devrites 6.0.4 → 6.1.1

package/pack/.claude/skills/devrites-prose-craft/SKILL.md

@@ -4,7 +4,7 @@ description: Rewrite prose to remove AI tells while preserving meaning and voice
 user-invocable: false
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/prose-style.md"],"triggers":{"word-choice":["devrites-prose-craft/reference/banned-phrases.md"],"structure":["devrites-prose-craft/reference/structures.md"],"examples":["devrites-prose-craft/reference/examples.md"]}} -->
-> Read-set manifest: `devrites-engine context [slug] --skill devrites-prose-craft` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
+> Read-set manifest: `devrites-engine context <slug> --skill devrites-prose-craft` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 # devrites-prose-craft: prose that reads human
 

package/pack/.claude/skills/devrites-source-driven/SKILL.md

@@ -4,7 +4,7 @@ description: Verify uncertain framework or library behavior in installed source
 user-invocable: false
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/tooling.md"],"triggers":{"agents":["devrites-lib/reference/standards/agents.md"]},"workspace":["state.md","spec.md","plan.md","decisions.md","evidence.md","references.md"],"workspaceByRole":{"evidence-scout":["state.md","spec.md","plan.md","references.md"]}} -->
-> Read-set manifest: `devrites-engine context [slug] --skill devrites-source-driven` bundles every file named below into one deduplicated read.
+> Read-set manifest: `devrites-engine context <slug> --skill devrites-source-driven` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read.
 
 # devrites-source-driven: verify, don't guess
 

package/pack/.claude/skills/devrites-ux-shape/SKILL.md

@@ -4,7 +4,7 @@ description: Shape UX/UI direction, states, and interactions before code. Use fo
 user-invocable: false
 ---
 <!-- loads: {"always":["devrites-ux-shape/reference/brief-template.md","devrites-ux-shape/reference/visual-direction-probe.md","rite-build/reference/frontend-trigger.md","devrites-frontend-craft/reference/design-references.md","devrites-frontend-craft/reference/quality-standards.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"]}} -->
-> Read-set manifest: `devrites-engine context [slug] --skill devrites-ux-shape` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
+> Read-set manifest: `devrites-engine context <slug> --skill devrites-ux-shape` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 # devrites-ux-shape: plan the UX/UI before code
 

package/pack/.claude/skills/overhaul/references/orchestration.md

@@ -277,10 +277,14 @@ correctness gate.
 ## Admission tool
 
 `devrites-engine overhaul admit receipt <run> <receipt.json> [--observed <paths.txt>]` checks one
-receipt against its dispatch packet: run, role, lane and snapshot match; timestamps
+receipt against its dispatch packet: the file is the attempt's own
+`<run>/receipts/<run_id>__<task_id>__<attempt_id>__<role>.json` (not a copy elsewhere
+or a symlink, and the attempt's recorded `receipt` when it has one); run, role, lane
+and snapshot match; timestamps
 and an allowed `outcome` are present; `no-findings` names inspected ranges; a writer's
 claimed paths stay inside its task contract and equal the observed paths.
 `devrites-engine overhaul admit anchor <tree> <proposals.json>` checks that every quoted location in
 `{"findings": [...]}` matches its file lines under the reviewed tree. It never edits
 canonical records; record its verdict in a staged generation. Exit codes: 0
-admissible or anchored, 1 reject, 2 usage or I/O error, 3 duplicate or late receipt.
+admissible or anchored, 1 reject, 2 usage or I/O error (including an extra or
+misspelled argument), 3 duplicate or late receipt.

package/pack/.claude/skills/overhaul/references/records.md

@@ -123,14 +123,19 @@ verifier attempt, repository-relative locations (external ones are labels, never
 host paths); `revisions.plan.file` equal to `revisions/plan-r<rev>.json`, required
 once approvals or writers exist; plan digest pins; known, acyclic dependencies;
 allowed paths that are exact files inside the repository (no `*` or `?`, no
-directories, no `.git`, no symlink or traversal escape); a separate verifier role;
+directories, no `.git` component or run-area path in any letter case or through a
+symlink, no symlink or traversal escape); a separate verifier role;
 approval and `accept-degradation` events with quote and trusted channel, approvals
 matching the plan digest, closure and current revision, none active after a later
 stop; a scorecard only with `revisions.rubric` and the same verdict as `run.json`;
+`READY_FOR_USER_REVIEW` only with a scorecard whose verdict is `MEETS_TARGETS`, and
+`COMPLETED_WITH_APPROVED_DEGRADATION` only with `MEETS_TARGETS_WITH_APPROVED_DEGRADATION`,
+each listing every audit gate (plus every repair gate outside assessment-only runs) as
+`PASS` or `NOT_APPLICABLE` (`G-CONCURRENCY` may be `WAIVED_OPERATIONAL` for the degraded outcome);
 no approval or writer in an assessment-only run; unchanged `run_id`, `repo_root`,
 `mode` and `assessment_only`; writers authorized for their task; one live writer
-per path (case-folded, symlink-resolved); no `dispatched`, `running` or `returned`
-attempt once the outcome leaves `RUNNING`; one outcome per approved task at the end;
+per path (case-folded, symlink-resolved); every attempt `admitted`, `rejected` or
+`cancelled` once the outcome leaves `RUNNING` (`timed-out` and `unknown` are not settled); one outcome per approved task at the end;
 a coverage denominator that never shrinks; append-only cycles, findings history and
 approval events; immutable revisions; view stamps; manifest integrity; stale stages
 and interrupted publishes. Across records: every finding's `domain` is a score key;

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

@@ -6,7 +6,7 @@ user-invocable: true
 disable-model-invocation: true
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md"],"triggers":{"intent":["devrites-lib/reference/intent-map.md"],"menu":["rite/reference/menu.md"],"dispatch":["devrites-lib/reference/parallel-dispatch.md"],"reply":["devrites-lib/reference/reply-contract.md"]}} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
+> Read-set manifest: `devrites-engine context <slug> --skill rite` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 # /rite: DevRites menu + router
 
@@ -75,9 +75,10 @@ What each verb does lives once, in the Menu below; this table is the dispatch ma
 Both forms call the same skill. The menu supports discovery; `/rite-<verb>` is the direct form.
 
 `use <slug>` is handled **inline**. There is no `rite-use` skill. Confirm
-`.devrites/work/<slug>/` exists, then re-point `.devrites/ACTIVE` to `<slug>` and report
+`<slug>` is a safe slug and `.devrites/work/<slug>/state.md` is a contained regular file, then re-point `.devrites/ACTIVE` to `<slug>` and report
 the now-active feature. It is cheap context-switching only: no re-spec, no phase run. If
-the workspace is missing, list the slugs under `.devrites/work/` and stop.
+the workspace or its `state.md` is missing, list the slugs under `.devrites/work/` that have
+`state.md` and stop.
 
 `guide` is an inline walkthrough for the first feature. Agree on one **real, small**
 change, then run spec → clarify → temper → define → vet → build → prove → polish → review → seal →

package/pack/.claude/skills/rite/reference/menu.md

@@ -32,14 +32,15 @@ Phase-ordered `/rite` reference. Load only for command detail or phase connectio
   `/rite-define` (plan) → `/rite-vet` (engineering review; light or full) →
   `/rite-build` ×N (all slices) → `/rite-prove` (once all built) →
   `/rite-polish` (always: code + UI if UI) → `/rite-review` → `/rite-seal` → `/rite-ship`.
-- **Existing codebase**: `/rite-adopt` → `/rite-clarify` → `/rite-define` → `/rite-vet` → build.
+- **Existing codebase**: `/rite-adopt` → `/rite-spec` → `/rite-clarify` → `/rite-define` → `/rite-vet` → build.
 - **Drift mid-build**: classify → bounded recovery for objective defects, `/rite-plan`
   repair for a wrong durable plan, or one user decision for real product/risk drift.
 - **Older workspace cannot resume**: `/rite-upgrade` audits first → only proven gaps use
-  Clarify/Plan repair/Converge/Vet or Prove/Polish/Review/Seal → resume. It never
-  migrates cursor format or invents a prior pass.
-- **Resumed / adopted / stalled**: `/rite-converge` (assess live code vs intent → append the
-  remaining slices) → `/rite-vet` → `/rite-build` ×N → continue at `/rite-prove`.
+  Clarify/Plan repair/Converge/Vet or Prove/Polish/Review/Seal → resume. A cursor with
+  no `schema` row needs `devrites-engine migrate <slug>` first; upgrade never migrates
+  cursor format itself or invents a prior pass.
+- **Resumed / stalled, or adopted after Define** (has `plan.md` + `tasks.md`): `/rite-converge`
+  (assess live code vs intent → append the remaining slices) → `/rite-vet` → `/rite-build` ×N → continue at `/rite-prove`.
 
 ## Rules this menu obeys
 

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

@@ -5,7 +5,7 @@ argument-hint: "[path or area to adopt] [+ what you want to build next]"
 user-invocable: true
 ---
 <!-- loads: {"always":["rite-adopt/reference/adoption.md","rite-adopt/reference/anti-patterns.md","rite-polish/reference/ledger.md"],"triggers":{"security":["devrites-lib/reference/standards/security.md"]}} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite-adopt` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
+> Read-set manifest: `devrites-engine context <slug> --skill rite-adopt` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 # /rite-adopt: onboard existing code
 
@@ -48,7 +48,8 @@ parallel convention system.
    resistance. Never create convention bands, scores, or a command cache.
 6. A genuine non-negotiable invariant may be proposed for
    `.devrites/principles.md`; the human must ratify it.
-7. Set the next step to `/rite-clarify` and stop. Do not plan or build.
+7. Set the next step to `/rite-spec <slug>` and stop; Spec extends this workspace and owns
+   `brief.md`, `checklists/`, and `spec_gate`. Do not plan or build.
 
 > Refuse the rationalizations in [`anti-patterns`](reference/anti-patterns.md).
 
@@ -59,5 +60,5 @@ Done: adopted <scope> into <slug>.
 Changed: <workspace artifacts>; project guidance <proposed | unchanged>
 Evidence: <source/CI paths inspected>
 Open: <questions | none>
-Next: /rite-clarify
+Next: /rite-spec <slug>
 ```

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

@@ -47,14 +47,16 @@ executable controller/harness/bundle bytes or a missing writer, read
   likewise internal when current authority resolves it.
 - Always follow agent-owned backward edges through repair, affected Vet,
   correction, and proof. A nested `STOP`/`Next step` is not a user handoff.
-  Pause only for a shared human/safety/access/exhaustion condition.
+  Pause only for a shared human/safety/access condition.
 - **Do not confuse an action budget with recovery exhaustion.** Spent action
   authority blocks another real execution, not offline correction of retained
   Critical/Important evidence. Stop for fresh GO only after changed conditions
   and READY Vet.
-- Every exact causal fingerprint gets at most three no-progress corrections.
-  Closing one is progress; a distinct Critical/Important invariant has its own
-  budget. Lower severity cannot prolong recovery.
+- Every exact causal fingerprint gets three no-progress corrections per strategy.
+  A spent strategy escalates to a new correction class inline; after three
+  escalations it parks while independent work continues. Never ask permission to
+  retry. Closing one is progress; a distinct Critical/Important invariant has its
+  own budget. Lower severity cannot prolong recovery.
 - Do not stop on `--max-slices`, sentinel `max_slices`, `max_agents`,
   `max_minutes`, or `max_review_queue`. Count failed, malformed, and
   unavailable leaf calls.
@@ -77,7 +79,7 @@ executable controller/harness/bundle bytes or a missing writer, read
    Before honoring `blocked` with terminal `next_action`,
    reconcile retained consumptive evidence and fingerprint attempts from
    `drift.md`/`evidence.md`; a retained fingerprint below its cap resumes offline
-   recovery.
+   recovery, and this new invocation reopens each parked fingerprint.
 <!-- workflow-artifact-adapter: {"module":"devrites-lib/reference/standards/workflow-artifacts.md","entry":"lifecycle cursor encounters admitted set or resumable journal","action":"invoke classifier; execute returned route internally","return":"saved phase/action; zero intermediate reply"} -->
    Reconstruct a missing return cursor only from
    the current phase and exact approved action in `test-plan.md`/evidence, never
@@ -116,20 +118,21 @@ executable controller/harness/bundle bytes or a missing writer, read
    route agent-owned red results through bounded recovery.
    Red gates block forward advancement and enter caller-owned recovery. Stop on
    hard risk, escalating, irreversible-risk, access, blocking with no
-   recommended option, remaining NO-GO, or the exact fingerprint's proven
-   exhaustion. An open blocking question that already names a ranked recommended
+   recommended option, remaining NO-GO, or parked fingerprints with no
+   independent work left. An open blocking question that already names a ranked recommended
    option (`proposed` or option 1 labelled Recommended) auto-resolves through
    `devrites-engine state resolve` and continues (a missing or failing resolver is
    the bounded resolver-failure stop); do not emit `/rite-resolve` as
    a user handoff. Exception: a question whose answer would add acceptance or
    product scope is never auto-resolved by a recommended option; it stops for a human.
-   Technical exhaustion records terminal
-   `Next step: none`, never a routine phase command. **Completion:** no stop is active, or its cursor and reason are durable.
-6. **Seal boundary.** Without a ship flag, stop at Seal GO with `/rite-ship` —
-   unless `continue_sequence: false` or sequence budget is spent; otherwise
-   leave the sealed workspace unshipped and open the next recorded continuation
-   ([loop.md § Sequence continuation](reference/loop.md#sequence-continuation));
-   report the sequence position on every stop.
+   A spent strategy escalates; parked recovery records
+   `Next step: /rite-autocomplete`, never a routine phase command. **Completion:** no stop is active, or its cursor and reason are durable.
+6. **Seal boundary.** Without a ship flag, leave the sealed workspace unshipped and
+   open the next recorded continuation
+   ([loop.md § Sequence continuation](reference/loop.md#sequence-continuation))
+   unless `continue_sequence: false`, the sequence budget is spent, or no entry
+   remains; then stop at Seal GO with `/rite-ship`. Report the sequence position on
+   every stop.
    With a ship flag, perform Ship preflight, disclose the exact Git plan, and stop for
    fresh literal `GO` plus native approval. **Completion:** performed no Git action before fresh literal `GO` plus native approval.
 

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

@@ -51,7 +51,8 @@ and parallel AFK headroom as stop conditions. Pass this invocation's
 that already name a ranked recommended option (recommended pick via
 `devrites-engine state resolve`) instead of queuing them or handing
 `/rite-resolve` to the user. Escalating, irreversible-risk, access, and
-blocking with no recommended option still pause.
+blocking with no recommended option still pause, as does Seal's judgment-only
+validating question (`slice: seal`).
 
 ## Phase arc
 
@@ -105,7 +106,7 @@ parent's counter (same values, never a second charge); a child with no recorded
 parent/position is not a sequence member and the chain stops.
 
 Stop instead when: no recorded next entry; the cap or review-queue bound is
-reached; a human-owned, safety, access, or exhaustion condition fires; or Seal returns
+reached; a human-owned, safety, access, or parked-recovery stop fires; or Seal returns
 `NO-GO`. On stop, report the sequence position, the sealed-but-unshipped workspaces, and
 the single release command (`/rite-autocomplete <release milestone> --ship`, or
 `/rite-ship` for the current sealed workspace when the sequence is complete).
@@ -137,14 +138,16 @@ agent-owned earlier-phase gap:
 Ask only for a human-owned decision or mandatory safety/access action. An open
 blocking question with `proposed` or option 1 labelled Recommended is not that
 decision: resolve it and continue. Three no-progress corrections of one exact
-fingerprint exhaust; preserve its reproduction and dead ends without another
-Plan/Vet command.
+fingerprint spend only its strategy: escalate inline per the
+[retry contract](../../devrites-lib/reference/standards/afk-hitl.md#retry-cap-no-progress-loops-and-self-resolve),
+and park it after three escalations while independent work continues.
 
 ## Continuous caller obligation
 
 No user-facing reply is permitted while durable state contains agent-owned
 `NEEDS_REPLAN`, an intermediate Plan/Vet action, a distinct retained
-Critical/Important fingerprint below its cap, or an open blocking question that
+Critical/Important fingerprint below its cap or with an escalation left, runnable
+work independent of a parked fingerprint, or an open blocking question that
 already names a ranked recommended option. Invoke the next internal repair or
 `devrites-engine state resolve` immediately, unless that writer already hit the
 [resolver-failure stop](stop-conditions.md#other-stop-classes). **Failing case:**
@@ -154,4 +157,4 @@ Critical/Important invariant is progress, not exhaustion.
 The number of completed repair/Vet cycles is not a stop condition. Context
 pressure, compaction, session duration, and nested completion do not convert an
 internal checkpoint into a handoff. Persist it and resume until the requested
-rest point or a shared human/safety/access/exhaustion condition.
+rest point or a shared human/safety/access/parked-recovery condition.

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

@@ -1,10 +1,10 @@
 # Stop conditions: when autocomplete pauses
 
 On a real stop, write `state.md` as `awaiting_human` or `blocked`, persist the
-reason, and include one resume command only when an actual human/safety/access
-action can change it. Exhausted agent-owned recovery records terminal
-`Next step: none` and no runnable recovery command. `--ship` never bypasses a
-stop.
+reason, and include one resume command. Agent-owned recovery never ends the run:
+a spent strategy escalates and a fully escalated fingerprint parks while other
+work continues ([retry contract](../../devrites-lib/reference/standards/afk-hitl.md#retry-cap-no-progress-loops-and-self-resolve)).
+`--ship` never bypasses a stop.
 
 Authority: `.claude/skills/devrites-lib/reference/standards/acceptance-preserving-reslice.md`.
 
@@ -22,8 +22,8 @@ Regardless of flags or AFK ceiling:
 - external-service contract change; or
 - filesystem destruction outside the workspace.
 
-Red proof cannot advance. Run bounded Debug Recovery; stop after proven
-exhaustion unless the remaining owner is human.
+Red proof cannot advance. Run bounded Debug Recovery and escalate spent
+strategies; a fully escalated fingerprint parks unless the remaining owner is human.
 
 ## Not stops: internal technical routing
 
@@ -34,13 +34,16 @@ agent-owned.
 
 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. Stop only after three no-progress corrections of
-that exact fingerprint or a real human/safety/access gate. Preserve reproduction,
-attempts, and dead ends; never offer `/rite-plan unblock` or another routine
-phase command. Reinvocation with unchanged evidence does not reset the cap.
-`unchanged` means the same fingerprint already has three recorded no-progress
-corrections. Closure is progress; a separately evidenced Critical/Important
-invariant starts its own cap and cannot extend the closed one.
+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)
+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`
+or another routine phase command. A new user-issued `/rite-autocomplete`
+reopens parked fingerprints with fresh escalation; wakes and compaction do not.
+Closure is progress; a separately evidenced Critical/Important invariant starts
+its own cap and cannot extend the closed one.
 
 Spent consumptive-action authorization is not technical-recovery exhaustion.
 It blocks another execution; retained new Critical/Important evidence still
@@ -50,9 +53,8 @@ authorization and never reuse old GO.
 Past evidence being irretrievable is not by itself terminal. If an in-scope
 trusted seam can uniquely discriminate the next failure, run diagnostic-
 amplification Plan repair and narrow Vet inline, then pause for fresh GO before
-one evidence-acquisition attempt. Use terminal none only when no safe in-scope
-seam exists, a real human/risk/scope gate owns it, or bounded recovery is
-exhausted.
+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"} -->
 ## Other stop classes
@@ -64,7 +66,8 @@ exhausted.
   would add acceptance or product scope is never auto-picked, even with a
   recommended option; it stops for a human. Blocking with no
   recommended option still stops. Validating: auto-pick the recommended option,
-  close the question, continue.
+  close the question, continue — except Seal's judgment-only acceptance question
+  (`slice: seal`), which only a human answers; it stops.
 - **Temper:** `expand` and extra acceptance stop: ask through `AskUserQuestion`, hold the
   fold, and continue only after a human resolves the qid (an ADR is not that answer).
   Irreversible-risk still pauses. `hold-rigor`, `reduce-to-MVP`, and a skip do not pause.
@@ -83,7 +86,8 @@ exhausted.
 - **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.
-- **Repeated failure:** the exact fingerprint's bounded recovery is exhausted.
+- **Repeated failure:** not a stop. Escalate; a fully escalated fingerprint parks,
+  and the run stops only once no independent work remains.
 - **Resolver failure:** `devrites-engine state resolve` not found, or nonzero exit.
   Never hand-edit `questions.md`/`state.md` in its place. Not found stops at once;
   nonzero allows one identical re-run (the fingerprint is command + exit code +
@@ -98,7 +102,7 @@ disclose the exact plan, and stop for literal `GO` plus native approval. Without
 one, stop at Seal GO with `/rite-ship`. Seal GO, AFK, prior approval, and flags
 never satisfy Ship approval.
 
-A cold-resumable stop records `state.md` status, exact reason, and either one
-human-owned resume action or `none — technical recovery exhausted`; the owning
-question/drift/seal entry explains it. The user-facing line says what stopped
+A cold-resumable stop records `state.md` status, exact reason, and one resume
+action: the human-owned action, or `/rite-autocomplete` to reopen parked
+fingerprints; the owning question/drift/seal entry explains it. The user-facing line says what stopped
 and, only when applicable, what human action resumes it.

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

@@ -69,13 +69,16 @@ wrong contract or proof path — agent-owned recovery; never advance on broken s
 The fail-on-red path:
 
 1. Continue the same wright under `devrites-debug-recovery`, carrying exact output and dead
-   ends; cap writer + recovery at three no-progress attempts per exact causal fingerprint.
+   ends; cap writer + recovery at three no-progress attempts per exact causal fingerprint
+   and strategy.
    A correction that closes the reproduction is progress; a different evidenced
    Critical/Important invariant starts a separate fingerprint.
 2. Green → record the slice. Product-contract/irreversible ambiguity → write the genuine
    human gate. Missing human-only credential/permission → write a human-intervention gate.
-3. Any other exhausted objective failure → set `Status: blocked`, preserve the reproduction,
-   set `Next step: none — technical recovery exhausted for <causal fingerprint>; requires new evidence or changed failure conditions`, and STOP without a qid or runnable phase command. Reinvocation with the unchanged fingerprint remains blocked and does not reset the cap.
+3. Any other spent strategy → escalate inline to the next correction class; after three
+   escalations park the fingerprint and build every slice that does not depend on it,
+   per the [retry contract](../../devrites-lib/reference/standards/afk-hitl.md#retry-cap-no-progress-loops-and-self-resolve).
+   Never ask a qid or permission to retry; never hand back a routine phase command.
 4. Fire `notify:` only for an actual `awaiting_human` transition.
 
 AFK never starts the next slice while checks are red and never asks the human to approve

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

@@ -182,11 +182,11 @@ Repair rejected work in place; never discard/rebuild while budget remains.
   exhaustion. Use plan path only if inventory proves the approach unsound.
 - Stop under the canonical retry/authority/resource conditions, or when evidence
   proves the approach unsound and no in-scope corrected decomposition exists.
-- Exhaustion is not abort: record one technical blocker (`Status: blocked`;
-  `Next step: none — technical recovery exhausted; requires new evidence or changed failure conditions`), preserve
-  lease/worktrees/branches, STOP — same fingerprint stays blocked on
-  reinvoke; new evidence resumes repair in place. Human-owned decisions use
-  the drift-guard question and wait.
+- A spent strategy is not abort: escalate per the canonical retry contract,
+  preserving lease/worktrees/branches; a fully escalated fingerprint parks and
+  the batch keeps its independent members. Repair resumes in place on
+  escalation or reinvocation. Human-owned decisions use the drift-guard
+  question and wait.
 
 ## Engine verbs
 

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

@@ -11,6 +11,15 @@ Claude grants only the exact wright `acceptEdits`; Codex uses its workspace root
 the exact `:workspace` wright, and read-only specialists. Never bypass/substitute
 the wright or recreate an engine bridge.
 
+## Standalone correction
+
+`/rite-quick`, `/rite-dogfood`, and `/rite-pr-feedback` fixes have no `tasks.md`
+slice, so skip Prepare's `check slice`, `context --slice`, and the build `dispatch`
+wave. Give the wright an inline contract: goal, acceptance check, exact
+project-relative paths, and proof command. With an active workspace, `claim add`
+those paths first. On return, compare its file list and `git diff --name-only`
+with the paths; reject any extra path.
+
 ## Isolated writer-worktree pilot
 
 Use native isolation only when the current host exposes an explicit named-writer
@@ -64,6 +73,8 @@ worktrees stay forbidden.
    topology/data/integration standard, include only the feature-specific owner/invariant,
    failure or partial-state case, recovery rule, and required proof from the vetted plan.
    Do not paste the whole standard or silently omit an applicable risk.
+   Quote every active `decisions.md` carry-forward constraint whose `Files:`
+   overlap the task paths (or that names no files).
    A new path requires a new bounded contract; the wright cannot widen the task.
 3. Record `git diff --name-only` before dispatch so unrelated work remains
    distinguishable. For an isolated pilot, also record committed base SHA and exact
@@ -141,3 +152,11 @@ TTL is crash recovery, not normal cleanup.
    escalation without the checked-assumption list (verified|falsified) is
    malformed; root sweeps the unchecked remainder per
    [`spec-drift-guard.md`](spec-drift-guard.md) before repair.
+6. **Learning edge.** A correction accepted with a confirmed cause (a review,
+   gate, or proof rejection plus its fix) becomes a carry-forward constraint so
+   later slices start where this one ended: append one line under
+   `decisions.md` `## Carry-forward constraints` —
+   `- <rule> — from <SLICE-ID> (<evidence ref>); Files: <paths>`. Record the
+   derived rule, not the output, at the scope its evidence supports: "this
+   button is blue" never becomes "buttons are blue". Never edit `tasks.md` mid-build (it is a
+   readiness input). **Failing case:** slice 3 repeats a defect slice 2 fixed.

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

@@ -101,9 +101,10 @@ Pull on demand:
    Produces. A principle violated in the current code is its own top-severity gap.
    Dispatch up to three independent inventory partitions to `devrites-evidence-scout` on the
    same live-code snapshot — build each scout's read-set once with
-   `devrites-engine context <slug> --phase converge --role evidence-scout` and hand it the
-   bundle path; run the wave through
-   `devrites-engine dispatch <slug> open|start|seal|return` (per
+   `devrites-engine context <slug> --phase converge --role evidence-scout --out
+   ctx/converge-evidence-scout.p<n>.bundle.md` and hand it the bundle path; run the wave
+   through `devrites-engine dispatch <slug> open|start|seal|return` with one lane label
+   per partition (`--role evidence-scout.p1 --role evidence-scout.p2 ...`, per
    [`parallel-dispatch.md`](../devrites-lib/reference/parallel-dispatch.md)), which
    auto-records dispatch/return metrics. Await their
    dossiers, then reconcile the cited facts in the root

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

@@ -6,7 +6,7 @@ user-invocable: true
 disable-model-invocation: true
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md"],"triggers":{"security":["devrites-lib/reference/standards/security.md"]},"workspace":[]} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite-customize` bundles every file named below into one deduplicated read.
+> Read-set manifest: `devrites-engine context <slug> --skill rite-customize` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read.
 
 # /rite-customize: native project customization
 

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

@@ -106,6 +106,8 @@ Pull these via `Read` when shaping the plan:
    capability end to end; first is the thinnest useful path, ordered by dependency then
    risk. Apply the slice-count and broad-refactor rules above plus
    [`slicing.md`](../rite-plan/reference/slicing.md) and [`task-breakdown.md`](../rite-plan/reference/task-breakdown.md).
+   Run `devrites-engine recall --paths <files likely touched>`; fold each relevant prior
+   decision, carry-forward constraint, or finding into that slice's `Prior-slice learnings`.
    Mark per slice: **Frontend craft required**
    and **Browser proof required** (UI), and whether it's **fullstack** (FE+BE → contract
    first, see [`fullstack.md`](../devrites-frontend-craft/reference/fullstack.md)). **For UI slices, name which
@@ -169,8 +171,7 @@ Pull these via `Read` when shaping the plan:
    `Plan sanity` (slice count + riskiest boundary/gate), `Expected build interruptions`
    (`none` or only justified action-time gates), and `Build exactly this?` (yes → approve;
    no → `/rite-plan revise`). When the human confirms the plan, write `Plan approved: <iso>` to
-   `state.md` (see [state-workspace](../rite-spec/reference/state-workspace.md)); `/rite-build`
-   checks this exists before building.
+   `state.md` (see [state-workspace](../rite-spec/reference/state-workspace.md)).
 
 ## tasks.md slice format
 

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

@@ -5,7 +5,7 @@ argument-hint: ""
 user-invocable: true
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md"],"workspace":["state.md"]} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite-doctor` bundles every file named below into one deduplicated read.
+> Read-set manifest: `devrites-engine context <slug> --skill rite-doctor` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read.
 
 # /rite-doctor: DevRites diagnostics
 
@@ -27,12 +27,18 @@ Read-only: never repair files, advance a feature, or diagnose the application.
    For enabled surfaces, require the canonical Claude skills/settings and the
    generated Codex skills, exact agent profiles, config, and AGENTS bridge.
    Cross-check the loaded/effective host configuration when the host exposes it:
-   Claude root plan mode with only `devrites-slice-wright` writable; Codex root
-   `devrites-orchestrator`, wright `:workspace`, all reviewers `:read-only`.
-   Also allowed as writers: `fast-builder` (`acceptEdits` / `:workspace`) and the
-   `overhaul-*` agents (every tool); the other `fast-*` roles are read-only.
+   Claude read-only roles keep a tools allowlist without Edit/Write plus
+   `permissionMode: plan`, which Claude honors only while the parent is not in
+   acceptEdits/auto/bypass — the guarantee is tools + instructions, the mode is
+   best-effort; only `devrites-slice-wright` (`acceptEdits`) writes in the
+   lifecycle. Codex root `devrites-orchestrator`, wright `:workspace`, all
+   reviewers `:read-only`. Also allowed as writers: `fast-builder` (`acceptEdits`
+   / `:workspace`) and the `overhaul-*` agents (every tool; `overhaul-implementer`
+   `acceptEdits`); the other `fast-*` roles are read-only.
    File presence without effective loading is `WARN`; wrong permissions or a
-   missing required profile is `FAIL`.
+   missing required profile is `FAIL`. A project or local Claude
+   `permissions.defaultMode: plan` blocks the root's `.devrites` writes:
+   `FAIL`, remediation: remove it.
 4. **Inspect workspace topology.** Read `.devrites/ACTIVE` if present. An empty
    cursor is `OK` (no active feature). Otherwise require one safe slug, a
    contained regular `.devrites/work/<slug>/state.md`, and no symlink in the

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

@@ -6,7 +6,7 @@ user-invocable: true
 disable-model-invocation: true
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-frontend-craft/reference/quality-standards.md","devrites-lib/reference/reply-contract.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"],"testing":["devrites-lib/reference/standards/testing.md"],"tooling":["devrites-lib/reference/standards/tooling.md"]},"workspace":["state.md","questions.md","dogfood.md"]} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite-dogfood` bundles every file named below into one deduplicated read.
+> Read-set manifest: `devrites-engine context <slug> --skill rite-dogfood` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read.
 
 # /rite-dogfood: diff-scoped browser QA
 
@@ -26,7 +26,7 @@ Step 0: Read `.claude/skills/devrites-lib/reference/standards/core.md`, then [`t
 2. **Map changed journeys.** Read the diff and relevant routes/components. Write or update `.devrites/work/<slug>/dogfood.md` with Mermaid flowcharts for each touched user journey. Completion: every user-visible changed surface appears in at least one flow or is marked non-browser-testable.
 3. **Build matrix.** Turn flow nodes and branches into scenarios: happy, error, empty, permission, responsive, accessibility basics, and persona paper cuts. Completion: every flow branch has a scenario row.
 4. **Run browser.** Start/reuse the dev server (honor `--port N` when given), visit each route, capture screenshot/console/network notes, and mark each scenario `Pass`, `Fail`, `Fixed`, `Blocked (human verify)`, or `Blocked (human decision)`.
-5. **Safe fix loop.** For `Fail` or sharp paper cut: fix only if obvious and contained; add a regression test or record why a replay/screenshot is the only meaningful check; re-run the scenario. Otherwise record the decision for a human.
+5. **Safe fix loop.** For `Fail` or sharp paper cut: fix only if obvious and contained; add a regression test or record why a replay/screenshot is the only meaningful check; re-run the scenario. Otherwise record the decision for a human. The root never edits source/tests: each fix goes to exact `devrites-slice-wright` with an exact-path contract per [wright-dispatch.md § Standalone correction](../rite-build/reference/wright-dispatch.md#standalone-correction); reject any returned path outside it.
 6. **Finalize.** Run the relevant test command once, update `dogfood.md`, and add follow-ups to `questions.md` only for real human decisions.
 
 ## Output

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

@@ -6,7 +6,7 @@ user-invocable: true
 disable-model-invocation: true
 ---
 <!-- loads: {"always":["rite-explain/reference/intake.md"],"triggers":{"repo":["devrites-lib/reference/standards/tooling.md"],"style":["devrites-lib/reference/standards/prose-style.md"],"principles":["devrites-lib/reference/standards/principles.md"]}} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite-explain` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
+> Read-set manifest: `devrites-engine context <slug> --skill rite-explain` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 # /rite-explain: the human half of the learning loop
 

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

@@ -69,7 +69,9 @@ installed and no fresh context is available, stop with `Stopped: fast-* agents m
    record `unproven: no commands` and continue. PROVE will report it.
 3. Pick a short kebab-case slug from the task. If the argument names an existing
    `.devrites/work/<slug>/plan.md` with `Lane: fast`, **resume**: read the ledger and
-   continue at the first phase or slice that is not complete.
+   continue at the first phase or slice that is not complete. If `.devrites/work/<slug>/`
+   exists without `Lane: fast`, or `.devrites/archive/<slug>/` exists, pick a new slug;
+   if the user named that slug, stop instead — never overwrite another workspace.
 
 ## 1. Shape: spec, plan, questions
 

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

@@ -6,7 +6,7 @@ disable-model-invocation: true
 argument-hint: "[what the next session will focus on]"
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md","rite-handoff/reference/handoff-template.md","devrites-lib/reference/reply-contract.md"],"triggers":{"hygiene":["devrites-lib/reference/standards/context-hygiene.md"]}} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite-handoff` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
+> Read-set manifest: `devrites-engine context <slug> --skill rite-handoff` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 # /rite-handoff: chat-only context, into a fresh-agent doc
 
@@ -48,8 +48,9 @@ For each of these, write the content into its **canonical home** first, then mer
 - **Assumption** about behaviour / API / user intent → append to `assumptions.md`.
 - **Drift event raised but not fully resolved** → update `drift.md` with the current
   resolution status (open / asked-user / repaired).
-- **Files modified in chat not yet in `touched-files.md`** → append to
-  `touched-files.md`.
+- **Files modified in chat not yet in `touched-files.md`** → no recorded provenance, so
+  record them as drift in `drift.md` (or a `questions.md` entry); never append them to
+  `touched-files.md`, the candidate manifest Ship stages.
 
 The handoff doc itself then says "synced N entries into decisions.md", not the entries
 themselves. The workspace is the canonical store; the handoff is the chat-only delta.

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

@@ -6,7 +6,7 @@ user-invocable: true
 disable-model-invocation: true
 ---
 <!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/documentation.md","devrites-lib/reference/standards/tooling.md"],"workspace":["state.md","decisions.md","drift.md","evidence.md","review.md","seal.md","questions.md"],"workspaceByRole":{"retrospector":["state.md","decisions.md","drift.md","evidence.md","review.md","seal.md","questions.md"]},"triggers":{"agents":["devrites-lib/reference/standards/agents.md"]}} -->
-> Read-set manifest: `devrites-engine context [slug] --skill rite-learn` bundles every file named below into one deduplicated read.
+> Read-set manifest: `devrites-engine context <slug> --skill rite-learn` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read.
 
 # /rite-learn: review durable lessons
 
@@ -29,7 +29,7 @@ of one authority; it cannot promote a rule alone.
    A missing, failed, timed-out, or malformed result reports `Candidate: NOT-RUN
    (unavailable: <reason>)` as a gap, never `Candidate: none`; an unavailable role stops
    for HITL per [`agents.md`](../devrites-lib/reference/standards/agents.md) (trigger `agents`).
-3. Keep corrections repeated in two features, a judgement call made twice, or a defect class seen twice; drop one-off preferences, task-specific detail, generic advice.
+3. Keep corrections repeated in two features (a `## Carry-forward constraints` rule recurring in two archived `decisions.md` qualifies), a judgement call made twice, or a defect class seen twice; drop one-off preferences, task-specific detail, generic advice.
    Broad mode also proposes **retirements**: a rule found via a `rite-learn: accepted`
    marker whose cited failing case or owner no longer exists in live source, whose
    review-by date passed unverified, or that is a model-default no-op. Zero is valid but