@mmerterden/multi-agent-pipeline 8.6.2 → 10.0.6

package/pipeline/commands/multi-agent/refs/android-guide.md

@@ -1,5 +1,7 @@
 ## Android/Kotlin Component Generation Guide
 
+> **MUST: Figma MCP-first (BLOCKING).** If the task references any Figma frame (URL, node ID, or "from the design"), the Dev phase MUST call `mcp__claude_ai_Figma__get_design_context` for every frame BEFORE writing a single Composable line. Use the `CodeConnectSnippet` component name verbatim - no sound-alike substitutions. Authentication failure is not a skip path. Full rule, trigger conditions, and gate failure modes: `pipeline/rules/figma-pipeline.md` "MUST: Figma MCP-first (BLOCKING)". Phase wiring: `refs/phases/phase-3-dev.md` "MUST: Figma MCP-first (BLOCKING pre-step)".
+
 When the task involves creating an Android UI component (Jetpack Compose), follow this architecture.
 
 ### Component Architecture: State / Screen / Content
@@ -166,23 +168,23 @@ fun onEmailChanged_updatesState() = runTest {
 
 After implementation:
 
-- `./gradlew assembleDebug` — zero errors
-- `./gradlew testDebugUnitTest` — all tests pass
-- `./gradlew ktlintCheck` — lint clean
+- `./gradlew assembleDebug`  -  zero errors
+- `./gradlew testDebugUnitTest`  -  all tests pass
+- `./gradlew ktlintCheck`  -  lint clean
 - Previews render in Android Studio
 
 ### Component Quality Checklist
 
-1. No magic numbers — all values are theme tokens or named constants
-2. State hoisting — stateful wrapper + stateless content pattern
-3. No ViewModel in child composables — pass state + lambdas
-4. Accessibility — contentDescription, testTag, 48dp touch targets
-5. Preview coverage — default, dark mode, large font, RTL
-6. Tests — Compose UI tests + ViewModel unit tests
-7. Dark mode — correct with MaterialTheme.colorScheme
-8. Strings — all use `stringResource()`, not hardcoded
-9. Stability — `@Immutable`/`@Stable` where appropriate
-10. Build passes — zero errors, lint clean
+1. No magic numbers  -  all values are theme tokens or named constants
+2. State hoisting  -  stateful wrapper + stateless content pattern
+3. No ViewModel in child composables  -  pass state + lambdas
+4. Accessibility  -  contentDescription, testTag, 48dp touch targets
+5. Preview coverage  -  default, dark mode, large font, RTL
+6. Tests  -  Compose UI tests + ViewModel unit tests
+7. Dark mode  -  correct with MaterialTheme.colorScheme
+8. Strings  -  all use `stringResource()`, not hardcoded
+9. Stability  -  `@Immutable`/`@Stable` where appropriate
+10. Build passes  -  zero errors, lint clean
 
 ### Compliance Rules (maps to dev-toolkit MCP audit tools)
 

package/pipeline/commands/multi-agent/refs/audit-guide.md

@@ -1,6 +1,6 @@
 ## Audit & Quality Tools Guide
 
-Standalone audit commands — runs directly via Bash, **no MCP server dependency**. These are the same checks that dev-toolkit-mcp provides as MCP tools, but embedded here as pipeline skills.
+Standalone audit commands  -  runs directly via Bash, **no MCP server dependency**. These are the same checks that dev-toolkit-mcp provides as MCP tools, but embedded here as pipeline skills.
 
 ### Trigger Model
 
@@ -8,7 +8,7 @@ Standalone audit commands — runs directly via Bash, **no MCP server dependency
 
 1. User explicitly requests: `/multi-agent test "accessibility"`, `/multi-agent test "store-ready"`
 2. User asks during Phase 5: "run accessibility audit", "check store compliance"
-3. Pipeline suggests and user confirms: "UI changes detected — want to run accessibility audit?"
+3. Pipeline suggests and user confirms: "UI changes detected  -  want to run accessibility audit?"
 
 **Pipeline never runs audits without user intent.** Phase 4 does code-level review (free, automatic). Phase 5 does device-level audit only when requested.
 
@@ -16,7 +16,7 @@ Standalone audit commands — runs directly via Bash, **no MCP server dependency
 
 ### iOS Accessibility Audit
 
-**When**: Phase 5 — user requests, app is running on simulator
+**When**: Phase 5  -  user requests, app is running on simulator
 **What it checks**: Missing labels, small tap targets (<44pt), missing identifiers
 
 **How to run** (requires ui-tree-dumper.swift in project or ~/.claude/scripts/):
@@ -37,7 +37,7 @@ UI_TREE=$(swift "$HOME/.claude/scripts/ui-tree-dumper.swift" 10 2>/dev/null)
 
 ```
 Only audit elements where identifier starts with "{scope}_"
-Skip elements outside scope — report scanned vs skipped count
+Skip elements outside scope  -  report scanned vs skipped count
 ```
 
 **Output format** (AI generates this from parsed tree):
@@ -48,20 +48,20 @@ Accessibility Audit:
   Scanned: {N} interactive elements
 
   CRITICAL: {N} missing labels
-    - AXButton at (120, 340) — no label, identifier: "btn_close"
+    - AXButton at (120, 340)  -  no label, identifier: "btn_close"
 
   IMPORTANT: {N} small tap targets
-    - AXButton "Submit" — 32x32pt (min 44x44)
+    - AXButton "Submit"  -  32x32pt (min 44x44)
 
   WARNING: {N} missing identifiers
-    - AXTextField at (20, 200) — has label "Email" but no identifier
+    - AXTextField at (20, 200)  -  has label "Email" but no identifier
 ```
 
 ---
 
 ### Android Accessibility Audit
 
-**When**: Phase 5 — user requests, app is running on emulator
+**When**: Phase 5  -  user requests, app is running on emulator
 **What it checks**: Missing contentDescription, small touch targets (<48dp), missing resource-id
 
 ```bash
@@ -86,7 +86,7 @@ cat /tmp/_audit_ui.xml
 
 ### iOS Biometric Test
 
-**When**: Phase 5 — auth flow testing
+**When**: Phase 5  -  auth flow testing
 
 ```bash
 DEVICE_ID=$(xcrun simctl list devices booted -j | python3 -c "import sys,json; devs=json.load(sys.stdin)['devices']; print(next(d['udid'] for ds in devs.values() for d in ds if d['state']=='Booted'))")
@@ -107,7 +107,7 @@ xcrun simctl keychain $DEVICE_ID biometric-match --face --no-match
 
 ### Android Launch Time
 
-**When**: Phase 5 — performance baseline
+**When**: Phase 5  -  performance baseline
 
 ```bash
 # Force stop first (cold start)
@@ -131,7 +131,7 @@ adb shell am start -W -n {package_name}/.MainActivity 2>&1
 
 ### iOS Archive Audit (App Store Compliance)
 
-**When**: Phase 6 — release branches only, user confirms
+**When**: Phase 6  -  release branches only, user confirms
 **Input**: Path to .xcarchive
 
 ```bash
@@ -178,15 +178,15 @@ ls "$APP_DIR/Frameworks/" 2>/dev/null
 
 **Verdict**:
 
-- Any CRITICAL → "FAIL — must fix before submission"
-- Only WARNING → "WARN — review before submission"
-- All pass → "PASS — ready for App Store"
+- Any CRITICAL → "FAIL  -  must fix before submission"
+- Only WARNING → "WARN  -  review before submission"
+- All pass → "PASS  -  ready for App Store"
 
 ---
 
 ### Android APK Audit (Play Store Compliance)
 
-**When**: Phase 6 — release branches only, user confirms
+**When**: Phase 6  -  release branches only, user confirms
 **Input**: Path to .apk
 
 ```bash
@@ -226,11 +226,11 @@ unzip -l "$APK" 2>/dev/null | grep "classes.*\.dex" | wc -l
 
 | Phase            | What Happens                                        | Method                          |
 | ---------------- | --------------------------------------------------- | ------------------------------- |
-| Phase 4 (Review) | Accessibility check — **code-level only**           | AI reads source code, no device |
-| Phase 5 (Test)   | Accessibility audit — **device-level, on-demand**   | Bash commands above             |
-| Phase 5 (Test)   | Biometric test — **on-demand**                      | `xcrun simctl keychain`         |
-| Phase 5 (Test)   | Launch time — **on-demand**                         | `adb shell am start -W`         |
-| Phase 6 (Commit) | Archive/APK audit — **release branches, on-demand** | Bash commands above             |
+| Phase 4 (Review) | Accessibility check  -  **code-level only**           | AI reads source code, no device |
+| Phase 5 (Test)   | Accessibility audit  -  **device-level, on-demand**   | Bash commands above             |
+| Phase 5 (Test)   | Biometric test  -  **on-demand**                      | `xcrun simctl keychain`         |
+| Phase 5 (Test)   | Launch time  -  **on-demand**                         | `adb shell am start -W`         |
+| Phase 6 (Commit) | Archive/APK audit  -  **release branches, on-demand** | Bash commands above             |
 
 ### Graceful Degradation
 

package/pipeline/commands/multi-agent/refs/backend-guide.md

@@ -15,7 +15,7 @@ When the task involves backend development (Python/FastAPI, Node.js/Express, Go)
 ### Python/FastAPI Pattern
 
 ```python
-# schemas/user.py — Pydantic models
+# schemas/user.py  -  Pydantic models
 class UserCreate(BaseModel):
     email: EmailStr
     name: str = Field(min_length=1, max_length=100)
@@ -26,7 +26,7 @@ class UserResponse(BaseModel):
     name: str
     model_config = ConfigDict(from_attributes=True)
 
-# services/user_service.py — business logic
+# services/user_service.py  -  business logic
 class UserService:
     def __init__(self, repo: UserRepository):
         self.repo = repo
@@ -37,7 +37,7 @@ class UserService:
             raise HTTPException(status_code=409, detail="Email already exists")
         return await self.repo.create(data)
 
-# routes/users.py — HTTP layer
+# routes/users.py  -  HTTP layer
 router = APIRouter(prefix="/users", tags=["users"])
 
 @router.post("/", response_model=UserResponse, status_code=201)
@@ -48,13 +48,13 @@ async def create_user(data: UserCreate, service: UserService = Depends()):
 ### Node.js/Express Pattern
 
 ```typescript
-// schemas/user.schema.ts — Zod validation
+// schemas/user.schema.ts  -  Zod validation
 const createUserSchema = z.object({
   email: z.string().email(),
   name: z.string().min(1).max(100),
 });
 
-// services/user.service.ts — business logic
+// services/user.service.ts  -  business logic
 export class UserService {
   constructor(private repo: UserRepository) {}
 
@@ -65,7 +65,7 @@ export class UserService {
   }
 }
 
-// routes/users.ts — HTTP layer
+// routes/users.ts  -  HTTP layer
 router.post("/", validate(createUserSchema), async (req, res) => {
   const user = await userService.createUser(req.body);
   res.status(201).json(user);
@@ -99,7 +99,7 @@ async def app_error_handler(request, exc):
 4. Rate limiting on public endpoints
 5. CORS properly configured (not `*` in production)
 6. SQL injection prevention (parameterized queries / ORM)
-7. No secrets in code — environment variables
+7. No secrets in code  -  environment variables
 8. HTTPS only
 9. Request/response logging (without sensitive data)
 10. Error messages don't leak internals
@@ -107,14 +107,14 @@ async def app_error_handler(request, exc):
 ### Testing
 
 ```python
-# Unit test — service layer
+# Unit test  -  service layer
 async def test_create_user_duplicate_email():
     repo = FakeUserRepository(existing_emails=["test@example.com"])
     service = UserService(repo)
     with pytest.raises(HTTPException, match="409"):
         await service.create_user(UserCreate(email="test@example.com", name="Test"))
 
-# Integration test — full endpoint
+# Integration test  -  full endpoint
 async def test_create_user_endpoint(client: AsyncClient):
     response = await client.post("/users/", json={"email": "new@example.com", "name": "New"})
     assert response.status_code == 201

package/pipeline/commands/multi-agent/refs/channels/confluence.md

@@ -1,8 +1,8 @@
-# Channel adapter — Confluence page
+# Channel adapter  -  Confluence page
 
 > Detailed contract for the `confluence` channel of `/multi-agent:channels`. Split out of `channels.md` in v8.0.0; the parent doc keeps a one-line summary and a link here.
 
-The Confluence adapter creates or updates a Confluence page under a chosen parent. Like the Jira adapter, it runs **once** per invocation — the page lives at the primary repo's component slug in multi-repo mode.
+The Confluence adapter creates or updates a Confluence page under a chosen parent. Like the Jira adapter, it runs **once** per invocation  -  the page lives at the primary repo's component slug in multi-repo mode.
 
 ## Required body structure
 
@@ -16,13 +16,13 @@ Every Confluence page written by this adapter follows the same section order. Se
 | 4 | `api_contracts` | `## API Kontratları` | `## API Contracts` | when work added or modified HTTP endpoints, GraphQL ops, or RPC methods |
 | 5 | `references` | `## İlgili Bağlantılar` | `## References` | when any context link exists |
 
-> Headings in the source markdown are `##`; the storage-format converter rewrites them to `<h2>…</h2>`. Sub-headings (`###`) become `<h3>` and so on.
+> Headings in the source markdown are `##`; the storage-format converter rewrites them to `<h2>...</h2>`. Sub-headings (`###`) become `<h3>` and so on.
 
 ### Section content rules
 
-**`overview`** — 3-6 sentences. Audience is stakeholders/PM/designers, not engineers — explain the change in user/business terms first, then a single sentence on the technical approach. No marketing voice, no "we are proud to announce".
+**`overview`**  -  3-6 sentences. Audience is stakeholders/PM/designers, not engineers  -  explain the change in user/business terms first, then a single sentence on the technical approach. No marketing voice, no "we are proud to announce".
 
-**`flow`** — when included, embed a flow diagram. Preferred form is a Mermaid block (Confluence renders Mermaid via the storage-format macro when the space has the plugin enabled); fallback is a numbered step list when Mermaid is unavailable. Template shape:
+**`flow`**  -  when included, embed a flow diagram. Preferred form is a Mermaid block (Confluence renders Mermaid via the storage-format macro when the space has the plugin enabled); fallback is a numbered step list when Mermaid is unavailable. Template shape:
 
 ```markdown
 ## Flow Diagram
@@ -38,9 +38,9 @@ sequenceDiagram
 
 Replace `<actor>` / `<service>` with the real names at write-time; do not invent placeholders that don't exist in the diff.
 
-**`technical_details`** — bullet list or sub-sections covering implementation specifics: data flow, key components touched, edge cases handled, performance notes. Code identifiers stay verbatim across languages.
+**`technical_details`**  -  bullet list or sub-sections covering implementation specifics: data flow, key components touched, edge cases handled, performance notes. Code identifiers stay verbatim across languages.
 
-**`api_contracts`** — for each new/changed endpoint:
+**`api_contracts`**  -  for each new/changed endpoint:
 
 ```markdown
 ### <METHOD> <path>
@@ -50,26 +50,26 @@ Replace `<actor>` / `<service>` with the real names at write-time; do not invent
 { "..." }
 \`\`\`
 
-**Response — 200**
+**Response  -  200**
 \`\`\`json
 { "..." }
 \`\`\`
 
 **Error responses**
-- `400` — <when>
-- `401` — <when>
-- `404` — <when>
+- `400`  -  <when>
+- `401`  -  <when>
+- `404`  -  <when>
 ```
 
-When the task referenced a Confluence API-contract source page (see Phase 0 link extraction / Phase 1 context injection), this section may consume that contract directly — verbatim where it matches, with a `(source: <confluence-page-url>)` annotation at the end of the section.
+When the task referenced a Confluence API-contract source page (see Phase 0 link extraction / Phase 1 context injection), this section may consume that contract directly  -  verbatim where it matches, with a `(source: <confluence-page-url>)` annotation at the end of the section.
 
-**`references`** — flat bullet list, mirrors the Jira `## References` shape (Swagger, Figma, Crashlytics, Fortify, source Confluence pages, PR URLs). Emit one line per link, never deduplicate across categories.
+**`references`**  -  flat bullet list, mirrors the Jira `## References` shape (Swagger, Figma, Crashlytics, Fortify, source Confluence pages, PR URLs). Emit one line per link, never deduplicate across categories.
 
 ### Assembly order (per run)
 
 ```
 1. Read agent-state.json (taskId, contextLinks, prUrls, language).
-2. Build section bodies in markdown — overview first, then in the table order, skipping conditional sections that don't apply.
+2. Build section bodies in markdown  -  overview first, then in the table order, skipping conditional sections that don't apply.
 3. Run the assembled body through the `humanizer` skill (tone target: formal, stakeholder-readable).
 4. Convert markdown → Confluence storage XML (see table below).
 5. POST / PUT.
@@ -104,7 +104,7 @@ Confluence parent page URL:
 
 ## Page title
 
-Auto-suggested as `"{jiraId} — {taskTitle}"` — user can edit at the prompt. The `taskTitle` comes from `state.taskTitle` if set, else from the Jira summary, else from the PR title.
+Auto-suggested as `"{jiraId}  -  {taskTitle}"`  -  user can edit at the prompt. The `taskTitle` comes from `state.taskTitle` if set, else from the Jira summary, else from the PR title.
 
 ## Body conversion (markdown → storage format)
 
@@ -117,7 +117,7 @@ Auto-suggested as `"{jiraId} — {taskTitle}"` — user can edit at the prompt.
 | Links `[t](u)` | `<a href="u">t</a>` |
 | Lists | `<ul><li>...</li></ul>` / `<ol><li>...</li></ol>` |
 
-Body is run through humanizer before XML conversion — Confluence tone is the most formal of the four channels (target audience: stakeholders, PMs, designers).
+Body is run through humanizer before XML conversion  -  Confluence tone is the most formal of the four channels (target audience: stakeholders, PMs, designers).
 
 ## POST contract
 
@@ -145,7 +145,7 @@ Successful POST → URL prepended to `prefs.projects[<project>].confluenceUrls`
 
 ## Hard rules (must not regress)
 
-- Real newlines and no HTML entities in the source body — XML conversion happens at adapter time, never embed `\n` literals.
+- Real newlines and no HTML entities in the source body  -  XML conversion happens at adapter time, never embed `\n` literals.
 - Section order is fixed: `overview` → `flow` (cond.) → `technical_details` → `api_contracts` (cond.) → `references` (cond.). Conditional sections may be omitted but never reordered.
 - Humanizer pass runs **after** body assembly and **before** storage-XML conversion. Tone: formal, stakeholder-readable. No "we are excited", no first-person plural.
 - Body content language follows `prefs.global.outputLanguage`. Code identifiers, API paths, file paths, type names, JSON keys, and the storage-XML markup stay verbatim. The template (this doc) is English because `promptLanguage="en"` is locked.

package/pipeline/commands/multi-agent/refs/channels/issue-comment.md

@@ -1,6 +1,6 @@
-# Channel adapter — GitHub Issue comment
+# Channel adapter  -  GitHub Issue comment
 
-> Canonical template for the `issue` channel of `/multi-agent:channels`. Every successful run that touched a tracked GitHub issue MUST post one comment using this template — no exceptions, no "state-only" shortcuts.
+> Canonical template for the `issue` channel of `/multi-agent:channels`. Every successful run that touched a tracked GitHub issue MUST post one comment using this template  -  no exceptions, no "state-only" shortcuts.
 
 ## When this fires
 
@@ -10,7 +10,7 @@ The Issue Comment adapter runs once per channels invocation when:
 state.tracker.kind === "github-issue"  AND  channels.selected includes "issue"
 ```
 
-In multi-repo tasks, the issue lives on the primary repo's issue tracker. Extras don't get separate issue comments — their PRs are linked back through the comment body.
+In multi-repo tasks, the issue lives on the primary repo's issue tracker. Extras don't get separate issue comments  -  their PRs are linked back through the comment body.
 
 ## The hard rule
 
@@ -22,39 +22,39 @@ The template (this doc) is English because `promptLanguage="en"` is locked. At w
 
 | # | Section key | Heading (`tr`) | Heading (`en`) | Required? |
 |---|---|---|---|---|
-| 1 | `title` | `## Geliştirme Detayı — \`<name>\`` | `## Implementation Detail — \`<name>\`` | always |
+| 1 | `title` | `## Geliştirme Detayı  -  \`<name>\`` | `## Implementation Detail  -  \`<name>\`` | always |
 | 2 | `summary` | (paragraphs immediately under the title) | (same) | always |
 | 3 | `prs_branches` | `### Pull Request / Dal` | `### Pull Requests / Branches` | always |
 | 4 | `acceptance_criteria` | `### Kabul Kriterleri` | `### Acceptance Criteria` | always |
-| 5 | `build_and_test` | `### Build & Test` | `### Build & Test` | always (heading stays English — tooling token) |
+| 5 | `build_and_test` | `### Build & Test` | `### Build & Test` | always (heading stays English  -  tooling token) |
 | 6 | `figma_extras` | `### Code Connect / Wiki` | `### Code Connect / Wiki` | only on the figma component task type |
-| 7 | `next_steps` | `### Sonraki Adımlar` | `### Next Steps` | always (empty list allowed — signals "fully complete") |
+| 7 | `next_steps` | `### Sonraki Adımlar` | `### Next Steps` | always (empty list allowed  -  signals "fully complete") |
 | 8 | `ref_footer` | `Ref: #<issueNumber>` | `Ref: #<issueNumber>` | always (token text, never translated) |
 
-### Template body (English — runtime renders headings in `outputLanguage`)
+### Template body (English  -  runtime renders headings in `outputLanguage`)
 
 ```markdown
-## Implementation Detail — `<ComponentOrTaskName>`
+## Implementation Detail  -  `<ComponentOrTaskName>`
 
 <1-3 paragraphs: why this approach was chosen, what changed, any architectural decision worth flagging>
 
 ### Pull Requests / Branches
-- **<repoName>:** <prKindLabel> — <prUrl OR "branch `<branchName>` pushed (commit `<shortSha>`), PR not opened">
+- **<repoName>:** <prKindLabel>  -  <prUrl OR "branch `<branchName>` pushed (commit `<shortSha>`), PR not opened">
 <one line per repo touched; never collapse multiple repos into one>
 
 ### Acceptance Criteria
-- [<x|·>] <AC text — `x` if delivered, `·` if intentionally deferred (with `(deferred: <reason>)` suffix)>
+- [<x|·>] <AC text  -  `x` if delivered, `·` if intentionally deferred (with `(deferred: <reason>)` suffix)>
 <one bullet per AC item from the issue body, or per implicit AC if the issue had none>
 
 ### Build & Test
-- Build: <green|red|baseline-pre-existing|skipped> — <one-line evidence: command + result OR "pre-existing failure verified on `<baselineSha>`">
+- Build: <green|red|baseline-pre-existing|skipped>  -  <one-line evidence: command + result OR "pre-existing failure verified on `<baselineSha>`">
 - Tests: <N tests added | tests skipped (Phase 5 user-test path) | none>
 <for figma component flow, also:>
-- Code Connect: <published | dry-run-only | not-applicable> — <URL of Figma node if published>
-- Wiki: <published | local-only | skipped> — <URL of wiki page if published>
+- Code Connect: <published | dry-run-only | not-applicable>  -  <URL of Figma node if published>
+- Wiki: <published | local-only | skipped>  -  <URL of wiki page if published>
 
 ### Next Steps
-- <follow-up bullet — PRs to open, manual deploys, push consents needed>
+- <follow-up bullet  -  PRs to open, manual deploys, push consents needed>
 <empty list is fine; the section header itself stays>
 
 Ref: #<issueNumber>
@@ -62,20 +62,20 @@ Ref: #<issueNumber>
 
 ### Section content rules
 
-- **`title`** — always wraps the component or task name in backticks. No emoji.
-- **`summary`** — 1-3 paragraphs, **why** before **what**. No bullet lists in the summary block — those belong in `acceptance_criteria`.
-- **`prs_branches`** — every repo the run touched gets exactly ONE line. If the PR was deferred, write the branch + commit SHA explicitly so the reader can `gh pr create` from there. Never collapse multiple repos into one line.
-- **`acceptance_criteria`** — copy from the issue body verbatim when an `### Acceptance Criteria` section exists. If the section is `_No response_`, the agent enumerates the implicit ACs it satisfied during Phase 1/3. `[x]` only when delivered and verified; `[·]` for deferred (with reason in parens).
-- **`build_and_test`** — required. If a build failure was pre-existing, the line includes the baseline SHA where the failure was reproduced (per `feedback_build_baseline_proof.md`).
-- **`figma_extras`** — emitted only when `state.taskType == "component"` and the figma sub-pipeline ran.
-- **`next_steps`** — empty list is fine; the section header itself stays. Empty signals "fully complete, no follow-ups".
-- **`ref_footer`** — always `Ref: #N` (or `Related: #N`). NEVER `Closes/Fixes/Resolves` — the pipeline never auto-closes issues (`feedback_no_issue_close.md`).
+- **`title`**  -  always wraps the component or task name in backticks. No emoji.
+- **`summary`**  -  1-3 paragraphs, **why** before **what**. No bullet lists in the summary block  -  those belong in `acceptance_criteria`.
+- **`prs_branches`**  -  every repo the run touched gets exactly ONE line. If the PR was deferred, write the branch + commit SHA explicitly so the reader can `gh pr create` from there. Never collapse multiple repos into one line.
+- **`acceptance_criteria`**  -  copy from the issue body verbatim when an `### Acceptance Criteria` section exists. If the section is `_No response_`, the agent enumerates the implicit ACs it satisfied during Phase 1/3. `[x]` only when delivered and verified; `[·]` for deferred (with reason in parens).
+- **`build_and_test`**  -  required. If a build failure was pre-existing, the line includes the baseline SHA where the failure was reproduced (per `feedback_build_baseline_proof.md`).
+- **`figma_extras`**  -  emitted only when `state.taskType == "component"` and the figma sub-pipeline ran.
+- **`next_steps`**  -  empty list is fine; the section header itself stays. Empty signals "fully complete, no follow-ups".
+- **`ref_footer`**  -  always `Ref: #N` (or `Related: #N`). NEVER `Closes/Fixes/Resolves`  -  the pipeline never auto-closes issues (`feedback_no_issue_close.md`).
 
 ### Assembly order (per run)
 
 ```
 1. Read agent-state.json (taskId, contextLinks, prUrls, taskType, language).
-2. Build section bodies in markdown — title first, then in the table order, skipping conditional sections that don't apply.
+2. Build section bodies in markdown  -  title first, then in the table order, skipping conditional sections that don't apply.
 3. Run the assembled body through the `humanizer` skill.
 4. Apply compaction policy if length > 4000 chars (see below).
 5. POST via `gh issue comment`.
@@ -83,11 +83,11 @@ Ref: #<issueNumber>
 
 ## Hard prohibitions
 
-- No "Co-Authored-By: Claude" trailer. No "🤖 Generated with …" footer. No mention of Claude / Copilot / AI / model names anywhere in the body.
-- No em-dashes (`—`) in prose. Use ` · ` or `→` per `feedback_no_em_dash.md`.
+- No "Co-Authored-By: Claude" trailer. No "🤖 Generated with ..." footer. No mention of Claude / Copilot / AI / model names anywhere in the body.
+- No em-dashes (` - `) in prose. Use ` · ` or `→` per `feedback_no_em_dash.md`.
 - No HTML entities. Use raw markdown.
 - No links to internal `/tmp/*` or local-machine paths.
-- No screenshots embedded as base64 — link to wiki / Figma instead.
+- No screenshots embedded as base64  -  link to wiki / Figma instead.
 
 ## Compaction policy
 
@@ -96,8 +96,8 @@ If the comment exceeds 4000 characters, compact in this order:
 1. `summary` trimmed to 1 paragraph.
 2. `acceptance_criteria` list moved to a `<details>` collapsible.
 3. `build_and_test` details collapsed to a one-line outcome.
-4. `prs_branches` stays verbatim — never compact.
-5. `next_steps` stays verbatim — never compact.
+4. `prs_branches` stays verbatim  -  never compact.
+5. `next_steps` stays verbatim  -  never compact.
 
 Below 4000 chars, no compaction; render the full template.
 
@@ -114,7 +114,7 @@ Token resolution: `gh auth status` for the active GitHub account selected in Pha
 Every issue comment post is paired with `pipeline/scripts/update-issue-progress.sh "$TASK_ID"` in the same Phase 7 step. Order: comment FIRST (so the timestamp marks the run), flags SECOND (so the body diff is one logical change).
 
 ```bash
-# Phase 7 Step 5 — issue channel
+# Phase 7 Step 5  -  issue channel
 gh issue comment "$ISSUE_NUMBER" --repo "$ORG/$REPO" --body-file /tmp/channels-$TASK_ID-issue.md
 bash $HOME/.claude/scripts/update-issue-progress.sh "$TASK_ID"
 ```
@@ -138,4 +138,4 @@ A failed assertion blocks `pre-push-check.sh`. This catches runs where the agent
 - Section order is fixed: `title` → `summary` → `prs_branches` → `acceptance_criteria` → `build_and_test` → `figma_extras` (cond.) → `next_steps` → `ref_footer`. Conditional sections may be omitted but never reordered.
 - Humanizer pass runs **after** body assembly and **before** compaction / POST.
 - Body content language follows `prefs.global.outputLanguage`. Repo names, branch names, commit SHAs, URLs, the `Ref: #N` footer, and the `### Build & Test` heading itself stay verbatim. The template (this doc) is English because `promptLanguage="en"` is locked.
-- Never update issue body Progress flags without also posting this comment — see "The hard rule" above and `pairing` block below.
+- Never update issue body Progress flags without also posting this comment  -  see "The hard rule" above and `pairing` block below.

package/pipeline/commands/multi-agent/refs/channels/jira.md

@@ -1,4 +1,4 @@
-# Channel adapter — Jira comment
+# Channel adapter  -  Jira comment
 
 > Detailed contract for the `jira` channel of `/multi-agent:channels`. Split out of `channels.md` in v8.0.0; the parent doc keeps a one-line summary and a link here.
 
@@ -11,16 +11,16 @@ Every Jira comment posted by this adapter follows the same section order. Sectio
 | # | Section key | Heading (`tr`) | Heading (`en`) | Required? |
 |---|---|---|---|---|
 | 1 | `summary` | `## Yapılan Çalışma Özeti` | `## Work Summary` | always |
-| 2 | `test_scenarios` | `## Test Senaryoları` | `## Test Scenarios` | always (use "—" placeholder line if truly N/A) |
+| 2 | `test_scenarios` | `## Test Senaryoları` | `## Test Scenarios` | always (use " - " placeholder line if truly N/A) |
 | 3 | `context_refs` | `## Bağlantılar` | `## References` | when any link exists |
 
 > Heading levels in the source markdown are `##`. The wiki-markup converter (next section) rewrites them to `h2.` for Jira rendering.
 
 ### Section content rules
 
-**`summary`** — 2-5 sentences in `outputLanguage`. What changed, why, and the user-visible impact. No "we", no marketing tone. Past tense (the work is done at the time the comment goes up).
+**`summary`**  -  2-5 sentences in `outputLanguage`. What changed, why, and the user-visible impact. No "we", no marketing tone. Past tense (the work is done at the time the comment goes up).
 
-**`test_scenarios`** — Given/When/Then numbered list. One scenario per acceptance criterion. The heading and scenario text are rendered in `outputLanguage` at write-time; the template itself (this file) shows the English skeleton:
+**`test_scenarios`**  -  Given/When/Then numbered list. One scenario per acceptance criterion. The heading and scenario text are rendered in `outputLanguage` at write-time; the template itself (this file) shows the English skeleton:
 
 ```markdown
 ## Test Scenarios
@@ -31,9 +31,9 @@ Every Jira comment posted by this adapter follows the same section order. Sectio
 2. **Given** ...
 ```
 
-Code identifiers (function names, file paths) stay verbatim — they are not translated. When there are no executable scenarios (pure doc change, dependency bump), write a single line: `- No manual test required — <short reason>`.
+Code identifiers (function names, file paths) stay verbatim  -  they are not translated. When there are no executable scenarios (pure doc change, dependency bump), write a single line: `- No manual test required  -  <short reason>`.
 
-**`context_refs`** — flat bullet list of external links the work depends on or produced. PR URL is **not** repeated here; it lives on the first line (see *Cross-link injection*). Common entries (only when present in the task):
+**`context_refs`**  -  flat bullet list of external links the work depends on or produced. PR URL is **not** repeated here; it lives on the first line (see *Cross-link injection*). Common entries (only when present in the task):
 
 ```markdown
 ## References
@@ -51,7 +51,7 @@ The links are pulled from `agent-state.json.contextLinks[]` (see Phase 0 link ex
 
 ```
 1. Read agent-state.json (taskId, contextLinks, prUrls, language).
-2. Build section bodies in markdown — summary first, test_scenarios next, context_refs last.
+2. Build section bodies in markdown  -  summary first, test_scenarios next, context_refs last.
 3. Run the assembled body through the `humanizer` skill (see Hard rules below).
 4. Apply Cross-link injection (PR URL on line 1).
 5. Run Wiki markup conversion.
@@ -65,7 +65,7 @@ Body markdown is rewritten to Jira wiki markup before POST:
 | Markdown | Jira wiki |
 |---|---|
 | `### Heading` | `*Heading*` |
-| `- [ ] task` / `- [x] task` | `# task` (numbered list — Jira renders TODO checkboxes inconsistently) |
+| `- [ ] task` / `- [x] task` | `# task` (numbered list  -  Jira renders TODO checkboxes inconsistently) |
 | `` `code` `` | `{{code}}` |
 | Tables (` | h | h | / | --- | --- |`) | `||h||h||` then `|c|c|` rows |
 | Code fences ` ```lang ` | `{code:lang} ... {code}` |
@@ -82,14 +82,14 @@ PR: https://github.com/<org>/<repo>/pull/4321
 Phase 4 review accepted 2 findings...
 ```
 
-In multi-repo mode, `channels-multi-repo.sh render-jira <state> <body>` prepends a bulleted `* PR:` list — primary first, extras after. Single-repo tasks fall through to the unchanged body.
+In multi-repo mode, `channels-multi-repo.sh render-jira <state> <body>` prepends a bulleted `* PR:` list  -  primary first, extras after. Single-repo tasks fall through to the unchanged body.
 
 ## Token resolution
 
 Token comes from `prefs.global.keychainMapping.jira` → `~/.claude/lib/credential-store.sh get "$ACCOUNT_JIRA_TOKEN_KEY"`. Resolution path:
 
 1. Read `keychainMapping.jira` from prefs.
-2. Resolve via `credential-store.sh get` — the driver auto-delegates to `keychain.py` on macOS / Linux and PowerShell `CredentialManager` on Windows.
+2. Resolve via `credential-store.sh get`  -  the driver auto-delegates to `keychain.py` on macOS / Linux and PowerShell `CredentialManager` on Windows.
 3. Missing → adapter prompts the inline Token Save Flow from `setup.md` (clipboard-based); user can save now or skip this run.
 4. Expired (401) → same Save Flow with the "expired" trigger; on skip, returns `{status: "skipped", reason: "token expired"}`, does not block other adapters.
 
@@ -112,16 +112,16 @@ curl -s -X POST -H "Authorization: Bearer $JIRA_TOKEN" \
      "$JIRA_BASE/rest/api/2/issue/$JIRA_ID/comment"
 ```
 
-The dispatch summary line includes the comment URL with `?focusedCommentId=…` so the user can paste it into Slack/Teams.
+The dispatch summary line includes the comment URL with `?focusedCommentId=...` so the user can paste it into Slack/Teams.
 
 ## Wiki → Jira auto-link triad
 
-When the **Wiki** adapter writes pages on the same run AND `prefs.global.wikiToJiraComment === true`, the Wiki adapter also posts a humanizer-passed Jira comment summarizing wiki pages (component name + variant count + wiki URL). That secondary comment is independent of this adapter — both can coexist on the same issue. Full contract: `refs/issue-jira-triad.md`.
+When the **Wiki** adapter writes pages on the same run AND `prefs.global.wikiToJiraComment === true`, the Wiki adapter also posts a humanizer-passed Jira comment summarizing wiki pages (component name + variant count + wiki URL). That secondary comment is independent of this adapter  -  both can coexist on the same issue. Full contract: `refs/issue-jira-triad.md`.
 
 ## Hard rules (must not regress)
 
-- Real newlines, no HTML entities — heredoc + `jq --rawfile` + `curl --data-binary @file`.
+- Real newlines, no HTML entities  -  heredoc + `jq --rawfile` + `curl --data-binary @file`.
 - Section order is fixed: `summary` → `test_scenarios` → `context_refs`. Never insert sections between them; never reorder.
-- Humanizer pass runs **after** body assembly and **before** wiki-markup conversion. Tone target: informal but technical. No marketing voice, no "we are excited", no "I have…".
+- Humanizer pass runs **after** body assembly and **before** wiki-markup conversion. Tone target: informal but technical. No marketing voice, no "we are excited", no "I have...".
 - Body content language follows `prefs.global.outputLanguage`. Code identifiers, file paths, type names, branch names, and the wiki-markup syntax stay verbatim. The `promptLanguage="en"` lock means any LLM prompt that produces the body is in English; the body itself is then rendered in the user's language.
-- Adapter failures are non-blocking — a missing token or 401 returns `skipped`/`failed`, the loop keeps going for PR / Confluence / Wiki.
+- Adapter failures are non-blocking  -  a missing token or 401 returns `skipped`/`failed`, the loop keeps going for PR / Confluence / Wiki.