending slice remains; a one-slice round is serial for that round only, then
+   `--parallel N`, else sentinel `max_parallel`, else 10) and refills a slot
+   per landing until no pending slice remains; a one-slice round is serial for that round only, then
    selection runs again (host isolation still forces serial when concurrent writers
    cannot be separated). When `--parallel N`
    is present, pass it into `/rite-build` and do not consult leftover sentinel

package/pack/generated/claude/skills/rite-autocomplete/reference/loop.md

@@ -67,7 +67,7 @@ Workspace files carry state; chat does not. Read and execute each phase skill:
 | 3 | `/rite-temper` | harden or reduce; `expand` and extra acceptance stop for a human; irreversible risk still pauses |
 | 4 | `/rite-define` | approved plan/tasks/traceability |
 | 5 | `/rite-vet` | every plan; derive mutable budget after READY |
-| 6 | `/rite-build` batch loop | largest eligible path-disjoint set (cap: this invocation's `--parallel N`, else sentinel `max_parallel`, else 10; one-slice round when <2 eligible); recompute after each round; charge once per green built slice |
+| 6 | `/rite-build` batch loop | largest eligible path-disjoint set (cap: this invocation's `--parallel N`, else sentinel `max_parallel`, else 10; one-slice round when <2 eligible); refill per landing; charge once per landed slice |
 | 7 | `/rite-prove` | all slices built; approved proof; recovery on red |
 | 8 | `/rite-polish` | re-prove after code edits |
 | 9 | `/rite-review` | in-scope correction then fresh proof |

package/pack/generated/claude/skills/rite-autocomplete/reference/stop-conditions.md

@@ -38,7 +38,7 @@ Agent-owned backtracking is not a stop condition while the exact causal
 fingerprint has budget. Invoke the earlier phase, affected Vet, remediation, and
 proof; then resume the origin. Three no-progress corrections of that exact
 fingerprint spend only its current strategy: escalate to the next correction
-class inline (shared root cause, boundary redesign, diagnostic amplification)
+class inline (shared root cause, diagnostic amplification, boundary redesign)
 with a fresh budget, never asking permission. After three escalations in this
 activation the fingerprint parks; finish all independent work, then stop once.
 Preserve reproduction, attempts, and dead ends; never offer `/rite-plan unblock`
@@ -58,7 +58,7 @@ amplification Plan repair and narrow Vet inline, then pause for fresh GO before
 one evidence-acquisition attempt. Without a safe seam, escalate to the next
 class or park; only a real human/risk/scope gate stops for a human.
 
-<!-- workflow-artifact-adapter: {"module":"devrites-lib/reference/standards/workflow-artifacts.md","entry":"classifier returns owner-busy, exhausted, or existing hard gate","action":"stop on exact WAIT_ACTIVE_OWNER, BLOCKED_EXHAUSTED, or BLOCKED_GATE result","return":"unchanged cursor plus fixed route-owned output"} -->
+<!-- workflow-artifact-adapter: {"module":"devrites-lib/reference/standards/workflow-artifacts.md","entry":"classifier returns owner-busy, exhausted, or existing hard gate","action":"escalate BLOCKED_EXHAUSTED; on WAIT_ACTIVE_OWNER run independent work and recheck; stop on exact BLOCKED_GATE result","return":"unchanged cursor plus fixed route-owned output"} -->
 ## Other stop classes
 
 - **Gate severity:** escalating always stops. Blocking with a ranked recommended
@@ -85,6 +85,10 @@ class or park; only a real human/risk/scope gate stops for a human.
   pre-existing remaining value, explicit flag, sentinel cap, or post-vet pending count
   does not stop. Zero with no pending slices is normal completion.
   Malformed flag stops before any write.
+- **Foreign writer:** a `live`/`expired` claim or `WAIT_ACTIVE_OWNER` held by
+  another session blocks only work on those paths; run independent work, re-check,
+  and stop only when nothing independent remains. `released`/`dead` claims are
+  reconciled per [§ Cancellation](../../devrites-lib/reference/parallel-dispatch.md#cancellation-and-terminal-reconciliation).
 - **Resource envelope:** overlapping run or missing AFK after arm still stops.
   Do not stop on `--max-slices`, `max_agents`, `max_minutes`, or `max_review_queue`.
 - **Confidence:** intent still cannot become testable acceptance after interview.

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

@@ -75,15 +75,15 @@ Wright applies anti-slop; root verifies returns and never patches source. Refuse
 
 Omitted/`1` ≡ serial; `2`–`10` is a **cap** — the root runs the largest eligible
 path-disjoint set it can start now (`N_eff`), takes fewer when the cap cannot be
-filled, and recomputes after every completed round (serial slice or parallel
-integrate) until no pending slice remains
+filled, and refills a slot per landing (serial slice or one sibling) until
+no pending slice remains
 ([`parallel-batch.md` § Dynamic selection](reference/parallel-batch.md#dynamic-selection-and-re-batching)).
-Unattended runs (`/rite-autocomplete`, `.devrites/AFK` `max_parallel`) repeat batches
-inside the same run; HITL stops after each batch. This invocation's `--parallel N`
+Unattended runs (`/rite-autocomplete`, `.devrites/AFK` `max_parallel`) refill
+inside the same run; HITL stops after each landing. This invocation's `--parallel N`
 is the cap: leftover sentinel `max_parallel` is not consulted. Autocomplete with
 that flag also writes or replaces only `max_parallel: N`. Non-integer/`N≤0`/`N>10` hard refuse.
-All-green (independent review + proof) then integrate as one local `WIP(<slug>):`
-commit per sibling onto the current control branch (never pushed). Do not
+Each sibling lands alone when its review + proof are green (`integrate --slice`):
+one local `WIP(<slug>):` commit onto the control branch (never pushed). Do not
 integrate a sibling because the wright returned. A red/gap sibling gets a bounded repair
 round in its own worktree — never rebuilt from scratch while budget remains.
 Post-writer inventory and affected rechecks follow `phase-contract.md` § Independent
@@ -94,7 +94,7 @@ a human `Fix`. Exhausted repair blocks and preserves everything;
 `cleanup --force` salvages slice branches before removing worktrees —
 human-gated to abandon a batch, orchestrator-emitted only as the salvage
 step of an automatic frozen-lease re-batch.
-AFK charges after integrate only. Running lease blocks another
+AFK charges per landed sibling only. Running lease blocks another
 `/rite-build`. Details: `parallel-batch.md`.
 
 ## Execute and reply

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

@@ -44,8 +44,8 @@ The controlling root owns the cap:
    before the next dispatch.
    - **Serial:** charge when fail-on-red is green and the built record is written
      (same rewrite as step 2).
-   - **Parallel `--parallel`:** charge only after **successful serial integrate**
-     — once per integrated green sibling. Abort / integrate-failed → charge **0**.
+   - **Parallel `--parallel`:** charge only after **successful integrate**
+     — once per landed green sibling. Abort / integrate-failed → charge **0**.
      Do not charge on worktree-green before integrate. See
      [`parallel-batch.md`](parallel-batch.md).
 

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

@@ -18,7 +18,7 @@ the orchestrator pauses for approval before landing it.
   and fail-on-red proof are green, with no open Critical/Important and no repair
   wright still in flight. Serial: git recipe below (skip empty index) or isolated
   FF of a matching `transfer_commit`. Parallel: `devrites-engine parallel
-  integrate --apply-to-control` (no second control `git commit`).
+  integrate --slice <id> --apply-to-control` (no second control `git commit`).
 - **Do not:** when a wright returns; before review/proof; with red/gap findings;
   fast-forward an isolated transfer onto control before those checks.
 

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

@@ -22,13 +22,14 @@ DISPATCH  → hand the slice contract to devrites-slice-wright (fresh context).
             — dispatch the initial read-only reviews of distinct decisions in parallel
             (independent claims, fresh contexts); wright fixes stay serial — writers share files
 PROVE     → root, concurrent with the reviews on the same frozen candidate:
-            required build/browser/E2E, then returned-diff/path recheck; fail-on-red
+            required build/browser/E2E (narrow self-check/smoke first, full gate only
+            after it is green, long runs in the background), 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>
             on the control branch (no slice id) → checkpoint.md
-NEXT      → HITL root reports and stops. AFK with parallel cap>1: return to parallel-batch selection and run the new N_eff; otherwise repeat under afk-discipline.md
+NEXT      → HITL root reports and stops. AFK with parallel cap>1: return to parallel-batch selection to refill; otherwise repeat under afk-discipline.md
 ```
 
 ## Why the boundary matters