devrites 5.13.0 → 5.14.0

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

@@ -83,6 +83,12 @@ exhausted.
   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.
+- **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 +
+  decisive stderr line; an unchanged re-run is not a correction, so no further
+  attempts). Then stop `blocked` with the exact command, exit code, and stderr line,
+  and resume action `/rite-doctor`.
 
 ## Final GO and durable stop
 

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

@@ -52,22 +52,14 @@ rewrite; do not claim cross-file atomicity):
    raised_at: <iso>
    ```
 
-2. **`state.md` updates:**
-
-   ```markdown
-   - Status: awaiting_human
-   - Active slice: <N — name>
-   - Slice mode: HITL
-   - Next step: /rite-resolve <qid> "<answer>"
-
-   ## Awaiting human
-   - qid: <q-...-NNN>
-   - gate: <gate>
-   - question: <Checkpoint text>
-   - proposed: <one-paragraph best-guess>
-   - raised_at: <iso>
-   - blocking_slices: [<list, from `Blocked by` lookups>]
-   ```
+2. **`state.md` updates:** cursor `status` = `awaiting_human`, `active_slice` =
+   `<N — name>`, `slice_mode` = `HITL`, `next_action` = `/rite-resolve <qid> "<answer>"`;
+   then the `Awaiting human` table (`question_id`, `gate`, `blocking_slices` from
+   `Blocked by` lookups) per its owner,
+   [`state-workspace.md`](../../rite-spec/reference/state-workspace.md#statemd-template) § state.md template.
+   Question text, `proposed`, and `raised_at` stay in the step 1 entry. Legacy
+   `- Status:`/`- Next step:`/`- qid:` bullets are engine-accepted aliases, not the
+   authoring format.
 
 3. **`notify:` hook (if `.devrites/AFK` defines one):** export all six env vars from the
    canonical contract in [`afk-discipline.md`](afk-discipline.md) (the `notify:` hook

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

@@ -62,6 +62,15 @@ overlap → sibling **gap** (a shared path is a contract defect). **Failing
 case:** two parallel wrights share a path and fan-out proceeds without that
 check.
 
+Before `parallel select`, add each slice's hidden write surfaces (list owner:
+[repository-topology.md § Ownership rules](../../devrites-lib/reference/standards/repository-topology.md#ownership-rules))
+— lockfile/manifest, the generated target of an edited source, migration chain,
+snapshot directory, formatter sweep — and compare paths case-folded
+(`src/Api.ts` = `src/api.ts`). Slices colliding on either run serially; the rest
+stay eligible. Record `serial: <ids> — <surface>` in `evidence.md`. **Failing
+case:** two slices each add a dependency, run in parallel, and integrate fails or
+lands a broken lockfile.
+
 ## Control vs workers
 
 Control owns `.devrites/work/<slug>/` (lease + bookkeeping).

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

@@ -95,7 +95,11 @@ not normal cleanup.
 1. Compare the returned file list and `git diff --name-only` with task paths.
    `devrites-engine check diff-scope <slug> --allow <task-paths>` is the
    mechanical subset gate — run it before any reviewer dispatch; a violation
-   restores through the bounded wright without spending review.
+   restores through the bounded wright without spending review, but only for a
+   path the wright's `files_changed` or diff trace attributes to it. An
+   unattributed extra path that was clean at the step-3 baseline is preserved
+   (never restored), recorded as drift, and stops for the human. **Failing case:**
+   a user edits `README.md` during a same-tree dispatch and the wright reverts it.
    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.

package/pack/generated/devin/skills/rite-clarify/SKILL.md

@@ -95,7 +95,7 @@ Evidence: Decision coverage: CLEAR; human packets <n>; agent-owned facts <n>
 Open: none blocking; deferred-nonblocking <n>
 Next: /rite-temper (or /rite-define for a low-stakes spec temper skips)
 Record: .devrites/work/<slug>/decision-coverage.md
-↻ Hygiene: /clear before /rite-temper (or /rite-define)
+↻ Hygiene: /clear — decision coverage is persisted in decision-coverage.md
 ```
 
 If not clear, name the exact rows and next genuine decision packet. An objective spec defect

package/pack/generated/devin/skills/rite-converge/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: rite-converge
-description: Converge intent and live code. Use when resuming a half-built feature, after `/rite-adopt` drift, or the user asks "what's left to build". Not for initial planning.
+description: Converge intent and live code. Use when resuming a half-built feature, after `/rite-adopt` drift, or live code may have diverged from the plan. Not for initial planning.
 argument-hint: "[feature-slug]"
 ---
 
@@ -58,6 +58,13 @@ Pull on demand:
 - **Principles are non-negotiable.** A live violation of a declared invariant with no recorded
   exception is the top-severity gap, walked first. Absent/empty principles file → none declared
   → skip the check gracefully, never block for its absence.
+- **Unadmitted bytes from a lost wright.** When a stalled slice's wright never returned an
+  admitted result, act only after its terminal state is proven
+  ([`parallel-dispatch.md`](../devrites-lib/reference/parallel-dispatch.md) § Cancellation);
+  unproven stays a gap. Then inspect task-path bytes changed since the recorded pre-dispatch
+  `git diff --name-only` baseline (none recorded → every changed task path counts). They are
+  never cited `built`, never discarded (user work): classify the slice `partial (unadmitted
+  bytes)` and name those paths in the appended slice. A change outside task paths stops for the human.
 - **Scout observes; root classifies and writes.** Use
   [`agents.md`](../devrites-lib/reference/standards/agents.md). The evidence scout returns
   live-code citations only; the controlling chat owns built/partial/absent calls and append-only
@@ -114,7 +121,7 @@ Pull on demand:
    `decisions.md` for any material call. When slices were appended, run
    `devrites-engine check task-graph <slug>` before invoking Vet; failure stays in
    Converge for correction and never spends a Vet reviewer context.
-7. **STOP.** Report units assessed, built / partial / absent counts, slices appended, and any
+7. **STOP.** Report units assessed, built / partial / absent / unrequested counts, slices appended, and any
    principle violation found. A direct invocation that appended slices becomes
    the caller for the mandated next step: save a return cursor
    (`return_phase`/`return_next_action`) naming this Converge pass as the

package/pack/generated/devin/skills/rite-converge/reference/convergence-assessment.md

@@ -52,6 +52,11 @@ Before appending a slice, separate the two failure directions:
   ([`spec-drift-guard.md`](../../rite-build/reference/spec-drift-guard.md)) + a recorded decision, and let `/rite-plan
   repair` reshape intent. Convergence enqueues work; it never launders a spec bug into a code
   task.
+- **Unrequested:** within `touched-files.md` paths and plan touch-points, observable behavior
+  no REQ/AC/decision explains. It never enqueues a build slice: keep it through the Spec Drift
+  Guard plus a recorded decision, or record a `drift.md` removal item for `/rite-review`. Report
+  its count; an unrouted one blocks a clean result. **Failing case:** adopted code serves an admin export
+  endpoint no REQ names, Converge says "nothing unmet", and later slices build on it.
 
 ## Numbering + ordering the appended batch
 

package/pack/generated/devin/skills/rite-define/SKILL.md

@@ -65,7 +65,8 @@ Pull these via `Read` when shaping the plan:
    and respect the IN/OUT line; map coverage against the **hardened** spec), and
    **`design-brief.md` if the feature touches UI** (the UX/UI contract `/rite-spec` shaped:
    its key states, interaction model, and proof targets drive how UI slices are cut). If a blocking
-   `[NEEDS CLARIFICATION]` remains, stop → `/rite-clarify`.
+   `[NEEDS CLARIFICATION]` remains, stop → `/rite-clarify`. Run the [`spec-grammar.md`](../devrites-lib/reference/standards/spec-grammar.md) marker
+   sweep; a kept hit stops the same way, and its `marker sweep:` line goes in the step-7 digest.
    Reconcile every `Applicability map` row against live repository evidence. Load each
    applicable standard; a false `not applicable` is a blocking spec gap, not a planning
    shortcut.
@@ -120,6 +121,10 @@ Pull these via `Read` when shaping the plan:
    ([`acceptance-criteria.md`](../rite-spec/reference/acceptance-criteria.md)); no orphaned criteria, no slice without a
    criterion. Lift covered/backstop `Edge Coverage` rows and resolved `Prohibitions (must-NOT)`
    rows into `traceability.md` and `test-plan.md`; unresolved rows get a gate/owner. Each
+   `Existing behavior to preserve` row becomes a regression row whose current evidence is
+   observed green on the unchanged baseline as a prerequisite of the first slice touching that
+   seam, and green again at Prove; a red baseline is recorded pre-existing, never relabelled.
+   Evidence that cannot run takes `characterize-before-modify` or blocks. Each
    cross-slice boundary names producer, consumer, invariant, integration step, and proof.
    Map each applicable topology/data/integration risk to a slice, failure/recovery path,
    and discriminating proof; a risk cannot live only in the architecture narrative.

package/pack/generated/devin/skills/rite-define/reference/plan-template.md

@@ -92,6 +92,9 @@ Shared contract impact: none — <specific justification>
 List slice prerequisites, non-code prerequisites, and deployable order:
 contract/schema/config → old/new app/worker → migration/backfill → exposure → removal.
 Name shared mutable resources that force serialization.
+Each temporary flag, shim/adapter, dual read/write, retained old column/endpoint, or deprecated
+alias the plan adds names its removal `SLICE-###` here, or a Non-goal continuation
+(`/rite-spec <slug>-N`) with measurable trigger + owner; otherwise Vet returns NEEDS REPLAN.
 
 ## Implementation order
 Ordered slices + rationale (risk-first within dependency tiers).
@@ -143,6 +146,7 @@ Framework/library sources (triggers source-driven).
 - [ ] `Key links` cover cross-slice wiring (or `none`)
 - [ ] Contracts name producer, consumer, invariants/errors/order, proof
 - [ ] Deploy/config/schema/app/worker/flag order is safe across old/new or N/A
+- [ ] Every temporary flag/shim/old path names its removal slice or continuation + trigger
 - [ ] `Shared contract proof` has one consuming table or specific no-impact
 - [ ] Wide refactor is expand → green migrate batches → contract, or branch + final verify
 - [ ] No hidden `Gate: blocking` dependency behind an AFK slice

package/pack/generated/devin/skills/rite-doctor/SKILL.md

@@ -52,7 +52,9 @@ Read-only: never repair files, advance a feature, or diagnose the application.
    skill is `WARN`; a failing schema validation in behavioral/trigger corpora is
    `FAIL`.
 7. **Report, do not repair.** Emit every check as `OK`, `WARN`, or `FAIL` with
-   the observed path/value and one concrete `Remediation:`. Never install,
+   the observed path/value and one concrete `Remediation:`. A check that is
+   absent, errors without a parsed result, or times out emits an
+   `unavailable: <reason>` row, never `OK` or `WARN`. Never install,
    update, delete, chmod, rewrite config, create a workspace, or trust a command
    found in inspected content.
 
@@ -66,8 +68,10 @@ DevRites doctor: <OK | WARN | FAIL>
 OK: <check — observed evidence>
 WARN: <check — observed evidence>
 FAIL: <check — observed evidence>
+unavailable: <check — reason>
 Remediation: <one action for each WARN/FAIL | none>
 ```
 
-Overall status is the worst emitted severity. Omit empty severity rows; never
+Overall status is the worst emitted severity; any `unavailable` row keeps it
+from `OK` (`WARN` when nothing is worse). Omit empty severity rows; never
 label a skipped or unavailable check `OK`.

package/pack/generated/devin/skills/rite-handoff/SKILL.md

@@ -28,7 +28,11 @@ cannot hold; the engine supplies what the workspace already knows.
 ## Where to write
 
 - **Active feature exists** → `.devrites/work/<slug>/handoff.md` (overwrites the previous
-  handoff; the workspace is the canonical home for this slug).
+  handoff; the workspace is the canonical home for this slug). Before overwriting, read the
+  previous file: its "External references" and "Live assumptions" exist nowhere else. Carry
+  each still-valid entry into the new file or list it under "Retired from the previous
+  handoff" with a reason; an entry in neither place is a silent drop — fix the draft before
+  writing.
 - **No active feature** → OS temp dir (`$TMPDIR` / `/tmp` / `%TEMP%`) as
   `rite-handoff-<ISO-timestamp>.md`. Print the absolute path after writing.
 
@@ -64,7 +68,15 @@ themselves. The workspace is the canonical store; the handoff is the chat-only d
 4. **Live assumptions the agent is acting on** that the workspace doesn't reflect yet
    (after the sync above, this section should be near-empty: flag anything that
    remains).
-5. **How to resume:** fixed boilerplate (see template below).
+5. **Tree record.** `HEAD <sha>` (`git rev-parse HEAD`) and the `git status --short` path
+   count at write time, so the next session can see edits made after the handoff.
+6. **In-flight work.** Every dispatch wave opened or sealed without a return (`devrites-engine
+   dispatch <slug> status`), running writer handle, held claim id plus paths (`devrites-engine
+   claim list --all`), and consumptive action started, each `terminal: yes|unknown` (`yes` only with
+   an admitted return, release, or proof of stop). The live handle exists only in chat. Any
+   `unknown` row makes item 1 a reconcile step (`dispatch <slug> status`, `parallel status`,
+   `claim list --all`), never a writer command: otherwise the next session dispatches a second writer.
+7. **How to resume:** fixed boilerplate (see template below).
 
 ## What NOT to include
 

package/pack/generated/devin/skills/rite-handoff/reference/handoff-template.md

@@ -10,6 +10,8 @@ Loaded on demand by `/rite-handoff`. Write the filled-in template to
 Current objective: <one sentence>
 Last completed slice: <SLICE-### | none>
 Blockers: <none | q-YYYY-MM-DD-NNN / released Q-### / DRIFT-###>
+Tree at write: HEAD <sha | no git>; dirty paths <n>
+In flight: <none | wave <id> role <r> handle <h> | wright SLICE-### handle <h> | claim <id> <paths> | action <name>>; each `terminal: yes|unknown`
 
 ## Read next
 1. `.devrites/work/<slug>/README.md` — workspace map.
@@ -18,17 +20,22 @@ Blockers: <none | q-YYYY-MM-DD-NNN / released Q-### / DRIFT-###>
 4. <phase-specific source artifact; link, do not duplicate>.
 
 ## Next action
-<one command or action, no option set>
+<one command or action, no option set; any `terminal: unknown` row makes it reconcile:
+`devrites-engine dispatch <slug> status`, `devrites-engine parallel status --root <repo> --slug <slug>`,
+`devrites-engine claim list --all` — never a writer command>
 
 ## What changed this turn
 - <short event; link to source artifact instead of copying full content>
 
 ## External references (chat-only)
-- <URL / Figma / screenshot path / video timestamp>
+- <URL / Figma / screenshot path / video timestamp>   (carried forward if still valid)
 
 ## Live assumptions (not yet in assumptions.md)
 - ...   (this section should be near-empty after the sync step)
 
+## Retired from the previous handoff
+- <none | reference or assumption — why it no longer holds>
+
 ## Synced this turn
 - decisions.md: <N entries appended>
 - questions.md: <N appended>
@@ -39,6 +46,11 @@ Blockers: <none | q-YYYY-MM-DD-NNN / released Q-### / DRIFT-###>
 ## How to resume
 1. Read this file.
 2. Read `.devrites/work/<slug>/state.md` for the workspace cursor.
-3. Run `/rite-status` for the current phase / next action / open drift.
-4. Continue with the `Next action` above.
+3. Tree check: compare `git rev-parse HEAD` and `git status --short` with `Tree at write`
+   and `touched-files.md`. Other HEAD, other dirty count, or a path missing from
+   `touched-files.md` → record it in `drift.md` or `questions.md` before any writer command.
+4. Any `In flight` row `terminal: unknown` → run the reconcile commands first; never dispatch
+   a second writer onto its paths.
+5. Run `/rite-status` for the current phase / next action / open drift.
+6. Continue with the `Next action` above.
 ```

package/pack/generated/devin/skills/rite-learn/SKILL.md

@@ -20,10 +20,20 @@ of one authority; it cannot promote a rule alone.
 
 ## Workflow
 
-1. Read [durable promotion](../devrites-lib/reference/standards/documentation.md#promote-durable-guidance);
-   bound the archive; inspect applicable `AGENTS.md`/`CLAUDE.md`, accepted ADRs, and relevant `.devrites/archive/*/{decisions,drift,review,seal}.md`.
+1. Read [durable promotion](../devrites-lib/reference/standards/documentation.md#promote-durable-guidance).
+   Before bounding, fixed-string search all of `.devrites/archive/` and active
+   `decisions.md` for `rite-learn: accepted` and `rite-learn: declined`; read every hit
+   whole. Then bound the archive; inspect applicable `AGENTS.md`/`CLAUDE.md`, accepted ADRs, and relevant `.devrites/archive/*/{decisions,drift,review,seal}.md`.
+   **Failing case:** a declined proposal returns because its feature fell outside the bound.
 2. Broad mode dispatches exact fresh/read-only `devrites-retrospector`; reconcile its claims against cited files.
+   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.
+   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
+   names the searched scope; a rule still guarding a live failing case is never retired.
 4. Verify claims against live authoritative sources; state currentness signal, applies/does-not-apply scope, `unknown` where unverifiable.
    **Research promotion requires:** each external claim carries a dated citation per
    [[`tooling.md`](../devrites-lib/reference/standards/tooling.md) § Research provenance](../devrites-lib/reference/standards/tooling.md#research-provenance-staleness-and-cost).
@@ -44,6 +54,20 @@ of one authority; it cannot promote a rule alone.
   conversation or on an unmerged branch is lost and will be re-litigated.
   **Failing case:** the same rejected proposal returns next round because no tracked
   entry exists.
+- Every disposition entry carries the fixed marker `rite-learn: accepted` or
+  `rite-learn: declined`, its evidence refs, and (accepted) owner path plus a review-by
+  date. A later round reuses a matching declined record instead of re-proposing.
+- A lesson needs an **external signal** (user correction, failing test/gate, review
+  finding) with its source; self-critique or model reflection alone never changes guidance.
+- Promotion path is fixed: lesson → artifact type (retrospector class) → one canonical
+  owner → human approval of the exact edit. A skipped stage is no promotion.
+- **Recurrence ⇒ mechanism.** When `Authority: existing <path>` already holds the violated
+  rule, the candidate is a check, gate, template slot, or default at that owner
+  ([`skill-authoring.md`](../devrites-lib/reference/standards/skill-authoring.md#match-form-to-failure) § Match form to failure),
+  never a reworded, bolder, or relocated copy; otherwise record `no mechanical form
+  possible: <reason>` and narrow the proposal. An unwired or broken existing check is
+  itself the candidate. **Failing case:** a round accepts a bolder copy of an `AGENTS.md`
+  rule that two archived features already violated.
 - A lesson proposing a new recurring check names its **controls**: the real past
   instance it would have caught (positive) and a near-miss class it must not fire on
   (negative). **Failing case:** a trigger patterned on an imagined command that never
@@ -52,17 +76,23 @@ of one authority; it cannot promote a rule alone.
 - A proposal names the **retrospective failing case**: the concrete past feature/artifact the
   rule would have caught. None → generic advice — drop.
 - ≤3 accepted lessons per round; proposals extend/narrow but never lower an existing bar (revisions show old text beside new); duplicates consolidate into one canonical edit — simplification (deletions/merges) counts toward the cap.
+  Net growth cap: a round adds at most 3 net rules across all owners (additions minus
+  retirements). A round whose approved edits add net bytes to an owner states the
+  retirement search it ran.
 - An accepted lesson ships with a **follow-through owner and deadline**: the exact edit
   lands in the named canonical file in the same round; a lesson unapplied at round end
   returns to candidates with its blocker recorded. **Failing case:** an accepted lesson
   with no applied edit and no recorded blocker — promotion failed; re-raise it.
+  Still unapplied at a second round end, it becomes an apply-or-decline decision; a
+  decline takes the `rite-learn: declined` record, so no lesson is carried a third time.
 
 ## Output
 
 ```text
 Done: reviewed <scope>.
 Changed: none (proposal only)
-Candidate: <specific proposal or none>
+Candidate: <specific proposal | none | NOT-RUN (unavailable: <reason>)>
+Retirements: <candidates | none — searched <scope>>
 Currentness: <live source + signal | unknown>
 Scope: applies <trigger>; does not apply <boundary>
 Authority: existing <path|none>; canonical <path>; consumers/discovery <route>
@@ -70,5 +100,5 @@ Disposition: <no conflict | update/narrow/replace/retire path + reason>
 Evidence: <feature/file references>
 Awaiting: <approval for exact edits | none>
 Next: <single action>
-Record: <nearest owning decisions file | chat-only>
+Record: <nearest owning decisions file | chat-only only when the round made no accepted/declined disposition>
 ```

package/pack/generated/devin/skills/rite-plan/SKILL.md

@@ -62,7 +62,8 @@ Before classifying any Reslice, read `.devin/skills/devrites-lib/reference/stand
    dependency's current API surface, consult context7 if available.
 2. **Pick the mode** (`$ARGUMENTS` or infer): Apply the marked action before writes and
    retain its decision/coverage evidence.
-   - **decompose:** first/again break the feature into vertical slices.
+   - **decompose:** break an already-sliced feature into vertical slices again. With no
+     `SLICE-###` in `tasks.md`, stop and route to `/rite-define`; first-pass decomposition is its.
    - **reslice:** a slice is too large; split into thinner end-to-end slices.
    - **repair:** a Spec Drift Guard event; fold the resolution into plan + tasks.
    - **reorder:** fix the dependency order.

package/pack/generated/devin/skills/rite-plan/reference/task-breakdown.md

@@ -38,6 +38,12 @@ This reference owns decomposition; the shared schema owns field names and meanin
   called `clearLayers()` in slice 3 and `clearFullLayers()` in slice 7 is a planning bug:
   name shared symbols once, here.
 - Don't pre-write code in the task: describe the outcome, not the implementation.
+- **Read the fields, not the title.** A slice fails Vet (`kind: contract`, Important, field
+  quoted) when its `Goal` or `Done condition` names an activity instead of an observable end
+  state ("implement backend", "add tests", "handle errors", "wire up UI"); when a no-op or
+  wrong diff could meet the `Done condition` ("tests pass", "works correctly"); or when
+  `Tests/proof` names no specific test or assertion ("run the suite"). **Failing case:**
+  `Goal: Implement export backend · Done condition: tests pass · Tests/proof: go test ./...`.
 - Don't bundle "while we're here" work into a slice. That's scope creep; log it as a
   follow-up instead.
 - Don't slice to a target number: the count comes from the capabilities + the sizing

package/pack/generated/devin/skills/rite-polish/SKILL.md

@@ -62,12 +62,18 @@ Incomplete comparison is **not** agreement. Record axis deltas in `polish-report
    Then read the explicit or active workspace's `state.md` directly.
 1. **Read** `state.md`, `touched-files.md`, the current candidate digest, and the
    `git diff` for the active workspace (or `$ARGUMENTS` if a target was given).
-2. **Detect UI scope:** UI is touched if the diff or `touched-files.md`
-   contains any of: `.tsx`, `.jsx`, `.vue`, `.svelte`, `.html`, `.css`,
+2. **Detect UI scope:** UI is touched when the diff changes rendered output:
+   markup, template, style, design token, client component, or a visible string
+   (including an API error message shown in the UI). These paths are leads to
+   inspect, not the predicate: `.tsx`, `.jsx`, `.vue`, `.svelte`, `.html`, `.css`,
    `.scss`, `.sass`, `.less`, `.styl`, component dirs (`components/`,
    `pages/`, `routes/`, `app/`, `views/`, `screens/`), Storybook stories,
-   or design-token files. When in doubt, look for visual changes that need
-   verification.
+   or design-token files; when in doubt whether output changes, treat it as UI
+   scope. A diff with no rendered-output change records
+   `UI scope: none (no rendered output)` and skips Phases 3–4; non-visual client
+   code still gets frontend engineering review (`devrites-code-reviewer` frontend lane).
+   **Failing case:** an `app/services/billing.rb` diff opens Phase 4 and demands
+   captures.
 3. **Always** read [`reference/code.md`](reference/code.md) and assess **Phase 1
    (code polish)**; if backend was touched, assess **Phase 2 (backend polish)** from
    the same file. Reconcile the findings, then send accepted corrections as one bounded

package/pack/generated/devin/skills/rite-polish/reference/anti-ai-slop.md

@@ -10,50 +10,72 @@ Tells of generic LLM-generated work — in **UI** and in **code**. Applies at tw
 Avoid these unless the project's existing system explicitly uses them. When in doubt,
 match the neighbors.
 
+## UI admission rule (tells are leads, not findings)
+Build avoids every UI entry; review and polish admit a hit only by this rule. Classes:
+**ENG** (engineering/realism), **A11Y** (WCAG 2.2 SC or platform requirement), **DS**
+(binding only where project tokens, components or `design-brief.md` declare it), **AES**
+(optional aesthetic). A hit is a finding only with cited mismatch evidence: it contradicts
+a declared token, brief line or nearest neighbour (cite both locations), or it has a
+measured user consequence (contrast ratio, overflow, CLS, lost or hidden focus). Otherwise
+it is an AES proposal under "Proposals (non-blocking)": never a Visual Verdict FAIL, never
+scored, capped at Suggestion/Minor, never blocking unless `design-brief.md` adopts it (then
+DS). Act on clusters per [`prose-style.md`](../../devrites-lib/reference/standards/prose-style.md).
+A broken task, data loss or misleading state is reported and fixed before any AES item.
+**Failing case:** `tokens.css` declares Inter and a 20 px card radius, yet review files
+"reflex font" and "balloon radius" as Important; or three eyebrows on six sections become
+a FAIL row with no brief conflict.
+
+**UI-copy boundary.** Craft owns functional copy: action-named controls, errors with cause
+and recovery, next-step empty states, product vocabulary, fit under expansion, and an
+accessible name containing the visible label (SC 2.5.3, A11Y). Long-form product text
+routes to `devrites-prose-craft`; translation catalogs stay untouched without their owner.
+
 ## UI anti-slop (banned defaults)
-- Default **purple/blue gradients** as the brand look. Special case: any
+- [AES] Default **purple/blue gradients** as the brand look. Special case: any
   hero hex in the `#6366f1 → #a855f7 → #ec4899` family applied as a default.
-- **Gradient text** (`background-clip: text`) used decoratively on headings.
-- **Glassmorphism** (`backdrop-filter: blur(...)` on translucent panels) as
+- [AES] **Gradient text** (`background-clip: text`) used decoratively on headings.
+- [AES] **Glassmorphism** (`backdrop-filter: blur(...)` on translucent panels) as
   a default surface.
-- **Side-stripe colored borders** on cards/sections — the
+- [AES] **Side-stripe colored borders** on cards/sections — the
   "tiny-bar-of-meaningful-accent-color-on-the-left" pattern. Distinctive
   templating tell.
-- **Pure `#000` / `#fff`** as raw text or background — too clinical; use
+- [AES] **Pure `#000` / `#fff`** as raw text or background — too clinical; use
   near-black/near-white tokens (`oklch(0.18 0 0)` / `oklch(0.98 0 0)` or
   the project's surface tokens).
-- **All-CAPS body text** for paragraphs/labels. Reserve uppercase for short
+- [AES] **All-CAPS body text** for paragraphs/labels. Reserve uppercase for short
   micro-copy (badges, eyebrows); never for sentences.
-- **Em-dashes in UI copy — zero.** Soft limits ("use sparingly") get ignored; the rule
-  is binary and greppable: no `—` in any visible string. Use a comma, period, or colon.
-- **Cards inside cards** — nested bordered/elevated containers.
-- **Identical card grids** for everything, regardless of content.
-- A **generic rounded-square icon tile** above every heading/section.
-- **Gray text on colored backgrounds** (fails contrast, looks templated).
-- The **hero-metric cliché** — three big numbers in a row with no real meaning.
-- **Decorative bounce / elastic easing** on everything; motion without purpose.
-- **Reflex fonts** picked because they're the default in a tutorial:
+- [AES] **Em dashes in UI copy** are a lead, not a ban: DS only where the project's
+  style guide bans them; otherwise no rule applies to product copy, because
+  [`prose-style.md`](../../devrites-lib/reference/standards/prose-style.md) governs DevRites
+  prose, not product UI.
+- [AES] **Cards inside cards** — nested bordered/elevated containers.
+- [AES] **Identical card grids** for everything, regardless of content.
+- [AES] A **generic rounded-square icon tile** above every heading/section.
+- [A11Y] **Gray text on colored backgrounds** — a finding with the measured ratio (SC 1.4.3).
+- [AES] The **hero-metric cliché** — three big numbers in a row with no real meaning.
+- [AES] **Decorative bounce / elastic easing** on everything; motion without purpose.
+- [AES] **Reflex fonts** picked because they're the default in a tutorial:
   - Inter for every product when the project has its own choice.
   - **DM Sans**, **Plus Jakarta Sans**, **Fraunces**, **Newsreader** when
     they're not the project's actual type system.
   Match the project; don't reach for the "tasteful default" of 2024.
-- **Modal-first thinking** — reaching for a modal as the answer to every interaction.
-- **Ghost-card** — a `1px` border *and* a soft (blur ≥16px) shadow on the same element.
+- [AES] **Modal-first thinking** — reaching for a modal as the answer to every interaction.
+- [AES] **Ghost-card** — a `1px` border *and* a soft (blur ≥16px) shadow on the same element.
   Borders separate; shadows lift — pick one
   ([`quality-standards.md`](../../devrites-frontend-craft/reference/quality-standards.md) — Materiality).
-- **Balloon radius** — `border-radius` above ~16px on cards, inputs, panels. Cards top
+- [AES] **Balloon radius** — `border-radius` above ~16px on cards, inputs, panels. Cards top
   out around 12–16px; full pills are for tags and buttons only.
-- **Uppercase tracked eyebrow above every section** — one named kicker is voice; one per
+- [AES] **Uppercase tracked eyebrow above every section** — one named kicker is voice; one per
   section is template grammar (countable cap below).
-- **Numbered-section scaffolding** (`01 / 02 / 03`) when the sections aren't a sequence.
-- **Fake UI-in-a-div** — a "product screenshot" assembled from nested divs, or hand-drawn/
+- [AES] **Numbered-section scaffolding** (`01 / 02 / 03`) when the sections aren't a sequence.
+- [ENG] **Fake UI-in-a-div** — a "product screenshot" assembled from nested divs, or hand-drawn/
   sketchy SVG scenery. Ship a real capture/asset or nothing (quality-standards — Materiality).
-- **Hero prop badges** — version labels (`V0.6`, `BETA`) and decorative pulsing status
+- [AES] **Hero prop badges** — version labels (`V0.6`, `BETA`) and decorative pulsing status
   dots as set dressing.
-- **Unstyled UA chrome** — shipping the browser's default blue selection, caret,
-  scrollbar, or focus outline as the look (quality-standards § Browser chrome).
-- **Invented metrics** — precise-looking numbers with no source (`+247% faster`,
-  `99.99% uptime`). **Off-token color** — a hex used inline that the token set doesn't
+- [AES] **UA chrome** — default selection, caret or scrollbar; the UA focus ring is a
+  finding only when SC 2.4.7/1.4.11 fails (quality-standards § Browser chrome).
+- [ENG] **Invented metrics** — precise-looking numbers with no source (`+247% faster`,
+  `99.99% uptime`). [DS] **Off-token color** — a hex used inline that the token set doesn't
   define. Both are realism failures, not styling choices.
 
 ### Required remediations (fix the hit, don't just flag it)
@@ -65,11 +87,11 @@ an incomplete finding.
 | Default purple/blue gradient; gradient text; glassmorphism default | Re-derive from the scene sentence and colour commitment, then re-run both category-reflex tests |
 | Invented metric | Replace with the state lattice's missing-data placeholder (quality-standards § Focus & states) plus a "metric to confirm" question, or delete the proof slot |
 | Off-token color | Lift into the token set as a named color; replace every inline use |
-| Wrapping CTA / nav overflow | Shorter label, `white-space: nowrap`, or a collapsed nav — never a shrunken tap target |
-| Horizontal scroll in 320–1920 | `minmax(0, 1fr)` on content tracks + `overflow-x: clip` on `html`/`body` (quality-standards § Responsive) |
+| Wrapping CTA / nav overflow | Shorter label or a collapsed nav, verified at 200% text zoom — never `white-space: nowrap` or a shrunken tap target |
+| Horizontal scroll in 320–1920 | Fix intrinsic sizing (`minmax(0, 1fr)`, wrapping, media constraints) with the bounded exception of quality-standards § Responsive — never `overflow-x: clip` on `html`/`body` |
 | Fake UI-in-a-div screenshot | Ship a real capture/asset or remove the block |
 | Sticky sub-nav hidden by a banner | Offset by the banner's token height; split z-index roles instead of one raised value |
-| Unstyled UA selection / focus ring / caret / scrollbar | Theme from tokens per quality-standards § Browser chrome, or decline in `design-brief.md` |
+| UA focus ring failing SC 2.4.7/1.4.11 | Apply the DS focus-ring token per quality-standards § Browser chrome |
 
 ### Copy & data realism
 Placeholder content is a tell even when the layout is clean: fake-perfect numbers
@@ -101,14 +123,15 @@ second one catches what the first one misses.
 Both pass = the surface looks like *this product*, not "an app in this category".
 
 ### Mechanical pre-flight (countable — run, don't vibe)
-Each is pass/fail by counting or grep, not judgment:
-- **Em-dashes** in visible UI strings: exactly **0**.
-- **Eyebrows** (uppercase-tracked kickers): ≤ `ceil(sections / 3)`.
-- **Layout families** (hero, image+text split, card grid, bento, table…): no family more
+Each is counted or grepped, not judged. ENG and DS rows pass or fail; an AES count past
+its cap is a lead for the admission rule, not a failure:
+- [AES] **Em dashes** in visible UI strings: counted; DS only where the style guide bans them.
+- [AES] **Eyebrows** (uppercase-tracked kickers): ≤ `ceil(sections / 3)`.
+- [AES] **Layout families** (hero, image+text split, card grid, bento, table…): no family more
   than twice per page; never 3 consecutive image+text zigzags.
-- **Icons**: 0 emoji-as-icon; exactly one icon set imported.
-- **State presence in code**: default+hover+focus-visible+active+disabled for every interactive element; loading/error/empty where data delays or fails — an unreachable state's screenshot proves nothing.
-- **Form inputs**: no border-width shifts between states; focus ring from outline/ring (not border swap); consistent control height; reserved helper slot; disabled beyond opacity alone.
+- [DS] **Icons**: 0 emoji-as-icon; exactly one icon set imported.
+- [ENG] **State presence in code**: every state the role lattice requires (quality-standards § Focus & states) — an unreachable state's screenshot proves nothing.
+- [ENG] **Form inputs**: no border-width shifts between states; focus ring from outline/ring (not border swap); consistent control height; reserved helper slot; disabled beyond opacity alone.
 
 ## Code anti-slop (UI **and** backend)
 - **Over-defensive checks** — `if (x && x.length > 0)` repeated, layered null guards,

package/pack/generated/devin/skills/rite-polish/reference/harden-checklist.md

@@ -55,7 +55,8 @@ might miss.
 - **Screen reader:** every control has a name; live regions for async
   feedback; reading order matches visual order.
 - **Reduced motion:** `prefers-reduced-motion` removes non-essential motion
-  (no auto-carousel, no spring entrances).
+  (no auto-carousel, no spring entrances); auto-moving content over 5 s pauses under any
+  preference ([`quality-standards.md`](../../devrites-frontend-craft/reference/quality-standards.md) § Motion).
 - **High zoom:** 200% text zoom; layout doesn't break, nothing overflows.
 
 ## 4. Localisation / i18n

package/pack/generated/devin/skills/rite-polish/reference/ui.md

@@ -50,6 +50,13 @@ Goal: this feature looks and behaves like it belongs in *this* product.
    components, align flow shape with neighbors, consolidate duplication, remove
    obsolete styles created by this feature. Ask the user when a design-system
    principle is genuinely ambiguous: don't guess the system's intent.
+4. **Protected contracts:** normalization never changes URL slugs or anchors, form
+   field `name`/`autocomplete`/order, analytics or test IDs, or legal/consent copy
+   unless `spec.md` or `decisions.md` names the change. The wright contract lists
+   these identifiers, the returned diff is checked against them, and visible-label
+   renames are recorded in `polish-report.md`. **Failing case:** polish renames
+   `name="email"` to `emailAddress`; autofill and analytics break while role-query
+   tests pass.
 
 ## Phase 4: UI polish
 
@@ -74,7 +81,7 @@ path isn't polish.
 - [ ] **Alignment** perfect at every breakpoint
 - [ ] **Typography** hierarchy consistent; line length sane (65-75ch prose)
 - [ ] **Color & contrast**: semantic roles; text ≥ 4.5:1 (≥ 3:1 large/UI), WCAG 2.2 AA
-- [ ] **All interaction states**: hover, active, focus, disabled, selected
+- [ ] **All states** the role lattice requires (quality-standards § Focus & states)
 - [ ] **Focus states visible** and **keyboard navigation** works
 - [ ] **Loading** states clear; **empty** states welcoming with a next action
 - [ ] **Error** states helpful (what happened + how to recover); **success** states clear
@@ -82,7 +89,7 @@ path isn't polish.
 - [ ] **Copy & terminology** consistent with the product's vocabulary
 - [ ] **Icons** consistent set, properly sized and aligned
 - [ ] **Responsive** behavior correct across target viewports
-- [ ] **Target size** ≥ 24×24px (WCAG 2.2 AA); ≥ 44×44px for primary touch; **no drag-only** actions
+- [ ] **Target size** ≥ 24×24px (WCAG 2.2 AA); 44×44px for primary touch is a DS preference; **no drag-only** actions
 - [ ] **Motion** smooth (~60fps), purposeful; **reduced-motion** respected
 - [ ] **Performance basics:** no obvious jank, oversized images, or blocking work
 - [ ] **No console errors or warnings**
@@ -105,7 +112,9 @@ Cite the evidence in `browser-evidence.md`.
 ### Triage
 
 If it ships in 30 minutes, fix what users will notice (hierarchy,
-states, broken layout, bad copy) before micro-spacing. Don't introduce bugs
+states, broken layout, bad copy) before micro-spacing. A broken task, data loss or
+misleading state outranks every AES proposal
+([anti-ai-slop.md](anti-ai-slop.md) admission rule); AES work waits while one is open. Don't introduce bugs
 while polishing: re-prove after changes.
 
 ### Refinement modes (optional dials within Phase 4)