Merge remote-tracking branch 'origin/capy/fixwave-baseline-repairs' into capy/audit-fix-wave

office-hours/SKILL.md

@@ -612,7 +612,7 @@ sections. Read a section in full before doing its step; do not work from memory.
 | When | Read this section |
 |------|-------------------|
 | running the startup-mode diagnostic (Phase 2A: operating principles, pushback patterns, and the six forcing questions) | `sections/phase-2a-startup-diagnostic.md` |
-| running the builder-mode brainstorm (Phase 2B: operating principles, the wild exemplar, and the generative questions) | `sections/phase-2b-builder-brainstorm.md` |
+| giving any builder-mode response (Phase 2B: brainstorm questions and every suggestion, adjacent unlock or riff; holds the operating principles, the wild exemplar, the response posture and the generative questions) | `sections/phase-2b-builder-brainstorm.md` |
 | writing the design doc and running the tiered relationship handoff (Phases 5-6, after the conversation and alternatives are done) | `sections/design-and-handoff.md` |
 ---
 
@@ -628,8 +628,9 @@ Use this mode when the user is building a startup or doing intrapreneurship.
 ## Phase 2B: Builder Mode — Design Partner
 
 Use this mode when the user is building for fun, learning, hacking on open source, at a hackathon, or doing research.
+The section below applies to every builder-mode reply, including a direct request for ideas or unlocks that skips the generative questions.
 
-> **STOP.** Before running the builder-mode brainstorm (Phase 2B: operating principles, the wild exemplar, and the generative questions), Read `~/.claude/skills/gstack/office-hours/sections/phase-2b-builder-brainstorm.md` and execute it
+> **STOP.** Before giving any builder-mode response (Phase 2B: brainstorm questions and every suggestion, adjacent unlock or riff; holds the operating principles, the wild exemplar, the response posture and the generative questions), Read `~/.claude/skills/gstack/office-hours/sections/phase-2b-builder-brainstorm.md` and execute it
 > in full. Do not work from memory — that section is the source of truth for this step.
 
 **If the vibe shifts mid-session** — the user starts in builder mode but says "actually I think this could be a real company" or mentions customers, revenue, fundraising — upgrade to Startup mode naturally. Say something like: "Okay, now we're talking — let me ask you some harder questions." Then switch to the Phase 2A questions.

office-hours/SKILL.md.tmpl

@@ -135,6 +135,7 @@ Use this mode when the user is building a startup or doing intrapreneurship.
 ## Phase 2B: Builder Mode — Design Partner
 
 Use this mode when the user is building for fun, learning, hacking on open source, at a hackathon, or doing research.
+The section below applies to every builder-mode reply, including a direct request for ideas or unlocks that skips the generative questions.
 
 {{SECTION:phase-2b-builder-brainstorm}}
 

office-hours/sections/manifest.json

@@ -14,7 +14,7 @@
       "id": "phase-2b-builder-brainstorm",
       "file": "phase-2b-builder-brainstorm.md",
       "title": "Phase 2B builder-mode brainstorm",
-      "trigger": "running the builder-mode brainstorm (Phase 2B: operating principles, the wild exemplar, and the generative questions)"
+      "trigger": "giving any builder-mode response (Phase 2B: brainstorm questions and every suggestion, adjacent unlock or riff; holds the operating principles, the wild exemplar, the response posture and the generative questions)"
     },
     {
       "id": "design-and-handoff",

qa/sections/exploratory.md

@@ -24,7 +24,7 @@ Write a **charter** per behavior: contract, risk, entrypoint, isolation, exit co
 
 For /review and /ship, no plan/server is required.
 Stop after 5 minutes or 12 probes, whichever comes first (SECONDS=300 across surfaces).
-Explicit plan checks remain required beyond this smoke budget.
+Explicit plan checks and revalidation remain required beyond this smoke budget.
 For /qa and /qa-only:
 - Browser Quick: SECONDS=30. Browser Full/Regression: SECONDS=900.
 - Functional Full, Quick and Regression have no default total timer.
@@ -66,7 +66,7 @@ Never batch probes.
 4. Replay the exact failing command/request from the same initial fixture state via steps 2–3 (same native command, fresh capture ID)
    before repair, then minimize via those gates. Expiry leaves confirmation/minimization incomplete.
    Another input or a regression test is not that replay.
-5. After source/commands/fixtures change, repeat affected review and return to step 2 for each affected revalidation. Keep limits/notes; status requires fresh evidence.
+5. After source/commands/fixtures change, re-review and return to step 2 for each affected revalidation. Keep limits/notes; status requires fresh evidence.
 
 ## 3. Parent handoff
 

review/SKILL.md

@@ -823,9 +823,9 @@ Never install, import cookies or bootstrap tests. Functional-only skips browser
 - Required: plan commands/assertions, listed separately. Other ideas are optional, untested.
 
 **3. Run smoke and plan checks.**
-Follow the shared Probe loop for smoke checks, replays and revalidation until the smoke limit.
-Then run required plan checks, even after smoke expires, using the same procedure but no smoke guard; never reset the clock.
-Use finite command timeouts, capped at the caller's remaining time if it has a deadline.
+Follow the shared Probe loop for smoke checks and replays until the smoke limit.
+Then run required plan checks and revalidation, even after smoke expires, using the same procedure but no smoke guard; never reset the clock.
+Use finite command timeouts, capped at the caller's remaining time if it has a deadline. /review sets none; only an invoker-supplied EARLIER_UTC counts.
 Await clock/guard results before acting. When the caller's deadline expires, mark unfinished checks not-run.
 
 **4. Check freshness before reporting.**
@@ -843,7 +843,8 @@ Return verified defects to Fix-First: `path`, `line`, `category`,
 `fingerprint: path:line:category`, replay, `test_stub`. Use checklist severity;
 unmatched functional failures are `functional-contract`, `CRITICAL`.
 Setup/permission blockers are not defects. Test creation needs user approval.
-Ask for setup/permission, never secrets. Unresolved coverage makes Step 5.8 incomplete; a ship waiver cannot complete it.
+Ask only for a named permission or setup the user performs, never secrets. Report-only /review never runs setup, installs or cookie import, even after approval.
+After a grant, recheck readiness and run affected checks; otherwise they stay blocked. Unresolved coverage makes Step 5.8 incomplete; a ship waiver cannot complete it.
 
 **5. Prepare one provisional QA section.**
 Read QA's `templates/functional-report-template.md`. Title it
@@ -1066,8 +1067,9 @@ for the native result, or vice versa. Step 4.8's structured-review gate still ap
 
 - Use Step 4.6's `specialists` object unchanged, including its empty small-diff map.
   If this host omits Review Army, use `specialists: {}` without claiming specialist coverage.
-- Build `findings` from final-pass core, specialist, verified exploratory QA
-  findings and invocation actions. Retain `fingerprint`, `severity`
+- Build `findings` from the final-pass findings Step 5 combined (core, specialist,
+  Step 4.8 adversarial, VALID & ACTIONABLE Greptile and verified exploratory QA
+  findings) and invocation actions. Retain `fingerprint`, `severity`
   (`CRITICAL|INFORMATIONAL`), `action`, and any `advisory`, `evidence_paths`,
   `helper_target`. Recheck source after fixes. The logger uses `sharedLibsFingerprint`,
   never supplied/model hashes.

review/SKILL.md.tmpl

@@ -386,8 +386,9 @@ for the native result, or vice versa. Step 4.8's structured-review gate still ap
 
 - Use Step 4.6's `specialists` object unchanged, including its empty small-diff map.
   If this host omits Review Army, use `specialists: {}` without claiming specialist coverage.
-- Build `findings` from final-pass core, specialist, verified exploratory QA
-  findings and invocation actions. Retain `fingerprint`, `severity`
+- Build `findings` from the final-pass findings Step 5 combined (core, specialist,
+  Step 4.8 adversarial, VALID & ACTIONABLE Greptile and verified exploratory QA
+  findings) and invocation actions. Retain `fingerprint`, `severity`
   (`CRITICAL|INFORMATIONAL`), `action`, and any `advisory`, `evidence_paths`,
   `helper_target`. Recheck source after fixes. The logger uses `sharedLibsFingerprint`,
   never supplied/model hashes.

review/sections/plan-completion.md

@@ -27,8 +27,8 @@ done
 3. **Validation:** For search results, read the first 20 lines and verify the project, feature and current branch. A mismatch means "no plan file found." Conversation-supplied paths bypass this search-result check.
 
 **Error handling:**
-- No plan file found → skip with "No plan file detected — skipping."
-- Plan file found but unreadable (permissions, encoding) → skip with "Plan file found but unreadable — skipping."
+- No plan file found → say "No plan file detected." and use the Fallback Intent Sources below.
+- Plan file found but unreadable (permissions, encoding) → say "Plan file found but unreadable." and use the Fallback Intent Sources below; never report plan items as verified.
 
 ### Actionable Item Extraction
 
@@ -192,13 +192,15 @@ The plan completion results augment the existing Scope Drift Detection. If a pla
 
 - **NOT DONE items** become additional evidence for **MISSING REQUIREMENTS** in the scope drift report.
 - **Items in the diff that don't match any plan item** become evidence for **SCOPE CREEP** detection.
-- **HIGH-impact discrepancies** trigger AskUserQuestion:
+- **HIGH-impact plan-file discrepancies** trigger AskUserQuestion:
   - Show the investigation findings
   - Options: A) Stop this review for implementation, B) Continue this review with P1 TODOs, C) Record the items as intentionally dropped
   - A ends this invocation before code review or implementation. List the missing work; after implementation, start a fresh /review.
   - B queues the approved TODO changes for Step 5, not this read-only audit. B/C continue to the final Scope Check and Step 2. None of these choices authorizes shipping or waives required verification.
 
-This is **INFORMATIONAL** unless HIGH-impact discrepancies are found (then it gates via AskUserQuestion).
+This is **INFORMATIONAL** unless HIGH-impact plan-file discrepancies are found (then it gates via AskUserQuestion).
+Discrepancies derived only from fallback sources (commit messages, TODOS.md, PR description) never trigger
+this question, whatever their IMPACT: report them in the Scope Check as lower-confidence missing requirements.
 
 When continuing after the audit (no HIGH-impact gate, or option B/C), emit the
 single final Scope Check using Step 1.5's provisional notes and this plan context:

scripts/resolvers/qa.ts

@@ -71,7 +71,7 @@ Write a **charter** per behavior: contract, risk, entrypoint, isolation, exit co
 
 ${reportOnly ? '' : `For /review and /ship, no plan/server is required.
 Stop after 5 minutes or 12 probes, whichever comes first (SECONDS=300 across surfaces).
-Explicit plan checks remain required beyond this smoke budget.`}
+Explicit plan checks and revalidation remain required beyond this smoke budget.`}
 For /qa and /qa-only:
 - Browser Quick: SECONDS=30. Browser Full/Regression: SECONDS=900.
 - Functional Full, Quick and Regression have no default total timer.
@@ -126,7 +126,7 @@ ${reportOnly ? `   For guarded text, copy the complete span between the guard's
    Another input or a regression test is not that replay.
 ${reportOnly ? `5. If the user or another process changes source, commands or fixtures, review the affected
    contracts and return to step 2 for each affected revalidation. Do not make product changes yourself.
-   Keep the original limits/notes; update outcomes only from fresh evidence.` : `5. After source/commands/fixtures change, repeat affected review and return to step 2 for each affected revalidation. Keep limits/notes; status requires fresh evidence.`}
+   Keep the original limits/notes; update outcomes only from fresh evidence.` : `5. After source/commands/fixtures change, re-review and return to step 2 for each affected revalidation. Keep limits/notes; status requires fresh evidence.`}
 
 ## 3. Parent handoff
 
@@ -255,9 +255,9 @@ Never install, import cookies or bootstrap tests. Functional-only skips browser
 - Required: plan commands/assertions, listed separately. Other ideas are optional, untested.
 
 **3. Run smoke and plan checks.**
-Follow the shared Probe loop for smoke checks, replays and revalidation until the smoke limit.
-Then run required plan checks, even after smoke expires, using the same procedure but no smoke guard; never reset the clock.
-Use finite command timeouts, capped at the caller's remaining time if it has a deadline.
+Follow the shared Probe loop for smoke checks and replays until the smoke limit.
+Then run required plan checks and revalidation, even after smoke expires, using the same procedure but no smoke guard; never reset the clock.
+Use finite command timeouts, capped at the caller's remaining time if it has a deadline.${ship ? '' : ' /review sets none; only an invoker-supplied EARLIER_UTC counts.'}
 Await clock/guard results before acting. When the caller's deadline expires, mark unfinished checks not-run.
 
 **4. Check freshness before reporting.**
@@ -275,7 +275,8 @@ Return verified defects to Fix-First: \`path\`, \`line\`, \`category\`,
 \`fingerprint: path:line:category\`, replay, \`test_stub\`. Use checklist severity;
 unmatched functional failures are \`functional-contract\`, \`CRITICAL\`.
 Setup/permission blockers are not defects. Test creation needs user approval.
-${ship ? 'Step 9.4 asks: permission/repair or explicit named-risk acceptance; otherwise blocked.' : 'Ask for setup/permission, never secrets. Unresolved coverage makes Step 5.8 incomplete; a ship waiver cannot complete it.'}
+${ship ? 'Step 9.4 asks: permission/repair or explicit named-risk acceptance; otherwise blocked.' : `Ask only for a named permission or setup the user performs, never secrets. Report-only /review never runs setup, installs or cookie import, even after approval.
+After a grant, recheck readiness and run affected checks; otherwise they stay blocked. Unresolved coverage makes Step 5.8 incomplete; a ship waiver cannot complete it.`}
 
 ${ship ? `Read QA's \`templates/functional-report-template.md\`: PR section \`## Exploratory QA\`,
 fields as subsections. Link every checkpoint; no second report. Separate browser results;

scripts/resolvers/review.ts

@@ -1483,8 +1483,9 @@ done
 3. **Validation:** For search results, read the first 20 lines and verify the project, feature and current branch. A mismatch means "no plan file found." Conversation-supplied paths bypass this search-result check.
 
 **Error handling:**
-- No plan file found → skip with "No plan file detected — skipping."
-${ship ? '- Plan file found but unreadable (permissions, encoding) → return an audit error to the parent. Do not report no plan or successful zero counts; the parent applies its audit-failure recovery and skip/stop decision.' : '- Plan file found but unreadable (permissions, encoding) → skip with "Plan file found but unreadable — skipping."'}`;
+${ship ? `- No plan file found → skip with "No plan file detected — skipping."
+- Plan file found but unreadable (permissions, encoding) → return an audit error to the parent. Do not report no plan or successful zero counts; the parent applies its audit-failure recovery and skip/stop decision.` : `- No plan file found → say "No plan file detected." and use the Fallback Intent Sources below.
+- Plan file found but unreadable (permissions, encoding) → say "Plan file found but unreadable." and use the Fallback Intent Sources below; never report plan items as verified.`}`;
 }
 
 // ─── Plan Completion Audit ────────────────────────────────────────────
@@ -1723,13 +1724,15 @@ The plan completion results augment the existing Scope Drift Detection. If a pla
 
 - **NOT DONE items** become additional evidence for **MISSING REQUIREMENTS** in the scope drift report.
 - **Items in the diff that don't match any plan item** become evidence for **SCOPE CREEP** detection.
-- **HIGH-impact discrepancies** trigger AskUserQuestion:
+- **HIGH-impact plan-file discrepancies** trigger AskUserQuestion:
   - Show the investigation findings
   - Options: A) Stop this review for implementation, B) Continue this review with P1 TODOs, C) Record the items as intentionally dropped
   - A ends this invocation before code review or implementation. List the missing work; after implementation, start a fresh /review.
   - B queues the approved TODO changes for Step 5, not this read-only audit. B/C continue to the final Scope Check and Step 2. None of these choices authorizes shipping or waives required verification.
 
-This is **INFORMATIONAL** unless HIGH-impact discrepancies are found (then it gates via AskUserQuestion).
+This is **INFORMATIONAL** unless HIGH-impact plan-file discrepancies are found (then it gates via AskUserQuestion).
+Discrepancies derived only from fallback sources (commit messages, TODOS.md, PR description) never trigger
+this question, whatever their IMPACT: report them in the Scope Check as lower-confidence missing requirements.
 
 When continuing after the audit (no HIGH-impact gate, or option B/C), emit the
 single final Scope Check using Step 1.5's provisional notes and this plan context:

ship/sections/review-army.md

@@ -502,8 +502,8 @@ Run the shared preflight; start its smoke guard once. Guard every smoke probe. F
 - Required: plan commands/assertions, listed separately. Other ideas are optional, untested.
 
 **3. Run smoke and plan checks.**
-Follow the shared Probe loop for smoke checks, replays and revalidation until the smoke limit.
-Then run required plan checks, even after smoke expires, using the same procedure but no smoke guard; never reset the clock.
+Follow the shared Probe loop for smoke checks and replays until the smoke limit.
+Then run required plan checks and revalidation, even after smoke expires, using the same procedure but no smoke guard; never reset the clock.
 Use finite command timeouts, capped at the caller's remaining time if it has a deadline.
 Await clock/guard results before acting. When the caller's deadline expires, mark unfinished checks not-run.
 

sync-gbrain/SKILL.md

@@ -672,6 +672,10 @@ Capability check (per /plan-eng-review §6):
 bun run ~/.claude/skills/gstack/bin/gstack-gbrain-read-capability.ts <user-args>
 ```
 
+`<user-args>` are the same flags this /sync-gbrain invocation passed to Step 2,
+unchanged (empty for a plain run). The helper needs no other input: run it once
+and use its JSON result; do not inspect its source or the gbrain CLI first.
+
 The helper reports JSON `status: ready` only after the successful code sync's
 source and real worktree match `.gbrain-source`, the source registration points
 to that worktree, and a bounded, source-scoped list/get returns the same page.
@@ -746,16 +750,17 @@ sync code walk for them requires an explicit `--allow-reclone` opt-in.
 <!-- gstack-gbrain-search-guidance:end -->
 ```
 
-Use the Read + Edit tools. The find-and-replace target is the entire region
-from `<!-- gstack-gbrain-search-guidance:start -->` through
+Read CLAUDE.md once and compute its new content. The replacement target is
+the entire region from `<!-- gstack-gbrain-search-guidance:start -->` through
 `<!-- gstack-gbrain-search-guidance:end -->`. If those markers are missing,
 search for `## GBrain Search Guidance (configured by /sync-gbrain)` heading
 and replace from there to the next `## ` or EOF. If no heading exists, append
 the entire block at the end of CLAUDE.md.
 
-**Atomic write:** write the new CLAUDE.md content to a tmp file alongside it
-(e.g., `CLAUDE.md.sync-gbrain.tmp`) then `mv` to atomic-rename, so a crash
-mid-write never leaves the file half-modified.
+**Atomic write (the only write path; do not Edit CLAUDE.md in place):** Write
+the complete new content to `CLAUDE.md.sync-gbrain.tmp` beside it, then `mv` it
+over CLAUDE.md, so a crash mid-write never leaves the file half-modified. Verify
+the block count in the same Bash call as the `mv`, then go to Step 5.
 
 **If `status=unknown`** — preserve the existing guidance block, if any, and
 report the helper's reason as WARN with advice to retry `/sync-gbrain` or the

sync-gbrain/SKILL.md.tmpl

@@ -323,6 +323,10 @@ Capability check (per /plan-eng-review §6):
 bun run ~/.claude/skills/gstack/bin/gstack-gbrain-read-capability.ts <user-args>
 ```
 
+`<user-args>` are the same flags this /sync-gbrain invocation passed to Step 2,
+unchanged (empty for a plain run). The helper needs no other input: run it once
+and use its JSON result; do not inspect its source or the gbrain CLI first.
+
 The helper reports JSON `status: ready` only after the successful code sync's
 source and real worktree match `.gbrain-source`, the source registration points
 to that worktree, and a bounded, source-scoped list/get returns the same page.
@@ -397,16 +401,17 @@ sync code walk for them requires an explicit `--allow-reclone` opt-in.
 <!-- gstack-gbrain-search-guidance:end -->
 ```
 
-Use the Read + Edit tools. The find-and-replace target is the entire region
-from `<!-- gstack-gbrain-search-guidance:start -->` through
+Read CLAUDE.md once and compute its new content. The replacement target is
+the entire region from `<!-- gstack-gbrain-search-guidance:start -->` through
 `<!-- gstack-gbrain-search-guidance:end -->`. If those markers are missing,
 search for `## GBrain Search Guidance (configured by /sync-gbrain)` heading
 and replace from there to the next `## ` or EOF. If no heading exists, append
 the entire block at the end of CLAUDE.md.
 
-**Atomic write:** write the new CLAUDE.md content to a tmp file alongside it
-(e.g., `CLAUDE.md.sync-gbrain.tmp`) then `mv` to atomic-rename, so a crash
-mid-write never leaves the file half-modified.
+**Atomic write (the only write path; do not Edit CLAUDE.md in place):** Write
+the complete new content to `CLAUDE.md.sync-gbrain.tmp` beside it, then `mv` it
+over CLAUDE.md, so a crash mid-write never leaves the file half-modified. Verify
+the block count in the same Bash call as the `mv`, then go to Step 5.
 
 **If `status=unknown`** — preserve the existing guidance block, if any, and
 report the helper's reason as WARN with advice to retry `/sync-gbrain` or the

test/fixtures/golden/codex-ship-SKILL.md

@@ -1996,8 +1996,8 @@ Run the shared preflight; start its smoke guard once. Guard every smoke probe. F
 - Required: plan commands/assertions, listed separately. Other ideas are optional, untested.
 
 **3. Run smoke and plan checks.**
-Follow the shared Probe loop for smoke checks, replays and revalidation until the smoke limit.
-Then run required plan checks, even after smoke expires, using the same procedure but no smoke guard; never reset the clock.
+Follow the shared Probe loop for smoke checks and replays until the smoke limit.
+Then run required plan checks and revalidation, even after smoke expires, using the same procedure but no smoke guard; never reset the clock.
 Use finite command timeouts, capped at the caller's remaining time if it has a deadline.
 Await clock/guard results before acting. When the caller's deadline expires, mark unfinished checks not-run.
 

test/fixtures/golden/factory-ship-SKILL.md

@@ -2255,8 +2255,8 @@ Run the shared preflight; start its smoke guard once. Guard every smoke probe. F
 - Required: plan commands/assertions, listed separately. Other ideas are optional, untested.
 
 **3. Run smoke and plan checks.**
-Follow the shared Probe loop for smoke checks, replays and revalidation until the smoke limit.
-Then run required plan checks, even after smoke expires, using the same procedure but no smoke guard; never reset the clock.
+Follow the shared Probe loop for smoke checks and replays until the smoke limit.
+Then run required plan checks and revalidation, even after smoke expires, using the same procedure but no smoke guard; never reset the clock.
 Use finite command timeouts, capped at the caller's remaining time if it has a deadline.
 Await clock/guard results before acting. When the caller's deadline expires, mark unfinished checks not-run.
 

test/helpers/sync-gbrain-readiness-fixture.ts

@@ -6,10 +6,11 @@ import { spawnSync } from 'node:child_process';
 const root = path.resolve(import.meta.dir, '../..');
 
 export function createReadinessFixture(kind: 'ready' | 'unknown') {
-  const workDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-ready-'));
-  const home = path.join(workDir, '.fixture-home');
-  const bin = path.join(workDir, '.fixture-bin');
-  fs.mkdirSync(home); fs.mkdirSync(bin);
+  const base = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-ready-'));
+  const workDir = path.join(base, 'repo');
+  const home = path.join(base, 'home');
+  const bin = path.join(base, 'bin');
+  fs.mkdirSync(workDir); fs.mkdirSync(home); fs.mkdirSync(bin);
   const init = spawnSync('git', ['init', '--quiet'], { cwd: workDir, timeout: 10_000 });
   if (init.status !== 0) throw new Error('readiness fixture git init failed');
   fs.writeFileSync(path.join(workDir, '.gbrain-source'), 'client-fixture\n');
@@ -57,6 +58,6 @@ else { console.error('unsupported operation'); process.exit(3); }
     sourceIntact: () => fs.readFileSync(path.join(workDir, '.gbrain-source'), 'utf8') === pin
       && fs.readFileSync(path.join(stateDir, '.gbrain-sync-state.json'), 'utf8') === state
       && !fs.existsSync(path.join(workDir, 'code')),
-    cleanup: () => fs.rmSync(workDir, { recursive: true, force: true }),
+    cleanup: () => fs.rmSync(base, { recursive: true, force: true }),
   };
 }

test/qa-browser-preservation.test.ts

@@ -149,7 +149,7 @@ describe('compact QA browser recipes retain native operations', () => {
       ]) expect(loop).toContain(contract);
       for (const field of ['observationCommand', 'observed', 'hypothesis', 'nextCommand']) expect(loop).toContain(`${field}:`);
       expect(loop).toContain('Functional Full, Quick and Regression have no default total timer');
-      if (skillName !== 'qa-only') expect(loop).toContain('Explicit plan checks remain required beyond this smoke budget');
+      if (skillName !== 'qa-only') expect(loop).toContain('Explicit plan checks and revalidation remain required beyond this smoke budget');
     }
   });
 

test/qa-caller-freshness-order.test.ts

@@ -70,7 +70,7 @@ describe('review and ship completion freshness contracts', () => {
         expect(gate).toContain('Reporting reserves cannot stop required revalidation within the caller\'s deadline');
         expect(body).toContain('Await clock/guard results before acting');
         expect(body).toContain('Smoke: 5 minutes/12 probes');
-        expect(body).toContain('Then run required plan checks, even after smoke expires');
+        expect(body).toContain('Then run required plan checks and revalidation, even after smoke expires');
         expect(body).toContain('no smoke guard; never reset the clock');
         expect(body).toContain('Use finite command timeouts, capped at the caller\'s remaining time if it has a deadline');
       });

test/qa-exploratory-callers.test.ts

@@ -608,8 +608,8 @@ describe('generated actual parent paths', () => {
       expect(load).toContain('Templates cannot replace them');
       const flat = parent.replace(/\s+/g, ' ');
       expect(flat).toContain('Only the parent runs report-only discovery');
-      expect(flat).toContain('Follow the shared Probe loop for smoke checks, replays and revalidation until the smoke limit');
-      expect(flat).toContain('Then run required plan checks, even after smoke expires');
+      expect(flat).toContain('Follow the shared Probe loop for smoke checks and replays until the smoke limit');
+      expect(flat).toContain('Then run required plan checks and revalidation, even after smoke expires');
       expect(flat).toContain('using the same procedure but no smoke guard; never reset the clock');
       expect(flat).toContain("Use finite command timeouts, capped at the caller\'s remaining time if it has a deadline");
       expect(flat).toContain('When the caller\'s deadline expires, mark unfinished checks not-run');
@@ -640,7 +640,7 @@ describe('generated actual parent paths', () => {
     expect(body).toContain('Stop after 5 minutes or 12 probes, whichever comes first');
     expect(body).toContain('G enforces the deadline');
     expect(body).toContain('Never reset D/bypass G');
-    expect(body).toContain('Explicit plan checks remain required beyond this smoke budget');
+    expect(body).toContain('Explicit plan checks and revalidation remain required beyond this smoke budget');
     expect(body).toContain('leaves /review incomplete');
     expect(body).toContain('/ship blocked unless the user explicitly accepts that named risk');
   });

test/qa-probe-gates.test.ts

@@ -40,8 +40,8 @@ function assertBoundsAndLayout(text: string) {
 function assertPlanExecution(text: string, shared = generateQAExploratory({ host: 'claude', skillName: 'qa', tmplPath: '', paths: HOST_PATHS.claude })) {
   const step = text.slice(text.indexOf('**3. Run smoke and plan checks.**'), text.indexOf('**4. Check freshness before reporting.**')).replace(/\s+/g, ' ');
   for (const contract of [
-    'Follow the shared Probe loop for smoke checks, replays and revalidation until the smoke limit',
-    'Then run required plan checks, even after smoke expires',
+    'Follow the shared Probe loop for smoke checks and replays until the smoke limit',
+    'Then run required plan checks and revalidation, even after smoke expires',
     'using the same procedure but no smoke guard; never reset the clock',
     "Use finite command timeouts, capped at the caller\'s remaining time if it has a deadline",
     'When the caller\'s deadline expires, mark unfinished checks not-run',
@@ -261,17 +261,19 @@ describe('QA probe entry and checkpoint gates', () => {
       const text = generateQAReview({ host: 'claude', skillName, tmplPath: '', paths: HOST_PATHS.claude }).replace(/\s+/g, ' ');
       assertPlanExecution(text);
       for (const [before, after] of [
-        ['Then run required plan checks, even after smoke expires', 'Skip plan checks when smoke expired'],
+        ['Then run required plan checks and revalidation, even after smoke expires', 'Skip plan checks when smoke expired'],
         ['no smoke guard; never reset the clock', 'restart and use the smoke guard'],
         ['same procedure', 'Start a new checkpoint sequence'],
         ['at the caller\'s remaining time', 'with no caller cap'],
         ['When the caller\'s deadline expires, mark unfinished checks not-run', 'If that deadline expired, mark the check passed'],
         ['Await clock/guard results before acting', 'Ignore clock results'],
+        ['plan checks and revalidation, even', 'plan checks, even'],
+        ['smoke checks and replays until', 'smoke checks, replays and revalidation until'],
       ]) {
         expect(text).toContain(before);
         expect(() => assertPlanExecution(text.replace(before, after))).toThrow();
       }
-      const smoke = 'Follow the shared Probe loop for smoke checks, replays and revalidation until the smoke limit.';
+      const smoke = 'Follow the shared Probe loop for smoke checks and replays until the smoke limit.';
       expect(() => assertPlanExecution(text.replace(smoke, '').replace('**4. Check', smoke + '\n**4. Check'))).toThrow();
       const shared = generateQAExploratory({ host: 'claude', skillName: 'qa', tmplPath: '', paths: HOST_PATHS.claude });
       for (const contract of ['First demonstrate success: output AND durable effects',

test/review-workflow-clarity.test.ts

@@ -32,7 +32,7 @@ test('review audits deliverables before deferring behavioral plan checks to the
   expect(audit.indexOf('Inspect the validator and its hooks')).toBeLessThan(audit.indexOf('If found and verified safe above, invoke it'));
   expect(audit).not.toContain('For each extracted plan item, run the verification dispatch');
   const qa = generateQAReview(ctx);
-  expect(qa).toContain('Then run required plan checks, even after smoke expires');
+  expect(qa).toContain('Then run required plan checks and revalidation, even after smoke expires');
   expect(qa).toContain('Report clean/completed only when all required checks pass on current inputs');
 });
 
@@ -249,7 +249,7 @@ test('caller QA defines execution, evidence ownership and report adaptation befo
     for (const contract of [
       'Only the parent runs report-only discovery',
       'Never overwrite another run',
-      'Follow the shared Probe loop for smoke checks, replays and revalidation until the smoke limit',
+      'Follow the shared Probe loop for smoke checks and replays until the smoke limit',
       'using the same procedure but no smoke guard; never reset the clock',
       'Read agent/user updates and await results without batching them with reporting/logging',
       'Compare each probe\'s recorded source, tests, contracts, commands and fixtures (or input fingerprint) with current inputs, even without updates',
@@ -378,7 +378,7 @@ test('review finalization ownership: the plan audit retains its high-impact gate
   expect(plan).not.toContain('never blocks the review');
   expect(plan).toContain('{{PLAN_COMPLETION_AUDIT_REVIEW}}');
   const audit = readFileSync(join(root, 'review/sections/plan-completion.md'), 'utf8');
-  const gate = audit.indexOf('**HIGH-impact discrepancies** trigger AskUserQuestion');
+  const gate = audit.indexOf('**HIGH-impact plan-file discrepancies** trigger AskUserQuestion');
   expect(gate).toBeGreaterThan(-1);
   expect(gate).toBeLessThan(audit.indexOf('When continuing after the audit (no HIGH-impact gate, or option B/C)'));
   expect(audit).toContain('then it gates via AskUserQuestion');
@@ -564,3 +564,25 @@ test('ship review clarity: parent settlement gate precedes classification and ca
   expect(gate).toContain('After terminal failure, independent evidence may support fixes');
   expect(gate).toContain('missing dispatched output still blocks continuation, even with a QA exception');
 });
+
+test('review resolves the judged smoke-clock, setup-authority, plan-gate and findings-source ambiguities', () => {
+  const ctx = { skillName: 'review', tmplPath: 'review/SKILL.md.tmpl', host: 'claude', paths: HOST_PATHS.claude } as TemplateContext;
+  const qa = generateQAReview(ctx).replace(/\s+/g, ' ');
+  expect(qa).toContain('Follow the shared Probe loop for smoke checks and replays until the smoke limit');
+  expect(qa).toContain('Then run required plan checks and revalidation, even after smoke expires, using the same procedure but no smoke guard');
+  expect(qa).toContain('/review sets none; only an invoker-supplied EARLIER_UTC counts');
+  expect(qa).toContain('Report-only /review never runs setup, installs or cookie import, even after approval');
+  expect(qa).toContain('After a grant, recheck readiness and run affected checks; otherwise they stay blocked');
+  expect(qa).not.toContain('Ask for setup/permission');
+  expect(generateQAReview({ ...ctx, skillName: 'ship', tmplPath: 'ship/SKILL.md.tmpl' })).not.toContain('/review sets none');
+  const shared = generateQAExploratory({ ...ctx, skillName: 'qa' }).replace(/\s+/g, ' ');
+  expect(shared).toContain('Explicit plan checks and revalidation remain required beyond this smoke budget');
+  const audit = generatePlanCompletionAuditReview(ctx).replace(/\s+/g, ' ');
+  expect(audit).toContain('No plan file found → say "No plan file detected." and use the Fallback Intent Sources below');
+  expect(audit).not.toContain('skip with "No plan file detected — skipping."');
+  expect(audit).toContain('**HIGH-impact plan-file discrepancies** trigger AskUserQuestion');
+  expect(audit).toContain('Discrepancies derived only from fallback sources (commit messages, TODOS.md, PR description) never trigger this question');
+  expect(generatePlanCompletionAuditShip({ ...ctx, skillName: 'ship', tmplPath: 'ship/SKILL.md.tmpl' })).toContain('skip with "No plan file detected — skipping."');
+  const persist = skill.slice(skill.indexOf('### 2. Fill the record')).replace(/\s+/g, ' ');
+  expect(persist).toContain('findings Step 5 combined (core, specialist, Step 4.8 adversarial, VALID & ACTIONABLE Greptile and verified exploratory QA findings)');
+});

test/ship-workflow-clarity.test.ts

@@ -14,7 +14,7 @@ test('Ship initializes and applies its smoke guard independently of required pla
     expect(body).toContain('Run the shared preflight; start its smoke guard once. Guard every smoke probe.');
     expect(body.indexOf('start its smoke guard once')).toBeLessThan(body.indexOf('**3. Run smoke and plan checks.**'));
     expect(body).toContain('Required even for small diffs or missing plans/servers');
-    expect(body).toContain('Then run required plan checks, even after smoke expires');
+    expect(body).toContain('Then run required plan checks and revalidation, even after smoke expires');
     expect(body).toContain('using the same procedure but no smoke guard; never reset the clock');
   }
 });