@windyroad/itil 0.47.10 → 0.47.11-preview.591

package/.claude-plugin/plugin.json

@@ -497,5 +497,5 @@
     }
   },
   "name": "wr-itil",
-  "version": "0.47.10"
+  "version": "0.47.11"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@windyroad/itil",
-  "version": "0.47.10",
+  "version": "0.47.11-preview.591",
   "description": "ITIL-aligned IT service management for Claude Code (problem, and future incident/change skills)",
   "bin": {
     "windyroad-itil": "./bin/install.mjs"

package/skills/capture-problem/REFERENCE.md

@@ -27,25 +27,27 @@ This is the structural rationale for:
 - **Title-only filename match** — body-content matches would be too noisy at the conservative threshold. Files whose filenames have zero overlap but whose bodies mention a keyword are almost always different tickets that happen to discuss similar topics. False-positive cost would dominate.
 - **No halt-on-match** — even when matches are found, capture proceeds. The duplicate gets resolved at next `/wr-itil:review-problems` (where the full-rank scan can detect and merge actual duplicates with the user in the loop).
 
-### Deferred-README-refresh contract
+### README refresh: inline (P199 Option 2 amendment, 2026-06-05)
 
-Capture-problem skips the P094 inline README refresh that `/wr-itil:manage-problem` Step 5 performs. The trade-off:
+Capture-problem stages `docs/problems/README.md` inline at Step 6, mirroring `/wr-itil:manage-problem` Step 5 P094 (refresh-on-create) + P134 (last-reviewed rotation). The previously-load-bearing "Deferred-README-refresh contract" was reversed by user direction recorded in P199 on 2026-05-31, then implemented on 2026-06-05.
 
-| Surface | Inline refresh (manage-problem) | Deferred refresh (capture-problem) |
-|---------|---------------------------------|-------------------------------------|
-| README authoritativeness | Always current at commit boundary | Lags new captures until next review |
-| Capture-time turn cost | +1-2 turns (regenerate + stage) | 0 turns |
-| WSJF ranking visibility | Immediate | Pending review |
-| Audit trail (commit) | One commit covers ticket + README | One commit covers ticket only |
-| README staleness window | None | Bounded by next review invocation |
+**Rationale for the reversal** (user direction):
+- The P165 README-refresh-discipline hook (shipped after the initial capture-problem design) blocks every capture commit that does not stage README. The P262 workaround (a `RISK_BYPASS: capture-deferred-readme` trailer) cleared the gate but kept the README transiently stale by design — a contract that always felt half-superseded by P165 reality.
+- Option 2 acknowledges reality: stage the README. The cost is one mechanical render-and-stage primitive (already proven in `/wr-itil:manage-problem`); the capture-time speed distinction from manage-problem comes from the wide-net duplicate grep + AskUserQuestion branches that capture-problem skips, not the README skip.
+- The `RISK_BYPASS: capture-deferred-readme` trailer is dropped from emission. The allow-list entry in `packages/itil/hooks/lib/readme-refresh-detect.sh::_README_REFRESH_BYPASS_TRAILERS` is retained as inert dead code for adopter compatibility (minimal-change discipline).
 
-The deferred contract is acceptable because:
+**Trade-off table (post-amendment)**:
 
-1. **The on-disk ticket inventory remains the source of truth**. README.md is a derived view — consumers that need WSJF rankings can re-derive from the ticket files (and `/wr-itil:list-problems` does exactly that on cache-stale fallback).
-2. **The trailing pointer in Step 7 is the user-visible signal** that the README is transiently stale. The user has explicit instructions for how to reconcile.
-3. **`/wr-itil:review-problems` Step 9b's auto-transition pass already re-rates deferred-placeholder tickets** (the literal string `(deferred — re-rate at next /wr-itil:review-problems)` is the keying signal). One review pass folds all captured-but-not-rated tickets into the ranking.
+| Surface | manage-problem | capture-problem (post-P199) |
+|---------|----------------|------------------------------|
+| README authoritativeness | Always current at commit boundary | Always current at commit boundary |
+| Capture-time turn cost | +1-2 turns (regenerate + stage) | +1-2 turns (same primitive) |
+| WSJF ranking visibility | Immediate (deferred-placeholder row) | Immediate (deferred-placeholder row) |
+| Audit trail (commit) | One commit covers ticket + README | One commit covers ticket + README |
+| README staleness window | None | None |
+| Distinguishing cost shape | Wide-net duplicate grep + multi-AskUserQuestion branches | Title-only 3-keyword grep + zero AskUserQuestion |
 
-The bound on the staleness window is "until the next `/wr-itil:review-problems` invocation". For sessions that capture and never review, the README stays stale — but the on-disk inventory is always correct, and the next session-start `wr-itil-reconcile-readme` preflight catches drift if it propagates beyond a single session.
+The on-disk ticket inventory remains the source of truth; `/wr-itil:list-problems` cache-stale fallback re-derives directly from ticket files when needed.
 
 ### No AskUserQuestion at all
 

package/skills/capture-problem/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: wr-itil:capture-problem
-description: Lightweight problem-capture skill for aside-invocation during foreground work — minimal duplicate-check, skeleton ticket file, single commit per capture, no inline README refresh. Defers full duplicate analysis and README refresh to /wr-itil:review-problems. Use this when the user (or agent mid-iter) wants to capture an observation quickly without disrupting current task flow. For full-intake new-problem creation, use /wr-itil:manage-problem.
+description: Lightweight problem-capture skill for aside-invocation during foreground work — minimal duplicate-check, skeleton ticket file, single commit per capture (covers new ticket + inline README refresh per P094 per P199 Option 2 amendment 2026-06-05). Defers full duplicate analysis to /wr-itil:review-problems. Use this when the user (or agent mid-iter) wants to capture an observation quickly without disrupting current task flow. For full-intake new-problem creation, use /wr-itil:manage-problem.
 allowed-tools: Read, Write, Edit, Bash, Grep, Glob, AskUserQuestion
 ---
 
@@ -46,6 +46,8 @@ This skill has **at most one direction-setting AskUserQuestion (the I12 derive-t
 
 Per ADR-013 Rule 6 fail-safe: every decision above resolves without interactive user input in non-interactive contexts. The derive-then-ratify AskUserQuestion fires only on derivation-failure (interactive surface) AND only when `--no-prompt` is absent (AFK callers pre-resolve via flags or halt-with-stderr-directive — never silently swallow the ratification gate).
 
+**ADR-013 Rule 6 carve-out audit (P352, 2026-06-06 amendment)**: the universal AFK default is **queue-and-continue** (queue the decision, continue the loop). The HALT-with-stderr-directive carve-outs in the Resolution table above (Empty `$ARGUMENTS`, AFK halt-without-flags) are documented deviations from the universal default, authorised by **ADR-074** (Confirm decision substance before building dependent work). Rationale: capture-problem creates a durable ticket artefact; auto-creating with derived-but-unratified persona/JTBD substance would build dependent work (the ticket file, the README row, the WSJF rank) on an unconfirmed decision — the precise harm ADR-074 prohibits. No-ticket-created is the user-pinned protection; the HALT is the persona-correct shape (JTBD-006's "queued for my return, not guessed at" is satisfied by the stderr directive surfacing on user return + the AFK loop continuing to the next problem).
+
 ## Steps
 
 ### 0. README reconciliation preflight (P118)
@@ -287,12 +289,27 @@ The deferred-placeholder pattern is load-bearing — `/wr-itil:review-problems`
 
 Single `Write` to `docs/problems/open/<NNN>-<kebab-title>.md` (per ADR-031 per-state-subdir layout). The P119 PreToolUse hook permits the Write because Step 2 set the marker.
 
-### 6. Commit per ADR-014 — single commit, no README refresh
+### 6. Commit per ADR-014 — single commit, inline README refresh (P094)
+
+**P199 / Option 2 amendment (2026-06-05).** This step previously skipped the README refresh and emitted a `RISK_BYPASS: capture-deferred-readme` trailer to clear the P165 README-refresh gate. The user-directed Option 2 resolution (recorded 2026-05-31 on P199) kills the deferred-README-refresh contract: capture-problem now stages `docs/problems/README.md` inline, mirroring `/wr-itil:manage-problem` Step 5 P094 (refresh-on-create) + P134 (last-reviewed rotation). The trailer is dropped from the commit; the allow-list entry in `packages/itil/hooks/lib/readme-refresh-detect.sh::_README_REFRESH_BYPASS_TRAILERS` is retained as inert dead code (minimal-change discipline — future adopters that registered against the token continue to work). Authority: P199 Option 2 user direction + ADR-032 amendment + ADR-014 bypass-token-table amendment (same single coherent commit).
+
+#### README.md refresh on new ticket (P094)
+
+After writing the new `.open.md` file at Step 5, regenerate `docs/problems/README.md` to insert the new ticket's row into the WSJF Rankings, and stage the refreshed README in the same commit as the new ticket. The mechanism is **inline at this execution site per P331** — not deferred via cross-reference — so a single-pass agent reading Step 6 does not silently skip the archive step (the canonical P331 silent-skip regression).
 
-**Stage list**: ONLY the new ticket file. **Do NOT** stage `docs/problems/README.md`. The deferred-README-refresh contract is the load-bearing distinction from `/wr-itil:manage-problem` — capture-time speed depends on skipping the regenerate-and-stage cycle.
+**Mechanism**: use the same rendering rules as `/wr-itil:manage-problem` Step 5 P094 / Step 7 P062 (glob `docs/problems/*.open.md` / `*.known-error.md` / `*.verifying.md` / `*.parked.md` AND the per-state-subdir layout `docs/problems/open/*.md` / `docs/problems/known-error/*.md` / `docs/problems/verifying/*.md` / `docs/problems/parked/*.md`; rank open/known-error by WSJF; list verifyings in the Verification Queue ordered by Released date ASC per P150; list parkeds in the Parked section). The refresh is a **render, not a re-rank** — existing WSJF values on the other ticket files are trusted per P062's established discipline. Only the new ticket's own (deferred-placeholder) WSJF is consumed from its freshly-written file. **WSJF Rankings tier + tie-break sort** (P138 + ADR-076) and **Verification Queue sort direction** (P150) and **Likely-verified cell shape** (P186) all follow the canonical render rules — see `/wr-itil:manage-problem` Step 5 P094 block for the full prose; drift here re-opens those tickets.
+
+**P134 last-reviewed rotation** — inline at this execution site (not deferred to a § subsection) per P331 silent-skip discipline. MUST execute IN ORDER:
+
+1. **Read** line 3 of `docs/problems/README.md`: `awk 'NR==3' docs/problems/README.md`.
+2. **Append-if-non-empty (BEFORE step 3, not after)** — if line 3 is non-empty AND not a same-session same-verb near-duplicate of the new fragment, append the existing line 3 verbatim to `docs/problems/README-history.md` under a `## YYYY-MM-DD` heading (creating the heading on first append for that date; subsequent same-day appends nest under the existing heading). Run this BEFORE the Edit-tool rewrite in step 3 — Edit's replace pattern destroys the displaced content otherwise.
+3. **Rewrite** line 3 of `docs/problems/README.md` with the new fragment of form `> Last reviewed: YYYY-MM-DD **P<NNN> captured** — <one-line title> (lightweight aside via /wr-itil:capture-problem)`. Soft cap ≤ 1024 bytes per fragment; hard ceiling 5120 bytes per ADR-040 Tier 3 envelope.
+4. **Stage all three** — `git add docs/problems/open/<NNN>-<kebab-title>.md docs/problems/README.md docs/problems/README-history.md` so the same single commit per ADR-014 captures the new ticket + refreshed README + (when line-3 displaced) history. Omit `README-history.md` from the stage list when no line-3 displacement occurred (no untracked diff). Canonical rationale anchor: `/wr-itil:manage-problem` § Last-reviewed line discipline (P134) subsection.
 
 ```bash
-git add docs/problems/open/<NNN>-<kebab-title>.md
+git add docs/problems/open/<NNN>-<kebab-title>.md docs/problems/README.md
+# If line-3 was rotated above, also:
+git add docs/problems/README-history.md
 ```
 
 Satisfy the commit gate per ADR-014 — same two-path pattern as manage-problem Step 11:
@@ -300,20 +317,17 @@ Satisfy the commit gate per ADR-014 — same two-path pattern as manage-problem
 - **Primary**: delegate to subagent type `wr-risk-scorer:pipeline` via the Agent tool.
 - **Fallback**: invoke `/wr-risk-scorer:assess-release` via the Skill tool when the subagent type is unavailable in the current tool surface.
 
-Land the commit via the **`wr-risk-scorer-restage-commit`** helper — atomic re-stage + commit in a single bash call (P326 wrapper). The Agent-tool delegation above can silently clear the index; the helper re-adds the supplied path, asserts non-empty staging, then runs `git commit` with the supplied `-m` args. The `RISK_BYPASS: capture-deferred-readme` trailer rides as a second `-m` paragraph so the literal token appears in the resulting commit-message command string the PreToolUse hook inspects:
+Land the commit via the **`wr-risk-scorer-restage-commit`** helper — atomic re-stage + commit in a single bash call (P326 wrapper). The Agent-tool delegation above can silently clear the index; the helper re-adds the supplied paths, asserts non-empty staging, then runs `git commit` with the supplied `-m` args:
 
 ```bash
 wr-risk-scorer-restage-commit \
   -m "docs(problems): capture P<NNN> <title>" \
-  -m "RISK_BYPASS: capture-deferred-readme" \
-  -- docs/problems/open/<NNN>-<kebab-title>.md
+  -- docs/problems/open/<NNN>-<kebab-title>.md docs/problems/README.md
+# If README-history.md was modified, append it to the path list:
+#   -- docs/problems/open/<NNN>-<kebab-title>.md docs/problems/README.md docs/problems/README-history.md
 ```
 
-The `capture` verb in the message is the audit signal that this ticket landed via the lightweight aside path (vs. `open` for manage-problem's full intake).
-
-**Why the trailer (P262)**: the P165 README-refresh-discipline hook (`packages/itil/hooks/itil-readme-refresh-discipline.sh`) treats any newly-staged ticket file as ranking-bearing and DENIES a `git commit` that does not also stage `docs/problems/README.md`. That enforcement is correct for `/wr-itil:manage-problem`'s full-intake path (P094 refresh-on-create) but conflicts with this skill's deliberate deferred-README-refresh contract. The `RISK_BYPASS: capture-deferred-readme` trailer is a registered allow-list token (P265 mechanism; registry of record is the ADR-014 commit-message bypass-token table) that clears the **README-refresh gate ONLY** — the commit is still risk-scored normally (`risk-score-commit-gate.sh` does not recognise this token).
-
-Do NOT drop the trailer and stage the README instead — that would silently abandon the deferred-README-refresh contract (the capture-time-speed distinction this skill exists to provide per ADR-032). The README is reconciled at the next `/wr-itil:review-problems` per Step 7's trailing pointer.
+The `capture` verb in the message is the audit signal that this ticket landed via the lightweight aside path (vs. `open` for manage-problem's full intake). The P165 README-refresh-discipline hook now allows the commit naturally because the README is staged — no `RISK_BYPASS` trailer needed.
 
 ### 7. Report
 
@@ -331,15 +345,15 @@ After the commit, report:
 
   | `preflight_reason`                                | Trailing-pointer shape                                                                                |
   |---------------------------------------------------|--------------------------------------------------------------------------------------------------------|
-  | `no-deferred-placeholders` / `below-threshold ...` / `fresh-readme ...` | Default (low-priority) pointer: *"Run `/wr-itil:review-problems` next to fold P\<NNN\> into the WSJF rankings, re-rate the deferred placeholders, and refresh `docs/problems/README.md`."* |
-  | `no-readme count=<N>`                              | **Highlighted (actionable) pointer**: *"⚠ `<N>` deferred-placeholder ticket(s) have accumulated AND `docs/problems/README.md` is missing/malformed — run `/wr-itil:review-problems` NOW to rebuild the README and re-rate placeholders."* |
-  | `stale-readme count=<N> age=<X>s threshold=<Y>s`   | **Highlighted (actionable) pointer**: *"⚠ `<N>` deferred-placeholder ticket(s) have accumulated AND the WSJF Rankings cadence is `<X>` days stale (> 7-day threshold) — run `/wr-itil:review-problems` NOW to re-rate placeholders and refresh `docs/problems/README.md`."* |
+  | `no-deferred-placeholders` / `below-threshold ...` / `fresh-readme ...` | Default (low-priority) pointer: *"Run `/wr-itil:review-problems` next to re-rate the deferred Priority/Effort placeholders on P\<NNN\>."* (README is now refreshed inline at Step 6 per P199 Option 2 — the pointer no longer names a README-refresh action in the default shape.) |
+  | `no-readme count=<N>`                              | **Highlighted (actionable) pointer**: *"⚠ `<N>` deferred-placeholder ticket(s) have accumulated AND `docs/problems/README.md` is missing/malformed — run `/wr-itil:review-problems` NOW to rebuild the README and re-rate placeholders."* (Fires only when README is genuinely missing/malformed despite this skill's inline refresh — a drift class the helper still surfaces.) |
+  | `stale-readme count=<N> age=<X>s threshold=<Y>s`   | **Highlighted (actionable) pointer**: *"⚠ `<N>` deferred-placeholder ticket(s) have accumulated AND the WSJF Rankings cadence is `<X>` days stale (> 7-day threshold) — run `/wr-itil:review-problems` NOW to re-rate placeholders."* (Inline refresh at Step 6 freshens the README mtime on every capture, so this shape now fires only when captures are absent for > 7 days — a real cadence-stale signal, not capture-driven drift.) |
 
-  **Why conditional, not auto-dispatch** (ADR-032 + JTBD-001): capture-problem is intentionally lightweight per ADR-032 P155 amendment. Auto-dispatching review-problems from capture would re-introduce the ~10-turn ceremony the lightweight aside is engineered to avoid. The conditional pointer preserves the speed-of-capture contract while surfacing the signal "the README is now MORE than transiently stale" when both axes hit threshold. The user picks when to absorb the re-rate cost.
+  **Why conditional, not auto-dispatch** (ADR-032 + JTBD-001): capture-problem is intentionally lightweight per ADR-032 P155 amendment. Auto-dispatching review-problems from capture would re-introduce the ~10-turn ceremony the lightweight aside is engineered to avoid. The conditional pointer surfaces the signal "deferred-placeholder backlog has grown AND the cadence axis hit threshold" when both axes fire. The user picks when to absorb the re-rate cost.
 
   **Fail-soft**: any error in the helper invocation MUST NOT block the report — fall back to the default pointer shape.
 
-The trailing pointer is **not optional** — it is the user-visible signal that the README is transiently stale and how to reconcile it. The conditional highlight (P271) escalates the signal when the deferred-placeholder backlog AND the cadence axis both hit threshold. Drift here re-opens P271.
+The trailing pointer is **not optional** — it is the user-visible signal for deferred-placeholder re-rating cadence. The conditional highlight (P271) escalates the signal when the deferred-placeholder backlog AND the cadence axis both hit threshold. Drift here re-opens P271.
 
 <!-- @jtbd JTBD-001 (Enforce Governance Without Slowing Down — conditional highlight escalates the signal without forcing a flow break) -->
 
@@ -353,7 +367,7 @@ The trailing pointer is **not optional** — it is the user-visible signal that
 | Type-tag prompt | RETIRED (P287, 2026-06-02) | RETIRED (P287, 2026-06-02) — the technical/user-business axis was removed as redundant with RFC/Story persona-anchoring per ADR-060 Phase 4 |
 | JTBD-trace + persona | Step 4-equivalent ingestion path | Step 1.5b I12 derive-then-ratify dispatch (ADR-060 Amendment 2026-06-02) — flag pre-resolution (`--jtbd=` / `--persona=`) silent-proceeds; lexical detection of JTBD-NNN citations silent-proceeds; cited-JTBD persona derivation silent-proceeds; derivation-failure → AskUserQuestion proposal with REJECT (= problem rejected; no ticket) / option-pick (acceptance) / free-text correction (correction-as-acceptance); AFK callers pre-resolve via flags or halt-with-stderr-directive when `--no-prompt` |
 | AskUserQuestion authority | Multiple branches (deviation-approval / direction-setting / taste / mechanical) | One direction-setting branch on the I12 derive-failure fallback (ADR-044 category 1); silent-framework (category 4) on derive-success paths; zero control-flow branches keyed on the answer's substance (REJECT/option-pick/correction are uniform handlers) |
-| README refresh | P094 inline (regenerate + stage in same commit) | Deferred to next `/wr-itil:review-problems` |
+| README refresh | P094 inline (regenerate + stage in same commit) | P094 inline (regenerate + stage in same commit) — P199 Option 2 amendment 2026-06-05; previously deferred to next `/wr-itil:review-problems` |
 | Status transitions | Step 7 owns Open → Known Error → Verifying → Closed | Out of scope (creation only) |
 | Commit grain | One commit per intake (or per split-concern set) | One commit per capture |
 | Use case | Full-intake new problem; user wants to walk the flow | Aside-invocation; capture-and-continue |
@@ -366,8 +380,9 @@ The two skills share the `/tmp/manage-problem-grep-${SESSION_ID}` create-gate ma
 - **P014** (`docs/problems/open/014-aside-invocation-for-governance-skills.md`) — parent / master tracker.
 - **P078** — capture-on-correction OFFER pattern; depends on capture-problem shipping.
 - **P119** — manage-problem create-gate hook; capture-problem composes with the same marker.
-- **P262** — the P165 README-refresh-discipline hook conflicted with this skill's deferred-README-refresh contract (Step 6 "do NOT stage README" was denied by the hook on every capture commit). Resolved by the `RISK_BYPASS: capture-deferred-readme` allow-list token (Step 6 trailer above); clears the README-refresh gate only, not the risk-score gate.
-- **P265** — the RISK_BYPASS-trailer allow-list mechanism in `readme-refresh-detect.sh` that P262's `capture-deferred-readme` token registers into.
+- **P199** (`docs/problems/verifying/199-...md`) — Option 2 amendment 2026-06-05: kill the deferred-README-refresh contract; Step 6 now stages README inline per P094. User direction recorded 2026-05-31 in the ticket. This SKILL change rides with the ADR-032 + ADR-014 amendments in the same coherent commit.
+- **P262** (closed) — the P165 README-refresh-discipline hook conflicted with this skill's previous deferred-README-refresh contract. The prior workaround was the `RISK_BYPASS: capture-deferred-readme` allow-list token. Superseded by P199 Option 2 (2026-06-05) — capture-problem now stages README inline and the trailer is no longer emitted. The allow-list entry in `packages/itil/hooks/lib/readme-refresh-detect.sh::_README_REFRESH_BYPASS_TRAILERS` is retained as inert dead code (minimal-change discipline; adopter compatibility).
+- **P265** — the RISK_BYPASS-trailer allow-list mechanism in `readme-refresh-detect.sh`. Still in force for the `adr-031-migration` token; the `capture-deferred-readme` entry is now inert (no live emitter) but registered for adopter compatibility.
 - **P170** (`docs/problems/known-error/170-problem-tickets-strain-as-fixes-decompose-into-multiple-coordinated-changes-need-rfc-framework.md`) — RFC framework driver; Slice 4 B7.T3 / item 8c historically authored the type-classification prompt at Step 1.5 (RETIRED by P287, 2026-06-02).
 - **P176** — agent-side I2 (no type-branching) coverage gap on the SKILL.md surface. P287 retires the type axis altogether; the regression guard is preserved under `packages/itil/scripts/test/no-type-regression-guard.bats` (asserting the `**Type**:` field is GONE from skeleton templates).
 - **P287** (`docs/problems/.../287-remove-technical-user-business-type-classification-from-problems-redundant-with-rfc-persona-anchoring.md`) — the user direction (twice-confirmed 2026-05-25 + 2026-06-02) that retired Step 1.5 Type classification; ADR-060 amendment substance (I12 replacement, Phase-4 rework) queued for user re-confirmation per ADR-074.

package/skills/manage-problem/SKILL.md

@@ -179,7 +179,7 @@ What "work" means depends on the problem's status:
    Exit 0 = unconfirmed (born without `human-oversight: confirmed`, not superseded) → the guard fires for that ADR. Exit 1 = confirmed or superseded → OK to build. Exit 2 = not found → treat as not-a-blocker (surface in the report).
 3. **If any referenced decision is unconfirmed**: do NOT implement yet. Surface its **substance** (the chosen option the ADR records — not a grain/meta question) for human confirmation:
    - **Interactive**: `AskUserQuestion` presenting the ADR's Decision Outcome + Considered Options so the user confirms / amends / rejects the substantive choice. On confirm, the recording skill writes the `human-oversight: confirmed` marker (ADR-066) before the build proceeds.
-   - **AFK** (`/wr-itil:work-problems` orchestrator): NEVER ask mid-loop — queue the substance to the iteration's `outstanding_questions` (ADR-044 AFK carve-out) and skip the build; do not guess.
+   - **AFK** (`/wr-itil:work-problems` orchestrator): NEVER ask mid-loop — queue the substance to the iteration's `outstanding_questions` (ADR-044 AFK carve-out) and skip the build; do not guess. This is the **queue-and-continue** universal default per ADR-013 Rule 6 (P352, 2026-06-06 amendment): the iter queues the substance + advances; the orchestrator main turn surfaces the queued question at loop end via the Step 2.5 batched AskUserQuestion.
 4. This ask is **ADR-044 category-1 direction-setting** and is EXCLUDED from the lazy-AskUserQuestion regression metric (it is legitimate, not lazy). The trigger is narrow — detection is mechanical (the predicate); only genuine unconfirmed decisions about to be built on fire it. Do NOT over-fire on confirmed/superseded/obvious decisions (inverse-P078 / P132 guard). A born-`proposed` marker is fine for *recording*; it is not a licence to *build* (ADR-066 carve-out).
 
 The Phase 2 working-the-problem traversal makes "implement the fix" concretely traceable via stories (per ADR-060 lines 300-320). Replaces the prior vague "implement the fix following the project's development workflow" with a deterministic problem → RFC → story dispatch:
@@ -496,6 +496,8 @@ Before writing the problem file, perform a concern-boundary analysis on the gath
 
 **Non-interactive fallback**: When `AskUserQuestion` is unavailable (e.g., non-interactive/AFK mode), automatically split into separate problems and note the auto-split in output. Do not block creation.
 
+**ADR-013 Rule 6 carve-out audit (P352, 2026-06-06 amendment)**: the universal AFK default is **queue-and-continue**; this site is a documented **AUTO-DEFAULT** carve-out. Authorising principle: policy-authorised safe default per ADR-044 category 4 (silent framework). Splitting is fully reversible (manual combine via Related cross-references + WSJF re-rank), the framework's lifecycle model rewards explicit per-concern WSJF ranking, and "split when in doubt" is the persona-correct safe heuristic for JTBD-006 — the loop progresses, over-splits are cheap to combine, and halt would cost more loop throughput than the over-split risk. Symmetric with the parallel `/wr-architect:create-adr` Step 1 multi-decision auto-split (same authority, same rationale).
+
 **Split implementation**: When splitting, assign consecutive IDs (e.g., if next ID is 035, create P035 and P036). Create each problem file independently. Cross-reference each ticket in the other's "Related" section.
 
 **Scope**: This step applies only to **new problem creation** (steps 2–5). It does NOT apply to updates, status transitions, or reviews of existing tickets.

package/skills/report-upstream/SKILL.md

@@ -401,10 +401,11 @@ Open the issue:
 gh issue create \
   --repo "${UPSTREAM_OWNER_REPO}" \
   --title "${TITLE_PREFIXED_BY_TEMPLATE}" \
-  --body "${FILLED_BODY}" \
-  --label "${MATCHED_TEMPLATE_LABEL_IF_ANY}"
+  --body "${FILLED_BODY}"
 ```
 
+Do **not** pass `--label` on this call (P207). Labels are supplied by the matched template's YAML `labels:` frontmatter and applied by GitHub when the issue form is submitted; passing `--label <name>` for a label that has not been pre-created on the upstream repo causes `gh issue create` to hard-fail with `could not add label: '<name>' not found`. The flag is redundant when the matched template carries `labels:` and a hard-fail surface when it does not. If the upstream has no matched template at all (structured-default body path, Step 3 preference order item 7), omit labels entirely — leave triage to the upstream maintainer's existing routing.
+
 Capture the returned issue URL. The voice-tone gate per ADR-028 may delegate-and-retry; treat this as expected (see "Voice-tone gate interaction" above). Proceed to Step 7 once the issue is created.
 
 ### 5c. Comment path (P070)

package/skills/review-problems/SKILL.md

@@ -134,7 +134,7 @@ Per ADR-062 (peer of ADR-024). Polls configured upstream channels, runs each unm
 Read `docs/problems/.upstream-channels.json`. Branch on state:
 
 - **File exists and parses cleanly** → continue to 4.5b with the parsed `channels[]` list.
-- **File exists but is malformed JSON** → log an advisory note (`channel config malformed JSON; inbound-discovery skipped this pass — fix the file then re-invoke`) and skip Step 4.5. This is genuine fail-soft because the user already SHIPPED a config and the malformation is an editing artefact best resolved by the user reading the parse error; auto-rewriting their file would destroy their work.
+- **File exists but is malformed JSON** → log an advisory note (`channel config malformed JSON; inbound-discovery skipped this pass — fix the file then re-invoke`) and skip Step 4.5. **ADR-013 Rule 6 carve-out (P352, 2026-06-06 amendment)**: this is a documented SKIP carve-out (deviation from the universal queue-and-continue default). Authorising principle: user-shipped artefact protection — the user already SHIPPED a config and the malformation is an editing artefact best resolved by the user reading the parse error; auto-rewriting their file (queue-then-overwrite-on-return) would destroy their work. The advisory note IS the queued surface for user attention on next interactive session; the loop continues. Same shape as a parse-error halt at a user-owned file boundary.
 - **File does NOT exist** → run the **auto-bootstrap routine** below per P351 / JTBD-101 / JTBD-007. **Adopters who never want to configure inbound-discovery** can keep `.upstream-channels.json` absent by answering `decline` at the interactive prompt OR allowing the AFK-mode outstanding-question to lapse; the absence stays zero-ceremony-tax (ADR-062 § Downstream-adopter non-obligation), but the silent skip is replaced by an explicit one-time-per-session prompt so the adopter has a visible signal that the inbound-discovery capability exists. <!-- @jtbd JTBD-101 (Extend the Suite — deliver-installed-features signal) --> <!-- @jtbd JTBD-007 (Keep Plugins Current — process reports what configured) --> <!-- @problem P351 (auto-bootstrap on missing precondition config) -->
 
 **Auto-bootstrap routine (P351)**: replaces the prior "missing file → silent skip" behaviour. The routine branches on AskUserQuestion availability per ADR-013 Rule 6 + ADR-044 category 1 (direction-setting):
@@ -149,6 +149,9 @@ Read `docs/problems/.upstream-channels.json`. Branch on state:
   - On `Decline permanently (write empty channels stub)`: write `{"channels": [], "ttl_seconds": 86400, "declined_at": "<ISO>"}` so future invocations parse cleanly + skip silently. Per ADR-062 § Downstream-adopter non-obligation — the empty-channels stub IS the documented "I never want this" surface.
 
 - **AFK mode** (AskUserQuestion unavailable, e.g. invoked from `/wr-itil:work-problems`):
+
+  **ADR-013 Rule 6 universal default (P352, 2026-06-06 amendment)** — queue-and-continue. This branch is the canonical exemplar: P351 lifted this site from the prior "missing file → silent skip" anti-pattern to queue-and-continue. The pattern below is the model the rest of the suite follows.
+
   1. Log advisory (`inbound-discovery: channel config absent; queued config-direction outstanding_question, skipping THIS pass to allow other passes to proceed`).
   2. Queue a `direction` entry per `/wr-itil:work-problems` SKILL.md Step 5 `outstanding_questions` schema (ADR-044 category 1):
 

package/skills/scaffold-intake/SKILL.md

@@ -164,6 +164,8 @@ When all three checks pass, the host emits a one-shot `AskUserQuestion` prompt w
 
 **AFK fail-safe**: when the host is invoked from an AFK orchestrator, do NOT fire the prompt. Append a one-line "pending intake scaffold" note to the iteration report and continue. The user catches up on next interactive session.
 
+**ADR-013 Rule 6 universal default (P352, 2026-06-06 amendment)**: this IS queue-and-continue — the iteration-report note is the queued surface; the loop advances. Persona-correct for JTBD-006 ("queued for my return, not guessed at"). Not a carve-out — this is the canonical default shape.
+
 ### Trigger 2: Pre-publish PreToolUse gate (hard stop)
 
 `packages/itil/hooks/pre-publish-intake-gate.sh` matches `npm publish` and `gh pr merge ... changeset-release/*` and denies if any of the five intake files are missing AND the decline marker is absent AND `INTAKE_BYPASS` is not set.

package/skills/work-problems/SKILL.md

@@ -511,7 +511,7 @@ rm -f "$ITER_JSON"
 
 1. **Context**: this is one iteration of the AFK work-problems loop. The user is AFK. The orchestrator selected `P<NNN> (<title>)` as the highest-WSJF actionable ticket.
 2. **Task**: apply the `/wr-itil:manage-problem` workflow for `work highest WSJF problem that can be progressed non-interactively as the user is AFK`. Follow manage-problem SKILL.md verbatim, including architect / jtbd / style-guide / voice-tone gate reviews and the commit gate (manage-problem Step 11). Because this subprocess has the Agent tool in its own surface, the normal review-via-subagent paths work — no inline-verdict fallback needed.
-3. **Constraints**: commit the completed work per ADR-014. Do NOT push, do NOT run `push:watch`, do NOT run `release:watch` — the orchestrator's Step 6.5 owns release cadence. Do NOT invoke `capture-*` background skills mid-iter (AFK carve-out — ADR-032), **EXCEPT for retro-surfaced observations of recurring class-of-behaviour** — those route to `/wr-itil:capture-problem` per the **P342 mechanical-stage carve-out** (see retro-on-exit constraint #4 below; same trust-boundary as `/wr-retrospective:run-retro` Step 4a verification close-on-evidence — P342). Do NOT use `ScheduleWakeup` under any circumstance (P083 — iteration workers must not self-reschedule). **NEVER call `AskUserQuestion` mid-loop in AFK** (P135 / ADR-044): direction / deviation-approval / one-time-override / silent-framework observations queue at `ITERATION_SUMMARY.outstanding_questions` for loop-end batched presentation. **This includes the manage-problem substance-confirm-before-build guard (ADR-074 (Confirm a decision's substance before building dependent work)):** when the propose-fix step detects that the fix builds on a born-`proposed` decision whose substance is unconfirmed (via `wr-architect-is-decision-unconfirmed`), the iter does NOT implement on it and does NOT ask mid-loop — it queues a `category: "direction"` entry naming the unconfirmed ADR + its Decision Outcome for loop-end confirmation, and routes the ticket to `action: skipped`, `skip_reason_category: user-answerable`. Building on the unconfirmed substance instead (or guessing the choice) is the P315 failure this guard exists to prevent. The queued substance-confirm is a legitimate cat-1 direction ask — it is NOT counted as lazy in the Step 2d Ask Hygiene Pass (ADR-074 lazy-count exclusion). Per-iter `AskUserQuestion` calls are sub-contracting framework-resolved decisions back to the user (lazy deferral per Step 2d Ask Hygiene Pass classification). Non-interactive defaults apply per ADR-013 Rule 6 + ADR-044's framework-resolution boundary. **Treat the user as transient** (P130): even when observably present at orchestrator dispatch time, the user may answer one question and disappear for hours; presence is not a reliable signal and is not the goal. The iter's job is to progress the ticket and accumulate questions for batched surfacing — not to ask "is it OK to proceed?" at a mechanical-stage boundary. **Do NOT poll `bats` output with a bats-console-summary regex against TAP-format output** (P146 — bash until-loop-deadlock antipattern). The bats-console-summary line `<N> tests, <M> failures` is emitted ONLY by bats's *default* (non-TAP) formatter; `bats --tap` does not emit a console summary, so a polling loop of shape `until [ -f $OUT ] && grep -qE '^[0-9]+ tests?,' $OUT; do sleep 5; done` spins forever after bats completes (silent deadlock — no error, no exit; recovery requires manual SIGTERM with metadata loss per the P146/P147 stuck-before-emit subclass). When you need to wait on a backgrounded bats run, prefer `wait $bg_pid` (Unix idiom — completion signaled by process exit, no regex required) or, for the Bash tool, `run_in_background=true` + `BashOutput` polling on the tool's exit-state field rather than regex-poll on stdout. If you genuinely must regex-poll TAP output, anchor on the TAP plan line `^[0-9]+\.\.[0-9]+` (e.g. `1..1455`) — TAP's plan line is emitted on completion and is format-stable across bats versions; the bats-console-summary line is not. The console-summary vs TAP-format divergence is the load-bearing detail: `bats` and `bats --tap` produce structurally different stdout, and the antipattern assumes the former when iter dispatch typically uses the latter. **Do NOT poll subprocess completion with `pgrep -f '<pattern>'` inside an `until` / `while` loop** (P232 — self-referential pgrep deadlock; sibling variant of P146). `pgrep -f` matches against the FULL command line of every running process, so the polling loop's own `zsh -c` argument (which contains the literal `pgrep -f '<pattern>'` text) matches itself; with multiple concurrent polling loops, each loop matches the others and spins forever. Worked example of the antipattern: `until ! pgrep -f 'bats --recursive' > /dev/null 2>&1; do sleep 5; done` — the 2026-05-16 P232 deadlock witness; 4 concurrent polling loops each matched the others' command lines while no actual bats process ran; 45 min wall-clock + $20-30 wasted before manual SIGTERM. The same self-reference shape applies to `while pgrep -f ...; do sleep; done` and to `until ! pkill -0 -f '<pattern>'` / `while pkill -0 -f '<pattern>'` (signal-0 polling). The structural fix is the same as P146: prefer `wait $bg_pid` (Unix idiom — shell-native completion signal, no regex / no pgrep) or Bash-tool `run_in_background=true` + `BashOutput` polling (harness-tracked completion state). The hook `packages/itil/hooks/itil-bash-polling-antipattern-detect.sh` denies these shapes at PreToolUse:Bash, but the prompt rule belongs here too — structural enforcement + prompt discipline together close the class.
+3. **Constraints**: commit the completed work per ADR-014. Do NOT push, do NOT run `push:watch`, do NOT run `release:watch` — the orchestrator's Step 6.5 owns release cadence. Do NOT invoke `capture-*` background skills mid-iter (AFK carve-out — ADR-032), **EXCEPT for retro-surfaced observations of recurring class-of-behaviour** — those route to `/wr-itil:capture-problem` per the **P342 mechanical-stage carve-out** (see retro-on-exit constraint #4 below; same trust-boundary as `/wr-retrospective:run-retro` Step 4a verification close-on-evidence — P342). Do NOT use `ScheduleWakeup` under any circumstance (P083 — iteration workers must not self-reschedule). **NEVER call `AskUserQuestion` mid-loop in AFK** (P135 / ADR-044): direction / deviation-approval / one-time-override / silent-framework observations queue at `ITERATION_SUMMARY.outstanding_questions` for loop-end batched presentation. **This includes the manage-problem substance-confirm-before-build guard (ADR-074 (Confirm a decision's substance before building dependent work)):** when the propose-fix step detects that the fix builds on a born-`proposed` decision whose substance is unconfirmed (via `wr-architect-is-decision-unconfirmed`), the iter does NOT implement on it and does NOT ask mid-loop — it queues a `category: "direction"` entry naming the unconfirmed ADR + its Decision Outcome for loop-end confirmation, and routes the ticket to `action: skipped`, `skip_reason_category: user-answerable`. Building on the unconfirmed substance instead (or guessing the choice) is the P315 failure this guard exists to prevent. The queued substance-confirm is a legitimate cat-1 direction ask — it is NOT counted as lazy in the Step 2d Ask Hygiene Pass (ADR-074 lazy-count exclusion). Per-iter `AskUserQuestion` calls are sub-contracting framework-resolved decisions back to the user (lazy deferral per Step 2d Ask Hygiene Pass classification). Non-interactive defaults apply per ADR-013 Rule 6 + ADR-044's framework-resolution boundary. **Treat the user as transient** (P130): even when observably present at orchestrator dispatch time, the user may answer one question and disappear for hours; presence is not a reliable signal and is not the goal. The iter's job is to progress the ticket and accumulate questions for batched surfacing — not to ask "is it OK to proceed?" at a mechanical-stage boundary. **Do NOT poll `bats` output with a bats-console-summary regex against TAP-format output** (P146 — bash until-loop-deadlock antipattern). The bats-console-summary line `<N> tests, <M> failures` is emitted ONLY by bats's *default* (non-TAP) formatter; `bats --tap` does not emit a console summary, so a polling loop of shape `until [ -f $OUT ] && grep -qE '^[0-9]+ tests?,' $OUT; do sleep 5; done` spins forever after bats completes (silent deadlock — no error, no exit; recovery requires manual SIGTERM with metadata loss per the P146/P147 stuck-before-emit subclass). When you need to wait on a backgrounded bats run, prefer `wait $bg_pid` (Unix idiom — completion signaled by process exit, no regex required) or, for the Bash tool, `run_in_background=true` + `BashOutput` polling on the tool's exit-state field rather than regex-poll on stdout. If you genuinely must regex-poll TAP output, anchor on the TAP plan line `^[0-9]+\.\.[0-9]+` (e.g. `1..1455`) — TAP's plan line is emitted on completion and is format-stable across bats versions; the bats-console-summary line is not. The console-summary vs TAP-format divergence is the load-bearing detail: `bats` and `bats --tap` produce structurally different stdout, and the antipattern assumes the former when iter dispatch typically uses the latter. **Do NOT poll subprocess completion with `pgrep -f '<pattern>'` inside an `until` / `while` loop** (P232 — self-referential pgrep deadlock; sibling variant of P146). `pgrep -f` matches against the FULL command line of every running process, so the polling loop's own `zsh -c` argument (which contains the literal `pgrep -f '<pattern>'` text) matches itself; with multiple concurrent polling loops, each loop matches the others and spins forever. Worked example of the antipattern: `until ! pgrep -f 'bats --recursive' > /dev/null 2>&1; do sleep 5; done` — the 2026-05-16 P232 deadlock witness; 4 concurrent polling loops each matched the others' command lines while no actual bats process ran; 45 min wall-clock + $20-30 wasted before manual SIGTERM. The same self-reference shape applies to `while pgrep -f ...; do sleep; done` and to `until ! pkill -0 -f '<pattern>'` / `while pkill -0 -f '<pattern>'` (signal-0 polling). The structural fix is the same as P146: prefer `wait $bg_pid` (Unix idiom — shell-native completion signal, no regex / no pgrep) or Bash-tool `run_in_background=true` + `BashOutput` polling (harness-tracked completion state). The hook `packages/itil/hooks/itil-bash-polling-antipattern-detect.sh` denies these shapes at PreToolUse:Bash, but the prompt rule belongs here too — structural enforcement + prompt discipline together close the class. **If the fix changes shippable code or package behaviour** (any path under `packages/<plugin>/{src,bin,hooks,skills,scripts,lib,agents}` excluding test paths — `test/`, `hooks/test/`, `scripts/test/` — and excluding `README.md` + `docs/*.md`), **the iter MUST author a `.changeset/*.md` entry in the same single ADR-014-grain commit as the fix** (the changeset names the bumping plugin via the YAML frontmatter `"@windyroad/<plugin>": <patch|minor|major>` per the changesets-action contract). **Doc-only changes** (under `docs/`, `*.md`) **and test-only changes** (under any `test/` path) **that ship no behaviour MAY omit the changeset**. The orchestrator's Step 6.5 release-cadence drain runs `release:watch` only when `.changeset/` is non-empty after push — without an iter-authored changeset, code-shape fixes accumulate without ever shipping to npm (violating JTBD-006's audit-trail expectation + JTBD-007's "Keep Plugins Current" closure dependency). Hook `packages/itil/hooks/itil-changeset-discipline.sh` (P141) provides hook-level enforcement at `git commit` time as defence-in-depth — but plugin hook execution depends on the marketplace cache carrying the current hook version, so the prompt-time constraint here MUST land independently (composes-with the hook; does NOT rely on the hook being installed). Inbound-reported from downstream consumer bbstats as their P195 — see [Related](#related) for `**Origin**: inbound-reported (bbstats#195)` per ADR-076. **`@jtbd JTBD-006`** (load-bearing) **`@jtbd JTBD-007`** (closure-dependent).
 4. **Retro-on-exit (P086) + retro-surfaced observation classification (P342)**: before emitting `ITERATION_SUMMARY`, invoke `/wr-retrospective:run-retro`. Retro runs INSIDE this subprocess so its Step 2b pipeline-instability scan has access to the iteration's rich tool-call history (hook misbehaviour, repeat-workaround patterns, subagent-delegation friction, release-path instability). Retro may create tickets or update `docs/BRIEFING.md` — run-retro commits its own work per ADR-014; any tickets it creates ride into either the iteration's own commit (if retro runs before the main commit) or a retro-owned follow-up commit, and the orchestrator picks them up on the next Step 1 scan. Proceed to `ITERATION_SUMMARY` emission regardless of retro findings — retro is non-blocking at the iter-subprocess layer (do not block on retro): if retro fails or surfaces findings, the iteration still returns a summary so the AFK loop does not silently halt on a flaky retro run. (Session-level retro at the orchestrator-main-turn layer per Step 2.4 gate (b) IS load-bearing — distinct surface; see Step 2.4 prose for the orchestrator-layer halt semantics.)
 
    **P342 classification taxonomy — retro-surfaced observations.** When the iter-retro's Step 4b Stage 1 surfaces a ticketable observation, the routing depends on classification:
@@ -1023,4 +1023,6 @@ When every skipped ticket is in the `upstream-blocked` category (stop-condition
 - **ADR-022** (`docs/decisions/022-problem-verification-pending.proposed.md`) — iteration outcomes map into the return-summary's `outcome` field (`verifying` for a released fix, `known-error` for a root-cause-confirmed ticket awaiting release, etc.).
 - **ADR-032** (`docs/decisions/032-governance-skill-invocation-patterns.proposed.md`) — pattern taxonomy parent; Step 5 implements the AFK iteration-isolation wrapper — subprocess-boundary variant per the P084 amendment (2026-04-21), refining the P077 Agent-tool amendment. The P077 amendment remains in the ADR as the historical Agent-tool variant; the subprocess variant is the lead for new adopters.
 - **ADR-037** (`docs/decisions/037-skill-testing-strategy.proposed.md`) — doc-lint bats contract-assertion pattern used by `test/work-problems-step-5-delegation.bats`.
-- **JTBD-001**, **JTBD-006**, **JTBD-101**, **JTBD-201** — personas whose reliability expectations the iteration-isolation wrapper restores.
+- **P206** (`docs/problems/known-error/206-work-problems-iter-workers-dont-add-changesets-fix-commits-accumulate-without-release.md`) — driver for Step 5 iter-prompt-body's explicit "if the fix changes shippable code, author a `.changeset/*.md` in the same commit" constraint (composes defence-in-depth with hook P141's `git commit`-time enforcement). Inbound-reported by downstream consumer **bbstats** as their P195 (`**Origin**: inbound-reported (bbstats#195)` per ADR-076 sort tier). Behavioural second-source: `test/work-problems-step-5-iter-changeset-required.bats` (structural-permitted per ADR-052; tdd-review comment in fixture).
+- **P141** (`docs/problems/verifying/141-iter-prompt-time-reminder-misses-40-percent-of-publishable-iters-hook-level-enforcement.md`) — sibling hook (`packages/itil/hooks/itil-changeset-discipline.sh`) that enforces the changeset-discipline rule at `git commit` time. The Step 5 iter-prompt-body constraint composes-with this hook; the prompt-time rule is load-bearing because plugin-hook execution depends on the marketplace cache carrying the current hook version (a fresh-cache adopter without P141 still gets the constraint via the prompt).
+- **JTBD-001**, **JTBD-006**, **JTBD-007**, **JTBD-101**, **JTBD-201** — personas whose reliability expectations the iteration-isolation wrapper restores. JTBD-006 (Progress the Backlog While I'm Away) + JTBD-007 (Keep Plugins Current Across Projects) are the load-bearing pair for the P206 changeset-discipline constraint — JTBD-006 requires the audit trail to stay accurate at release boundary; JTBD-007's closure depends on fixes actually shipping to npm.

package/skills/work-problems/test/work-problems-adr-013-rule-6-p352-amendment.bats

@@ -0,0 +1,160 @@
+#!/usr/bin/env bats
+# ADR-013 Rule 6 P352 amendment (2026-06-06): queue-and-continue is the
+# universal AFK default when a skill needs user input but AskUserQuestion is
+# unavailable. HALT/SKIP/AUTO-DEFAULT are deviations requiring inline-cited
+# carve-out justification.
+#
+# Structural assertion — Permitted Exception to the source-grep ban (ADR-005 /
+# P011). These assertions are load-bearing-string checks on the ADR + SKILL
+# specification prose. Per P081, structural tests are placeholders for
+# behavioural tests against P012's skill-testing harness; until the harness
+# can exercise AFK fallback shapes, prose assertions on the carve-out audit
+# are the confirmation mechanism named in the amended Rule 6 Confirmation
+# section.
+#
+# tdd-review: structural-permitted (justification: ADR Rule 6 + SKILL.md prose
+# contract assertions for an interaction-pattern contract that has no
+# behavioural skill-runtime harness yet — P012 + P081 Phase 2 bridge window.
+# Isomorphic precedent in this repo: work-problems-above-appetite-remediation.bats,
+# create-adr-substance-confirm-pattern.bats, create-adr-adr-044-contract.bats.)
+#
+# @problem P352 (AFK queue-and-continue is the universal default)
+# @adr ADR-013 (structured user interaction; Rule 6 amended 2026-06-06)
+# @adr ADR-044 (decision-delegation contract; AUTO-DEFAULT lives inside framework-resolution)
+# @adr ADR-052 (behavioural-by-default with structural bridge window)
+# @adr ADR-074 (confirm decision substance before building; authorises HALT carve-outs)
+# @jtbd JTBD-006 (Progress the Backlog While I'm Away — primary persona)
+# @jtbd JTBD-001 (Enforce Governance Without Slowing Down — queue keeps governance on during AFK)
+
+setup() {
+  REPO_ROOT="$(cd "$(dirname "$BATS_TEST_FILENAME")/../../../../.." && pwd)"
+  ADR_013="${REPO_ROOT}/docs/decisions/013-structured-user-interaction-for-governance-decisions.proposed.md"
+}
+
+# ----------------------------------------------------------------------
+# ADR-013 Rule 6 amendment prose
+# ----------------------------------------------------------------------
+
+@test "ADR-013 file exists" {
+  [ -f "$ADR_013" ]
+}
+
+@test "ADR-013 Rule 6 names queue-and-continue as the universal default (P352 amendment)" {
+  # The load-bearing prose: queue-and-continue is THE universal default.
+  run grep -nE "queue-and-continue is the universal default" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 dates the amendment (2026-06-06)" {
+  # Date-anchoring lets future readers correlate the prose with P352 timeline.
+  run grep -nE "2026-06-06 amendment" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 names halt-with-directive AND silent-skip as deviations" {
+  # The amendment's contract: HALT and SKIP are DEVIATIONS requiring carve-out
+  # justification — they are not the default.
+  run grep -nE "DEVIATIONS that require an explicit" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 documents the capture-problem HALT carve-out (ADR-074 authority)" {
+  # The amendment must explicitly name the documented HALT carve-outs so
+  # readers know the SKILL surfaces that LEGITIMATELY halt and why.
+  run grep -nE "capture-problem.*derive-then-ratify HALT" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 documents the create-adr Step 5 HALT carve-out" {
+  run grep -nE "create-adr.*Step 5 substance-confirm HALT" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 documents the manage-problem create-gate HALT carve-out" {
+  run grep -nE "manage-problem.*create-gate HALT" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 names AUTO-DEFAULT as framework-resolved-only (ADR-044 boundary)" {
+  # AUTO-DEFAULT is permitted ONLY when the decision is framework-resolved.
+  # Outside the framework-resolution boundary, AUTO-DEFAULT is a defect.
+  run grep -nE "AUTO-DEFAULT.*permitted ONLY when the decision is framework-resolved" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 cites ADR-044 (decision-delegation framework-resolution boundary)" {
+  run grep -nE "ADR-044" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 cites ADR-074 (substance-confirm authority for HALT carve-outs)" {
+  run grep -nE "ADR-074" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 cites JTBD-006 (Progress the Backlog While I'm Away)" {
+  run grep -nE "JTBD-006" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 cites P352 as the originating ticket" {
+  run grep -nE "\bP352\b" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+@test "ADR-013 Rule 6 records the shared-helper extraction as a follow-on (deferred)" {
+  # The ratified design explicitly deferred the shared-helper extraction to
+  # follow-on. The prose must record the deferral so future readers (and
+  # future iter agents) know the interim contract.
+  run grep -nE "Shared-helper extraction deferred" "$ADR_013"
+  [ "$status" -eq 0 ]
+}
+
+# ----------------------------------------------------------------------
+# Per-SKILL carve-out audit annotations
+# ----------------------------------------------------------------------
+
+@test "capture-problem SKILL.md carries the P352 carve-out audit (HALT per ADR-074)" {
+  SKILL="${REPO_ROOT}/packages/itil/skills/capture-problem/SKILL.md"
+  [ -f "$SKILL" ]
+  run grep -nE "ADR-013 Rule 6 carve-out audit \(P352" "$SKILL"
+  [ "$status" -eq 0 ]
+  # And the carve-out must name its authorising ADR
+  run grep -nE "authorised by \*\*ADR-074" "$SKILL"
+  [ "$status" -eq 0 ]
+}
+
+@test "create-adr SKILL.md carries the P352 carve-out audit (Step 1 AUTO-DEFAULT + Step 5 HALT)" {
+  SKILL="${REPO_ROOT}/packages/architect/skills/create-adr/SKILL.md"
+  [ -f "$SKILL" ]
+  run grep -nE "ADR-013 Rule 6 carve-out audit \(P352" "$SKILL"
+  [ "$status" -eq 0 ]
+}
+
+@test "manage-problem SKILL.md carries the P352 carve-out audit (Step 4b AUTO-DEFAULT)" {
+  SKILL="${REPO_ROOT}/packages/itil/skills/manage-problem/SKILL.md"
+  [ -f "$SKILL" ]
+  run grep -nE "ADR-013 Rule 6 carve-out audit \(P352" "$SKILL"
+  [ "$status" -eq 0 ]
+}
+
+@test "review-problems SKILL.md cites the P352 amendment at the Step 4.5 AFK branch" {
+  SKILL="${REPO_ROOT}/packages/itil/skills/review-problems/SKILL.md"
+  [ -f "$SKILL" ]
+  run grep -nE "ADR-013 Rule 6 universal default \(P352" "$SKILL"
+  [ "$status" -eq 0 ]
+}
+
+@test "scaffold-intake SKILL.md cites the P352 amendment as canonical queue-and-continue" {
+  SKILL="${REPO_ROOT}/packages/itil/skills/scaffold-intake/SKILL.md"
+  [ -f "$SKILL" ]
+  run grep -nE "ADR-013 Rule 6 universal default \(P352" "$SKILL"
+  [ "$status" -eq 0 ]
+}
+
+@test "run-retro SKILL.md cites the P352 amendment at the Step 1.5 AFK branch" {
+  SKILL="${REPO_ROOT}/packages/retrospective/skills/run-retro/SKILL.md"
+  [ -f "$SKILL" ]
+  run grep -nE "ADR-013 Rule 6 universal default \(P352" "$SKILL"
+  [ "$status" -eq 0 ]
+}

package/skills/work-problems/test/work-problems-step-5-iter-changeset-required.bats

@@ -0,0 +1,95 @@
+#!/usr/bin/env bats
+# P206 — work-problems Step 5 iteration-prompt-body must EXPLICITLY require
+# AFK iter subprocesses to author a `.changeset/*.md` alongside any fix
+# commit that ships shippable code. Hook P141 (itil-changeset-discipline.sh)
+# enforces this at git-commit time but depends on the plugin marketplace
+# cache being current. The prompt-time constraint composes defence-in-depth
+# with the hook so iter subprocesses self-author the changeset rather than
+# discovering the gap at commit time (or worse — slipping through when the
+# hook is missing from the install).
+#
+# Reported as inbound from downstream consumer bbstats (their P195) on
+# 2026-05-15; covered by ADR-076 Origin field tier.
+#
+# tdd-review: structural-permitted (justification: SKILL.md is the named
+# contract document under ADR-052; behavioural alternative would require a
+# synthetic `claude -p` iter dispatch harness that completes a fix commit
+# and asserts `.changeset/*.md` co-presence — that harness sits outside the
+# skill layer and depends on the Anthropic CLI binary. Same Permitted
+# Exception precedent as `work-problems-step-5-delegation.bats:99-105` and
+# the P083 / P086 / P089 ScheduleWakeup / retro / stdin-redirect fixtures
+# in the same directory).
+#
+# @problem P206
+# @problem P141
+# @jtbd JTBD-006
+# @jtbd JTBD-007
+# @jtbd JTBD-001
+#
+# Cross-reference:
+#   P206 — this ticket (work-problems iter workers don't add changesets)
+#   P141 — sibling changeset-discipline hook (hook-level enforcement;
+#     prompt-time constraint composes defence-in-depth)
+#   bbstats#195 — inbound report from downstream consumer
+#   ADR-014 (governance skills commit their own work)
+#   ADR-018 (inter-iteration release cadence — changesets are the load-
+#     bearing input to ADR-020's auto-release path)
+#   ADR-052 (behavioural tests default; structural-permitted with comment)
+#   ADR-076 (inbound-reported problems rank ahead via sort tier — Origin
+#     field stamping)
+#   JTBD-006 (Progress the Backlog While I'm Away) — load-bearing
+#   JTBD-007 (Keep Plugins Current Across Projects) — closure depends on
+#     release actually shipping
+
+setup() {
+  SKILL_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
+  SKILL_FILE="${SKILL_DIR}/SKILL.md"
+}
+
+@test "SKILL.md Step 5 iteration-prompt-body names changeset as required when fix changes shippable code (P206)" {
+  # The iteration-prompt-body must EXPLICITLY require iter subprocesses to
+  # author a `.changeset/*.md` alongside any fix commit that ships shippable
+  # code. Without the explicit constraint, iter subprocesses can complete
+  # fix commits that the orchestrator's Step 6.5 release-cadence drain
+  # then has nothing to release — fixes accumulate without an npm publish.
+  # The constraint must name `changeset` AND a "shippable code" qualifier
+  # so doc-only and test-only commits are correctly exempted.
+  run grep -niE "changeset.{0,200}(shippable|publishable|packages/<plugin>)" "$SKILL_FILE"
+  [ "$status" -eq 0 ]
+}
+
+@test "SKILL.md Step 5 iteration-prompt-body exempts doc-only and test-only changes from the changeset requirement (P206)" {
+  # Doc-only changes (e.g. JTBD edits, ADR edits, retro additions) and
+  # test-only changes (under `test/`) ship no behaviour — requiring a
+  # changeset for them would author noise CHANGELOG bullets per release.
+  # The constraint must name the exemption explicitly so iter subprocesses
+  # do not over-apply the rule.
+  run grep -niE "(doc.?only|docs.?only|test.?only).{0,80}(omit|may omit|no changeset|not required)|changeset.{0,80}(omit|exempt)" "$SKILL_FILE"
+  [ "$status" -eq 0 ]
+}
+
+@test "SKILL.md Step 5 iteration-prompt-body cites P141 as the defence-in-depth hook (P206)" {
+  # The prompt-time constraint composes with hook P141 (changeset-discipline).
+  # Naming P141 inline in the prompt-body makes the defence-in-depth
+  # composition self-documenting — a future contributor reading the prompt
+  # understands the hook is the second layer, not the only layer.
+  run grep -nE "P141" "$SKILL_FILE"
+  [ "$status" -eq 0 ]
+}
+
+@test "SKILL.md Related section cites P206 (this fix)" {
+  # ADR-037 + ADR-052 self-documenting contract: the contract document
+  # carries a Related section listing the problem tickets it satisfies.
+  # P206 closure depends on this citation landing.
+  run grep -nE "P206" "$SKILL_FILE"
+  [ "$status" -eq 0 ]
+}
+
+@test "SKILL.md Step 5 iteration-prompt-body cites bbstats#195 as the inbound source (P206 + ADR-076 Origin)" {
+  # ADR-076 reported-first tier requires the Origin field to be visible at
+  # the contract surface so future contributors understand the constraint
+  # was driven by external evidence, not internal speculation. The bbstats
+  # back-link is the audit anchor.
+  run grep -niE "bbstats.{0,20}195|bbstats/.{0,30}195|bbstats#195" "$SKILL_FILE"
+  [ "$status" -eq 0 ]
+}