@mmerterden/multi-agent-pipeline 18.0.0 → 19.1.0

package/pipeline/skills/shared/core/multi-agent/SKILL.md

@@ -75,13 +75,13 @@ multi-agent "LoginView dark mode fix" autopilot
 
 | Phase | Normal | Autopilot |
 |-------|--------|-----------|
-| Phase 2 (Plan Approval Gate) | Clarification (max 2 rounds) + approval loop  -  user replies `onayla`/`iptal`/free-text | **Gate skip**  -  log the plan, go straight to Phase 3 (autopilot contract: zero interaction) |
-| Phase 5 (User Test) | "Want to test it?" → wait | Skip → go straight to Phase 6 |
-| Phase 6 (Commit) | "Want to commit?" → wait | Automatic commit + push |
-| Phase 6 (PR) | "Want to open a PR?" → wait | Automatically create the PR |
+| Phase 1 (Plan Approval Gate) | Clarification (max 2 rounds) + approval loop  -  user replies `onayla`/`iptal`/free-text | **Gate skip**  -  log the plan, go straight to Phase 3 (autopilot contract: zero interaction) |
+| Phase 5 (User Test) | "Want to test it?" → wait | Skip → go straight to Phase 4 |
+| Phase 4 (Commit) | "Want to commit?" → wait | Automatic commit + push |
+| Phase 4 (PR) | "Want to open a PR?" → wait | Automatically create the PR |
 
 **What NEVER skips (even in autopilot):**
-- Phase 4 Review → if there is a blocking finding, return to Phase 3, fix + rebuild automatically (safety)
+- Phase 3 Review → if there is a blocking finding, return to Phase 3, fix + rebuild automatically (safety)
 - Kill/Purge confirmations → destructive operations always ask
 - Build fail → fix + rebuild automatically (max 3 retries). If it still fails after 3 retries → pause, ask the user
 
@@ -108,8 +108,8 @@ ID is stored in `agent-state.json` and shown in `multi-agent status`:
 
 | ID | Jira | Branch | Phase | Status |
 |----|------|--------|-------|--------|
-| #1 | PROJ-12345 | feature/PROJ-12345-... | 3/7 Dev | ⚡ in progress |
-| #2 | PROJ-67890 | feature/PROJ-67890-... | 1/7 Analysis | 📊 scanning |
+| #1 | PROJ-12345 | feature/PROJ-12345-... | 2/5 Dev | ⚡ in progress |
+| #2 | PROJ-67890 | feature/PROJ-67890-... | 1/5 Analysis | 📊 scanning |
 ```
 
 ID counter stored at `.worktrees/.multi-agent-counter` (persists across sessions).
@@ -181,14 +181,14 @@ When `multi-agent purge` is called:
 
 When `multi-agent resume [id]` is called:
 
-1. **Find state file**: `$HOME/.claude/logs/multi-agent/{project}/{task-id}/agent-state.json`  -  that is where Phase 0 writes it, not inside the worktree. A task finalized by Phase 6 keeps its state at `.../{task-id}/artifacts/agent-state.json`, so look there too before reporting not-found.
+1. **Find state file**: `$HOME/.claude/logs/multi-agent/{project}/{task-id}/agent-state.json`  -  that is where Phase 0 writes it, not inside the worktree. A task finalized by Phase 4 keeps its state at `.../{task-id}/artifacts/agent-state.json`, so look there too before reporting not-found.
    - If no `id` given, take the most recent task dir with `status != "done"`
 2. **Read state**: Parse `agent-state.json` → determine last completed phase
 3. **Restore context**: Read `agent-log.md` for previous findings:
-   - Phase 1 analysis findings → reuse in Phase 2+
-   - Phase 2 plan/todos → reuse in Phase 3+
-   - Phase 3 code changes → already on disk in worktree
-   - Phase 4 review findings → reuse if re-reviewing
+   - Phase 1 analysis findings → reuse in Phase 2+ (Dev onwards)
+   - Phase 1 plan/todos → reuse in Phase 2+
+   - Phase 2 code changes → already on disk in worktree
+   - Phase 3 review findings → reuse if re-reviewing
 4. **Resume from next phase**: Skip completed phases, start from `currentPhase + 1`
 5. **Log**: `🔄 Resumed PROJ-{id} from Phase {N}`
 
@@ -204,28 +204,29 @@ This works across sessions because:
 
 Every agent persona under `$HOME/.claude/agents/*.md` declares a `preferredModel` frontmatter field. The orchestrator MUST honor it on every dispatch, on both Claude Code and Copilot CLI  -  cross-CLI parity is enforced by `smoke-cross-cli-behavior.sh`.
 
-| Persona | `preferredModel` | Rationale (condensed) |
-|---|---|---|
-| `explorer` | `sonnet` | Scan/pattern work, cost-efficient without quality loss |
-| `code-reviewer` | `fable` | Reviewer 1; Phase 4 sets Reviewer 2 `opus`, Reviewer 3 `sonnet` |
-| `security-auditor` | `opus` | False-negative cost is high; opus reduces miss rate |
-| `ios-architect` | `fable` | Deep module/protocol/migration reasoning |
-| `android-architect` | `fable` | Gradle modules, Compose stability, Hilt graphs |
-| `backend-architect` | `fable` | API + migration + scaling reasoning |
+Each persona file carries its own `modelRationale`; this is the rung only.
 
-**Dispatch contract (pseudo-code):**
+| Persona | `preferredModel` |
+|---|---|
+| `explorer` | `sonnet` |
+| `code-reviewer` | `fable` (Reviewer 1; Phase 3 sets Reviewer 2 `opus`, Reviewer 3 `sonnet`) |
+| `security-auditor` | `opus` |
+| `ios-architect` / `android-architect` / `backend-architect` | `fable` |
+
+**Dispatch contract:**
 
 ```bash
 persona_file="$HOME/.claude/agents/${persona}.md"
 pref_model="$(awk '/^preferredModel:/ {print $2; exit}' "$persona_file")"
-override="${PHASE_MODEL_OVERRIDE:-}"   # set by orchestrator per-dispatch (e.g. Phase 4 Reviewer 3 → sonnet)
-resolved_model="${override:-${pref_model:-opus}}"
+override="${PHASE_MODEL_OVERRIDE:-}"   # per-dispatch, e.g. Phase 3 Reviewer 3 → sonnet
+routed="${override:-$("$HOME/.claude/lib/model-dispatch.sh" subagent --persona "$persona" --phase "$currentPhase" --task-kind "$taskType" --default "${pref_model:-opus}" 2>/dev/null)}"
+resolved_model="${routed:-${pref_model:-opus}}"
 
 export CLAUDE_CODE_SUBAGENT_MODEL="$resolved_model"
-# Claude Code honors the env var; Copilot CLI reads the same env + passes as --model flag.
+# Claude Code honors the env var; Copilot CLI also passes it as --model.
 ```
 
-**Precedence:** per-dispatch `PHASE_MODEL_OVERRIDE` > persona `preferredModel` > global default (`opus`).
+**Precedence:** per-dispatch `PHASE_MODEL_OVERRIDE` > `prefs.global.modelRouting` rule > persona `preferredModel` > global default (`opus`). Routing here is Anthropic-only: features/model-fallback.md "Routing at dispatch".
 
 **Observability:** emit `phase.agent.dispatch` OTel span with `{persona, resolved_model, override_source}` attributes when `MULTI_AGENT_OTEL_SPANS=1` (see `phase-tracker.sh`).
 
@@ -255,7 +256,7 @@ matched_skills=$(node "$HOME/.claude/scripts/match-skills.mjs" \
   --limit 12 \
   --json)
 
-# Inject only matched skills[] into subagent prompts for Phase 2-4.
+# Inject only matched skills[] into subagent prompts for Phase 1-3.
 # Skills not in the matched list are not loaded  -  saves ~10K-30K tokens
 # per subagent dispatch on small tasks.
 ```
@@ -289,16 +290,14 @@ and the copy named a path the code had stopped using.
 
 Every user-facing phase title  -  TaskCreate cards, `phase-banner.sh` headers, and any status line rendered to the terminal  -  MUST come from this table. Phase labels are English on every host (`promptLanguage` is fixed to `en`; picker text follows its own matrix):
 
-| # | Label                  |
-|---|------------------------|
-| 0 | Phase 0: Init          |
-| 1 | Phase 1: Analysis      |
-| 2 | Phase 2: Planning      |
-| 3 | Phase 3: Dev           |
-| 4 | Phase 4: Review        |
-| 5 | Phase 5: Test          |
-| 6 | Phase 6: Commit & PR   |
-| 7 | Phase 7: Report        |
+| # | Label                |
+|---|----------------------|
+| 0 | Phase 0: Init        |
+| 1 | Phase 1: Plan        |
+| 2 | Phase 2: Dev         |
+| 3 | Phase 3: Review      |
+| 4 | Phase 4: Commit & PR |
+| 5 | Phase 5: Report      |
 
 **Render rule:**
 
@@ -313,7 +312,7 @@ Every user-facing phase title  -  TaskCreate cards, `phase-banner.sh` headers, a
 All TaskCreate calls fire in strict phase-number order BEFORE any TaskUpdate is applied (Claude Code path; Copilot CLI does not have a TaskList widget so this rule is Claude-only). The native widget renders by creation order, not by phase-number metadata  -  out-of-order calls produce visually scrambled tile stacks (e.g. `1 ✓ · 2 ✓ · 4 ✓ · 0 ▶ · 3 ☐`) even when the underlying state file is correct. Pre-marking phases as completed/skipped before Phase 0 starts is FORBIDDEN: register the tile in order with default `pending` status, then flip via TaskUpdate when the phase actually short-circuits. Mode-specific phase sets:
 
 - `multi-agent`: 0 → 1 → 2 → 3 → 4 → 5 → 6 → 7
-- `multi-agent-local`, `multi-agent-autopilot`, `multi-agent-local-autopilot`: 0 → 1 → 2 → 3 → 4 → 6 → 7 (the interactive Phase 5 gate needs a worktree checkout and an attended run)
+- `multi-agent-local`, `multi-agent-autopilot`, `multi-agent-local-autopilot`: 0 → 1 → 2 → 3 → 4 → 5 (the interactive Phase 5 gate needs a worktree checkout and an attended run)
 - `multi-agent-analysis`: 0 → 1 → 2 → 4 → 6 → 7 (no code, so no Dev and no Test)
 
 Depth decides WHICH of the command's set is registered. The tracker boots at Step -1, long before the depth question can be asked, so it registers Phase 0 alone and the remaining tiles are created at Step 7.5 once the answer is known - a Short run never draws an Analysis or Planning tile.
@@ -421,26 +420,26 @@ Full contract: `refs/tracker-contract.md` section "TaskCreate ordering (strict)"
 
 **IMPORTANT**: Update `agent-state.json` at EVERY phase transition. This file is the resume source of truth.
 
-### Phase 1: Analysis (claude-sonnet-5, `explorer` persona)
-1. Launch **explore agents** (parallel) to scan codebase:
-   - Related files to the task
-   - Existing patterns and conventions
-   - Potential impact areas
+### Phase 1: Plan
+Two halves, one phase, one approval gate (Phases 1 and 2 until 19.0.0).
+
+**1a  -  Analysis** (claude-sonnet-5, `explorer` persona)
+1. Launch **explore agents** (parallel) to scan the codebase: related files, existing patterns and conventions, potential impact areas
 2. Optionally launch **security-auditor** agent for pre-check
 3. Summarize findings
-4. Log: `📊 Phase 1: Analysis  -  {N} files identified, {summary}`
+4. Log: `📊 Phase 1: Plan (analysis)  -  {N} files identified, {summary}`
 
-### Phase 2: Planning (claude-fable-5)
+**1b  -  Planning** (claude-fable-5)
 1. Create task breakdown → todos with dependencies
 2. Launch **ios-architect** agent for architecture review (if structural changes)
 3. Determine development approach per todo (new file, modify, refactor)
-4. Log: `🧠 Phase 2: Plan  -  {N} todos created`
-5. **Plan Approval Gate** (Full + interactive only  -  a Short run has no plan, autopilot may not ask). Full flow in `refs/phases/phase-2-planning.md` Step 5:
+4. Log: `🧠 Phase 1: Plan  -  {N} todos created`
+5. **Plan Approval Gate** (Full + interactive only  -  a Short run has no plan, autopilot may not ask). Full flow in `refs/phases/phase-1-plan.md` Step 5:
    - **5a  -  Clarification** (conditional, max 2 rounds): if the Jira/issue description is ambiguous (vague acceptance, UI task without Figma, API task without endpoint contract, `ambiguityScore >= 2`, parent-story scope drift), ask structured questions before rendering the plan. User answers → plan regenerated. If it is still unclear after the 2nd round, render the plan with a "best-effort" banner.
    - **5b  -  Approval loop**: render plan → user: `onayla`/`iptal`/free-text. A free-text edit request → the planning model (Fable) revises the plan → show it again. No iteration cap; user controls exit via `onayla` or `iptal`.
-   - Persist `clarificationRounds`, `clarificationQuestions`, `clarificationAnswers`, `planIterations`, `planApprovedAt`, `planEditRequests` to `state.phases["2"]`.
+   - Persist `clarificationRounds`, `clarificationQuestions`, `clarificationAnswers`, `planIterations`, `planApprovedAt`, `planEditRequests` to `state.phases["1"]`.
 
-### Phase 3: Dev (claude-sonnet-5)
+### Phase 2: Dev (claude-sonnet-5)
 For each todo (respecting dependency order):
 1. Update todo status: `in_progress`
 2. **TDD cycle**:
@@ -450,31 +449,31 @@ For each todo (respecting dependency order):
 3. Run build: `xcodebuild` via **task agent**
 4. If build fails → fix → rebuild (max 3 attempts, track `retryCount` in `agent-state.json`)
 5. Update todo status: `done`
-6. Log: `⚡ Phase 3: {todo-id}  -  Test ✅ Build ✅`
+6. Log: `⚡ Phase 2: {todo-id}  -  Test ✅ Build ✅`
 
-### Phase 4: Review (parallel + triage)
+### Phase 3: Review (parallel + triage)
 0. **Diff Risk Scoring (advisory, v8.3+)**  -  before reviewer dispatch run `node $HOME/.claude/scripts/diff-risk-score.mjs --base "$BASE_BRANCH" --top 5` and inject the top-N risk-ranked files as a `${PRIORITY_FILES}` block into each reviewer's prompt. Heuristic, deterministic, sub-second, never gates the pipeline. Disabled when `prefs.global.diffRiskAdvisory = false`. Signals: security paths (×3), schema migrations (×4), public API surfaces (×2), no-test-change (×2.5), complexity delta (×1.5), UI-critical paths (×1.5), loc changed (×1).
 1. Launch **code-reviewer** agents in parallel. Reviewer set depends on which CLI is hosting the pipeline:
    - **Claude Code** (3 reviewers): `claude-fable-5` (deep security + architecture) + `claude-opus-5` (edge cases, different perspective) + `claude-sonnet-5` (quality + correctness)
    - **Copilot CLI** (3 reviewers): `gpt-5.4` (edge cases, different perspective) + `claude-opus-5` + `claude-sonnet-5` (Fable 5 is not offered on Copilot CLI)
    - Triage: single top-tier pass over merged findings (`claude-fable-5` on Claude Code, `claude-opus-5` on Copilot CLI)
 2. Collect findings, classify:
-   - 🔴 **Blocking** → must fix → back to Phase 3 (max 3 iterations)
+   - 🔴 **Blocking** → must fix → back to Phase 2 (max 3 iterations)
    - 🟡 **Important** → fix and re-review
    - 🟢 **Suggestion** → apply if reasonable
-3. Log: `🔍 Phase 4: Review  -  {consensus}`
+3. Log: `🔍 Phase 3: Review  -  {consensus}`
 
-### Phase 5: Test
-Lets the user physically test the code before opening a PR. The prompt MUST make it explicit that saying yes **removes the worktree and checks the branch out locally**  -  otherwise the user is hit with an implicit side effect.
+#### Phase 3 user test (optional, interactive)
+Lets the user test the code before the PR. The prompt MUST say that yes **removes the worktree and checks the branch out locally**, or the side effect is implicit.
 
-0. **Test Gap Report (advisory, v8.3+)**  -  before the local-checkout prompt run `node $HOME/.claude/scripts/test-gap-scan.mjs --base "$BASE_BRANCH" --stack <ios|android|python|node>` to surface public symbols added in this branch that have no paired test. Heuristic, deterministic, sub-second, never gates by default. iOS `*View.swift` / Android `@Composable` symbols default to `important` severity; other public API additions to `suggestion`. Optional gating via `prefs.testGap.blockingThreshold` (loops back to Phase 4 rework when the important+blocking count exceeds the threshold). Disabled when `prefs.testGap.enabled = false`.
+0. **Test Gap Report (advisory, v8.3+)**  -  before the local-checkout prompt run `node $HOME/.claude/scripts/test-gap-scan.mjs --base "$BASE_BRANCH" --stack <ios|android|python|node>` to surface public symbols added in this branch that have no paired test. Heuristic, deterministic, sub-second, never gates by default. iOS `*View.swift` / Android `@Composable` symbols default to `important` severity; other public API additions to `suggestion`. Optional gating via `prefs.testGap.blockingThreshold` (loops back to Phase 2 rework when the important+blocking count exceeds the threshold). Disabled when `prefs.testGap.enabled = false`.
 1. **Ask** with a native `AskUserQuestion` picker (never a typed y/N prompt). The options MUST make the local-checkout side effect explicit  -  testing removes the worktree and checks the branch out into the main repo:
    - `question`: "Check out locally to test now?" (rendered in `outputLanguage`)
    - `header`: "Test" (English, <=12 chars)
    - `options`:
      - `{ label: "Test now", description: "Removes the worktree and checks the branch out into the main repo for Xcode / manual test" }`
-     - `{ label: "Skip", description: "Stay in the worktree and go to Phase 6" }`
-   - **Skip** → go to Phase 6
+     - `{ label: "Skip", description: "Stay in the worktree and go to Phase 4" }`
+   - **Skip** → go to Phase 4
    - **Test now** → continue:
 2. **Remove the worktree and switch to the branch** (automatic):
    ```bash
@@ -491,18 +490,18 @@ Lets the user physically test the code before opening a PR. The prompt MUST make
      • Xcode → open the app's `.xcworkspace` → Cmd+B → Cmd+U
      • Manual test on the Simulator
 
-   ✅ "tamam" → proceeds to Phase 6
-   ❌ "fix: ..." → worktree is recreated, returns to Phase 3
+   ✅ "tamam" → proceeds to Phase 4
+   ❌ "fix: ..." → worktree is recreated, returns to Phase 2
    ```
 4. **Pause and wait**: Wait for the user's response
 5. **If a fix is needed**:
    - Recreate the worktree: `git worktree add .worktrees/PROJ-{id} {branch-name}`
-   - Return to Phase 3
-6. Log: `🧪 Phase 5: Test  -  {result}`
+   - Return to Phase 2
+6. Log: `🧪 Phase 3: Review (user test)  -  {result}`
 
 > ⚠️ Commits live on the branch  -  removing the worktree does NOT delete the commits.
 
-### Phase 6: Commit & PR
+### Phase 4: Commit & PR
 
 **Project-specific commit strategy:**
 
@@ -513,7 +512,7 @@ Lets the user physically test the code before opening a PR. The prompt MUST make
 2. Run `/figma-iteration-commit {ComponentName}`
    - Build verification, test, key sync, code review, submodule commits to `iteration/develop`, push with rebase-retry, issue housekeeping, auto-unblock dependents  -  the skill handles all of it
    - Do NOT commit manually  -  the skill manages everything
-3. Log: `📦 Phase 6: figma-iteration-commit  -  {ComponentName}`
+3. Log: `📦 Phase 4: figma-iteration-commit  -  {ComponentName}`
 
 #### my-app / generic
 1. **Ask**: "Want to commit?"
@@ -524,15 +523,15 @@ Lets the user physically test the code before opening a PR. The prompt MUST make
    - Author: resolved from `prefs.global.identities[]` (e.g. `Ada Lovelace <ada@example.com>`)  -  NEVER hardcode.
 4. Push to remote
 5. **Ask**: "Want to open a Pull Request?"
-   - **No** → go to Phase 7 (only commit + push will have been done)
+   - **No** → go to Phase 5 (only commit + push will have been done)
    - **Yes** → create the PR (target: source branch)
 6. **Issue body update** (if GitHub Issue exists):
    - Fill PR links in issue body: `- **common:** {PR URL}`, `- **uicomponents:** {PR URL}`
    - Update Progress flags: `Implementation 🟢`, `Testing 🟢`, `Code Connect 🟢`
    - Use `gh issue edit {issueNo} --body "{updated body}"`  -  preserve all existing sections
-7. Log: `📦 Phase 6: Commit {sha}  -  PR #{number}`
+7. Log: `📦 Phase 4: Commit {sha}  -  PR #{number}`
 
-### Phase 7 Report Step 2: WIKI + Figma Screenshots (for component tasks with GitHub Issue)
+### Phase 5 Report Step 2: WIKI + Figma Screenshots (for component tasks with GitHub Issue)
 
 Skip this sub-step if the task is NOT a component implementation (e.g., bug fix, refactor).
 
@@ -566,9 +565,9 @@ Skip this sub-step if the task is NOT a component implementation (e.g., bug fix,
    git push origin HEAD:master
    ```
 7. **Update issue Wiki flag**: Set `Wiki` → `🟢` in issue body
-8. Log: `📖 Phase 7 Step 2: Wiki  -  {ComponentName}.md + {ComponentName}-iOS.md + screenshot`
+8. Log: `📖 Phase 5 Step 2: Wiki  -  {ComponentName}.md + {ComponentName}-iOS.md + screenshot`
 
-### Phase 7: Report
+### Phase 5: Report
 1. Finalize `agent-log.md` with ALL sections:
    - **Timeline table**: phase, agent, model, duration, status, detail
    - **Agent Activity Report**: per-agent call count, total duration, models used, skill count
@@ -586,7 +585,7 @@ Skip this sub-step if the task is NOT a component implementation (e.g., bug fix,
    📖 Wiki: {ComponentName}.md pushed to wiki master
    📋 Full report: ~/.claude/logs/multi-agent/{project}/{task-id}/agent-log.md
    ```
-3. Log: `📋 Phase 7: Report complete`
+3. Log: `📋 Phase 5: Report complete`
 
 ---
 
@@ -635,27 +634,27 @@ Sub-agents have embedded skills in their `.agent.md` files. Each agent is pre-lo
 
 | Agent | Embedded Skills | When Activated |
 |-------|----------------|----------------|
-| **code-reviewer** | Code Review Excellence, Security Audit, Performance Review, TDD Verification, Error Detective | Phase 4: Review |
-| **ios-architect** | Spec-Driven Architecture, Context Management, Multi-Agent Coordination, API Design, Performance Architecture, Design System Governance | Phase 2: Planning |
-| **security-auditor** | iOS Security Deep Dive, App Store Review Gates, Third-Party SDK Risk, Error Detective (Security) | Phase 1: Analysis (pre-check) + Phase 4: Review |
+| **code-reviewer** | Code Review Excellence, Security Audit, Performance Review, TDD Verification, Error Detective | Phase 3: Review |
+| **ios-architect** | Spec-Driven Architecture, Context Management, Multi-Agent Coordination, API Design, Performance Architecture, Design System Governance | Phase 1: Plan |
+| **security-auditor** | iOS Security Deep Dive, App Store Review Gates, Third-Party SDK Risk, Error Detective (Security) | Phase 1: Plan (analysis half, pre-check) + Phase 3: Review |
 
 ### Phase → Agent → Skills Flow
 
 ```
-Phase 1: Analysis
+Phase 1: Plan  -  analysis half
   ├─ explore agents (no skills needed  -  pure file reading)
   └─ security-auditor agent
        └─ Skills: iOS Security Deep Dive, App Store Review Gates, SDK Risk
 
-Phase 2: Planning
+Phase 1: Plan  -  planning half
   └─ ios-architect agent
        └─ Skills: Spec-Driven Architecture, API Design, Performance Architecture
 
-Phase 3: Dev
+Phase 2: Dev
   └─ Ana agent (reads copilot-instructions.md directly)
        └─ TDD, token rules, code style  -  from global instructions
 
-Phase 4: Review (parallel + triage)
+Phase 3: Review (parallel + triage)
   Claude Code  (3 parallel):
     ├─ code-reviewer (claude-opus)   → all 5 review skills
     └─ code-reviewer (claude-sonnet) → all 5 review skills
@@ -671,13 +670,13 @@ Phase 4: Review (parallel + triage)
 When calling sub-agents, the ana agent SHOULD add task-specific context to the prompt:
 
 ```
-For code-reviewer in Phase 4:
+For code-reviewer in Phase 3:
   "Review this diff for PROJ-{id}. Focus areas based on analysis:
    - {files changed summary from Phase 1}
-   - {architecture decisions from Phase 2}
+   - {architecture decisions from Phase 1}
    - {specific risk areas identified}"
 
-For ios-architect in Phase 2:
+For ios-architect in Phase 1:
   "Evaluate architecture for PROJ-{id}. Context:
    - {task description from Jira/GitHub}
    - {affected modules from Phase 1 analysis}
@@ -697,9 +696,9 @@ When `multi-agent status` is called, show:
 
 | ID | Jira | Branch | Phase | Status | Duration |
 |----|------|--------|-------|--------|----------|
-| #1 | PROJ-12345 | feature/PROJ-12345-... | 3/7 Dev | ⚡ todo-2 in progress | 4m |
-| #2 | PROJ-67890 | feature/PROJ-67890-... | 4/7 Review | 🔍 Waiting consensus | 7m |
-| #3 | PROJ-11111 | feature/PROJ-11111-... | 7/7 DONE | ✅ Complete | 12m |
+| #1 | PROJ-12345 | feature/PROJ-12345-... | 2/5 Dev | ⚡ todo-2 in progress | 4m |
+| #2 | PROJ-67890 | feature/PROJ-67890-... | 3/5 Review | 🔍 Waiting consensus | 7m |
+| #3 | PROJ-11111 | feature/PROJ-11111-... | 5/5 DONE | ✅ Complete | 12m |
 
 💡 kill #2  |  log #1  |  resume #3
 ```

package/pipeline/skills/shared/core/multi-agent-autopilot/SKILL.md

@@ -17,9 +17,9 @@ Run the task end-to-end with no confirmations.
 | Phase | Normal | Autopilot |
 |-----|--------|-----------|
 | Phase 2 (Plan) | "Shall I continue?" → wait | Go straight to Phase 3 |
-| Phase 5 (Test) | "Do you want to test?" → wait | Skip → Phase 6 |
-| Phase 6 (Commit) | "Shall I commit?" → wait | Automatic commit + push |
-| Phase 6 (PR) | "Shall I open a PR?" → wait | Create PR automatically |
+| Phase 5 (Test) | "Do you want to test?" → wait | Skip → Phase 4 |
+| Phase 4 (Commit) | "Shall I commit?" → wait | Automatic commit + push |
+| Phase 4 (PR) | "Shall I open a PR?" → wait | Create PR automatically |
 
 ## What is NEVER skipped
 

package/pipeline/skills/shared/core/multi-agent-channels/SKILL.md

@@ -1,14 +1,14 @@
 ---
 name: multi-agent-channels
 language: en
-description: "Multi-channel reporter  -  Jira/Confluence/Wiki/PR description. Multi-select channels + content, humanizer pass, reviewer-preserving Bitbucket PR PUT. Phase 7 delegates to this skill; users can invoke post-hoc by Jira ID / PR URL / branch."
+description: "Multi-channel reporter  -  Jira/Confluence/Wiki/PR description. Multi-select channels + content, humanizer pass, reviewer-preserving Bitbucket PR PUT. Phase 5 delegates to this skill; users can invoke post-hoc by Jira ID / PR URL / branch."
 user-invocable: true
 argument-hint: '<Jira-id | PR-url | #N | Jira-url> [--channels pr,jira,confluence,wiki] [--content normal,technical,test,auto-diff,note] [--message "..."] [--message-file path] [--dry-run] [--append] [--ready]'
 ---
 
 # multi-agent-channels  -  Multi-Channel Reporter
 
-> **TLDR**  -  Single entry point for posting task reports to external channels. Supports Jira, Confluence, Wiki (component-only), and PR description updates. Multi-select channels × multi-select content sources. Phase 7 of the pipeline delegates to this skill; users can also invoke it post-hoc by Jira ID / PR URL / branch.
+> **TLDR**  -  Single entry point for posting task reports to external channels. Supports Jira, Confluence, Wiki (component-only), and PR description updates. Multi-select channels × multi-select content sources. Phase 5 of the pipeline delegates to this skill; users can also invoke it post-hoc by Jira ID / PR URL / branch.
 >
 > **Replaces the old enrich skill in v5.7+**  -  all enrich capabilities (diff auto-summarize, manual mode, reviewer-preserving Bitbucket PR PUT) are preserved and extended with two additional channels (Confluence, Wiki).
 
@@ -39,7 +39,7 @@ multi-agent-channels PROJ-12345 --dry-run                  # preview, no POST
 1. **Target resolution**  -  Parse argument, classify (Jira-id, Jira-url, PR-url GitHub or Bitbucket, GitHub-issue-number, empty→cwd+branch). Resolve linked entities (Jira→PR, PR→Jira). Detect remote type.
 2. **Context source detection**  -  auto-pick best available: pipeline log (`$HOME/.claude/logs/multi-agent/<project>/<task-id>/agent-log.md` matching jiraId), PR diff (`gh pr diff` or Bitbucket `/diff?contextLines=5`), or manual `--message`.
 3. **Menu (multi-select)**  -  channel + content, previous selections pre-ticked from `prefs.global.reportChannels` + `prefs.global.reportContent`. Greyed-out rules per context availability.
-4. **Mode short-circuit**  -  `--channels X,Y` + `--content A,B` flags skip menu. Autopilot ALWAYS pauses at the menu (v5.7+ Phase 7 exception).
+4. **Mode short-circuit**  -  `--channels X,Y` + `--content A,B` flags skip menu. Autopilot ALWAYS pauses at the menu (v5.7+ Phase 5 exception).
 5. **Generator**  -  for each selected content source, produce a section body. Humanizer pass per channel separately.
 6. **Body preview + approval gate**  -  interactive runs render every selected channel's final body and ask Approve & post / Edit (loop) / Skip channels / Cancel BEFORE any external write. Skipped only by autopilot and `--dry-run`. What is posted is byte-identical to the approved preview.
 7. **Channel dispatch**  -  parallel adapter calls, never before the gate resolves: PR description (reviewer-preserving PUT on Bitbucket), Jira comment (wiki markup), Confluence page (storage format + parent page), Wiki (component adapter  -  Case A scope multi-select or Case B precondition menu).
@@ -69,7 +69,7 @@ Rendered in English (`promptLanguage` is locked to `en`).
 **Greyed-out rules:**
 - Wiki unselectable unless `state.taskType === "component"` AND `figmaConfig.wiki.enabled === true`.
 - Normal analiz + Test senaryoları unselectable if no pipeline log found.
-- Teknik analiz unselectable if no Phase 2 planning log AND no PR diff.
+- Teknik analiz unselectable if no Phase 1 planning log AND no PR diff.
 - Auto-diff unselectable if no PR found.
 - Manuel not always available.
 
@@ -192,9 +192,9 @@ forgotten, and that is how the selector above shipped.
 
 ### Technical Details               ← if "Teknik analiz" selected
 #### Changes
-{Per changed-file-group, what changed + why  -  from Phase 3 dev log}
+{Per changed-file-group, what changed + why  -  from Phase 2 dev log}
 #### Architecture
-{Structural decisions, pattern changes  -  from Phase 2 plan}
+{Structural decisions, pattern changes  -  from Phase 1 plan}
 #### Dependencies
 {New imports / frameworks / packages  -  from git diff --stat, or "None"}
 
@@ -290,16 +290,16 @@ Target length: < 80 lines (fits one screen). Auto-diff capped at 5 lines per sec
 | Jira token missing/expired | Token Save Flow inline; skip on user-skip |
 | Wiki preconditions not met | Case B menu per `refs/wiki-capture.md` |
 
-## Phase 7 delegation contract
+## Phase 5 delegation contract
 
-Phase 7 builds a state bundle and invokes this skill internally. Responsibilities:
+Phase 5 builds a state bundle and invokes this skill internally. Responsibilities:
 
 | Who | What |
 |---|---|
-| Phase 7 | Progress tracker (3 sub-steps), agent-log finalization, knowledge+memory capture, telemetry emission |
+| Phase 5 | Progress tracker (3 sub-steps), agent-log finalization, knowledge+memory capture, telemetry emission |
 | `multi-agent-channels` | All external delivery: PR description update, Jira comment, Confluence page, Wiki pages |
 
-**State bundle** passed from Phase 7:
+**State bundle** passed from Phase 5:
 ```json
 {
   "jiraId": "PROJ-12345",
@@ -313,7 +313,7 @@ Phase 7 builds a state bundle and invokes this skill internally. Responsibilitie
 }
 ```
 
-**Autopilot pause contract:** Phase 7 ALWAYS pauses at the channels menu  -  30-min timeout → session ends cleanly → resumable via `/multi-agent:resume`. Full contract in `refs/phases/modes.md` + `refs/phases/phase-7-report.md`.
+**Autopilot pause contract:** Phase 5 ALWAYS pauses at the channels menu  -  30-min timeout → session ends cleanly → resumable via `/multi-agent:resume`. Full contract in `refs/phases/modes.md` + `refs/phases/phase-5-report.md`.
 
 ## Cross-CLI parity
 
@@ -322,12 +322,12 @@ Prompts MUST be byte-identical between Claude and Copilot. `smoke-cross-cli-beha
 Progress emission on Copilot (no native TaskCreate UI):
 
 ```bash
-bash ~/.copilot/scripts/phase-tracker.sh sub 7 1 "Channels dispatch" in_progress
+bash ~/.copilot/scripts/phase-tracker.sh sub 5 1 "Channels dispatch" in_progress
 # ... adapter runs ...
-bash ~/.copilot/scripts/phase-tracker.sh sub 7 1 "Channels dispatch" completed
+bash ~/.copilot/scripts/phase-tracker.sh sub 5 1 "Channels dispatch" completed
 ```
 
-Same shape as Phase 7 sub-step tracking.
+Same shape as Phase 5 sub-step tracking.
 
 ## Examples
 

package/pipeline/skills/shared/core/multi-agent-diff-explain/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multi-agent-diff-explain
 language: en
-description: "Map Phase 4 triage findings to branch diff lines. Read-only post-hoc command, used after review to answer 'which finding lines up with which code change'. Use when a review finding has to be traced to the exact lines that caused it."
+description: "Map Phase 3 triage findings to branch diff lines. Read-only post-hoc command, used after review to answer 'which finding lines up with which code change'. Use when a review finding has to be traced to the exact lines that caused it."
 user-invocable: true
 argument-hint: "[#task-id | --triage <path> | --state <path>] [--branch <name>] [--base <name>]"
 ---
@@ -10,12 +10,12 @@ argument-hint: "[#task-id | --triage <path> | --state <path>] [--branch <name>]
 
 **Input**: $ARGUMENTS
 
-Maps the Phase 4 triage output (`accepted` / `deferred` / `rejected`) to the branch's `git diff` output. For each finding, the relevant file/line hunk is embedded in the output. **Produces no side effects**  -  it only runs `git diff` and emits markdown.
+Maps the Phase 3 triage output (`accepted` / `deferred` / `rejected`) to the branch's `git diff` output. For each finding, the relevant file/line hunk is embedded in the output. **Produces no side effects**  -  it only runs `git diff` and emits markdown.
 
 ## When to use it
 
 - After Phase 4 but before Phase 5/6: to answer "which finding lines up with which code?".
-- Phase 7 reporting content: "review summary with code context" for Wiki / Confluence.
+- Phase 5 reporting content: "review summary with code context" for Wiki / Confluence.
 - Post-hoc audit: review-vs-fix comparison for a closed PR.
 
 ## Steps
@@ -40,7 +40,7 @@ Maps the Phase 4 triage output (`accepted` / `deferred` / `rejected`) to the bra
 
 4. **Show the output to the user** and optionally add commentary:
    - Phase 3 fix coverage: were all blocking findings touched
-   - Deferred follow-up: are they all on the Phase 7 list
+   - Deferred follow-up: are they all on the Phase 5 list
 
 ## Output template
 
@@ -57,7 +57,7 @@ Maps the Phase 4 triage output (`accepted` / `deferred` / `rejected`) to the bra
 > Race condition: order total computed twice without lock
 **Fix:** Compute total once inside the existing transaction block
 \`\`\`diff
-@@ -98,5 +98,7 @@ ...
+ -98,5 +98,7  ...
 \`\`\`
 ```
 

package/pipeline/skills/shared/core/multi-agent-graph/SKILL.md

@@ -11,7 +11,7 @@ argument-hint: "[build | refresh | ask \"<question>\" | affected \"<symbol>\" |
 
 A code graph is a map of what this repo declares and what refers to what, built by
 regex over comment-stripped source. It exists so Phase 1 can narrow its Explore
-fan-out and Phase 7 can refresh `~/.claude/knowledge/<project>/` without an LLM
+fan-out and Phase 5 can refresh `~/.claude/knowledge/<project>/` without an LLM
 pass. It answers "where does this live" and "what depends on this". It does not
 answer "what calls this at runtime": call graphs and type resolution need a real
 parser, which would be an npm runtime dependency, and ADR-0004 forbids one.

package/pipeline/skills/shared/core/multi-agent-help/SKILL.md

@@ -59,30 +59,31 @@ How It Works (Phase 0  -  Interactive Flow):
 Pipeline (after Phase 0):
 
   Phase 0: Init      -> The 8 steps above
-  Phase 1: Analysis  -> Stack detection + codebase scan (Sonnet)
-  Phase 2: Planning  -> Task breakdown + architecture review + Plan Approval Gate
-  Phase 3: Dev       -> TDD: test -> code -> build (Sonnet) + build queue
-  Phase 4: Review    -> Deterministic gates + parallel AI review + Fable triage
+  Phase 1: Plan      -> Stack detection + codebase scan, then task breakdown,
+                        architecture review and the Plan Approval Gate (Opus)
+  Phase 2: Dev       -> TDD: test -> code -> build (Sonnet) + build queue, then the
+                        Verify exit gate: build, lint, tests, secrets
+                        (the build runs ONCE per run; its log carries into Review)
+  Phase 3: Review    -> Parallel AI review + Fable triage, then the optional user test
                         (Claude Code: Fable + Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
-  Phase 5: Test      -> Optional: switch to branch, test in Xcode
-  Phase 6: Commit    -> Commit -> push -> PR + issue body update (never auto-closes)
-  Phase 7: Report    -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
+  Phase 4: Commit    -> Commit -> push -> PR + issue body update (never auto-closes)
+  Phase 5: Report    -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
                         + internal capture (agent-log · knowledge · memory)
 
-  Autopilot always pauses at the Phase 7 channels menu (30-min timeout → session ends).
+  Autopilot always pauses at the Phase 5 channels menu (30-min timeout → session ends).
 
 ------------------------------------------------------------
 
 Modes:
 
   Depth is asked at Phase 0 Step 7.5, not passed as a flag:
-    Full   Analysis -> Plan -> Dev(Sonnet) -> Review -> Test -> Commit -> Report
-    Short  Dev(Opus, self-contained) -> Review -> Test -> Commit -> Report
+    Full   Plan -> Dev(Sonnet) -> Review -> Commit -> Report
+    Short  Dev(Opus, self-contained) -> Review -> Commit -> Report
   Recommended from taskType. Review is never skipped either way.
 
   --local              No worktree  -  works directly on local branch
   autopilot            Skip all confirmations, including the depth question, so
-                       it always runs Full (EXCEPT Phase 7 channels menu)
+                       it always runs Full (EXCEPT Phase 5 channels menu)
 
 Dedicated dash commands (Copilot):
   multi-agent-local, multi-agent-autopilot, multi-agent-local-autopilot
@@ -147,7 +148,7 @@ UI Testing (standalone):
   and lives at /multi-agent:store-ready. The old /multi-agent:test "store-ready"
   tag still works and hands off there.
 
-Manual Test (Phase 5 standalone  -  Xcode hint flow):
+Manual Test (Phase 3 user-test step, standalone  -  Xcode hint flow):
 
   /multi-agent:manual-test [#N]      Checkout task branch, print Xcode/SourceTree hints.
                                      (Renamed from :test in v5.7.4.)
@@ -232,30 +233,31 @@ Nasıl Çalışır (Phase 0  -  İnteraktif Akış):
 Pipeline (Phase 0'dan sonra):
 
   Phase 0: Init      -> Yukarıdaki 8 adım
-  Phase 1: Analysis  -> Stack tespiti + codebase taraması (Sonnet)
-  Phase 2: Planning  -> Task kırılımı + mimari inceleme + Plan Onay Kapısı
-  Phase 3: Dev       -> TDD: test -> kod -> build (Sonnet) + build queue
-  Phase 4: Review    -> Deterministik kapılar + paralel AI review + Fable triage
+  Phase 1: Plan      -> Stack tespiti + codebase taraması, ardından task kırılımı,
+                        mimari inceleme ve Plan Onay Kapısı (Opus)
+  Phase 2: Dev       -> TDD: test -> kod -> build (Sonnet) + build queue, sonra
+                        Verify çıkış kapısı: build, lint, test, sır taraması
+                        (build koşu başına BİR kez çalışır, log'u Review'a devreder)
+  Phase 3: Review    -> Paralel AI review + Fable triage, sonra opsiyonel kullanıcı testi
                         (Claude Code: Fable + Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
-  Phase 5: Test      -> Opsiyonel: branch'e geç, Xcode'da test
-  Phase 6: Commit    -> Commit -> push -> PR + issue body güncelleme (hiç auto-close yok)
-  Phase 7: Report    -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
+  Phase 4: Commit    -> Commit -> push -> PR + issue body güncelleme (hiç auto-close yok)
+  Phase 5: Report    -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
                         + internal capture (agent-log · knowledge · memory)
 
-  Autopilot Phase 7 channels menüsünde HER ZAMAN durur (30 dk timeout → session biter).
+  Autopilot Phase 5 channels menüsünde HER ZAMAN durur (30 dk timeout → session biter).
 
 ------------------------------------------------------------
 
 Modlar:
 
   Derinlik Faz 0 Adım 7.5'te sorulur, bayrakla geçilmez:
-    Tam    Analiz -> Plan -> Dev(Sonnet) -> Review -> Test -> Commit -> Report
-    Kısa   Dev(Opus, kendi kendine yeten) -> Review -> Test -> Commit -> Report
+    Tam    Plan -> Dev(Sonnet) -> Review -> Commit -> Report
+    Kısa   Dev(Opus, kendi kendine yeten) -> Review -> Commit -> Report
   taskType'a göre önerilir. Review iki durumda da atlanmaz.
 
   --local              Worktree yok  -  doğrudan local branch'te çalışır
   autopilot            Derinlik sorusu dahil tüm onayları atlar, bu yüzden her
-                       zaman Tam koşar (İSTİSNA: Phase 7 channels menüsü)
+                       zaman Tam koşar (İSTİSNA: Phase 5 channels menüsü)
 
 Dedicated dash komutlar (Copilot):
   multi-agent-local, multi-agent-autopilot, multi-agent-local-autopilot

package/pipeline/skills/shared/core/multi-agent-language/SKILL.md

@@ -14,7 +14,7 @@ Two-axis language preference for the pipeline:
 
 | Field | Controls | Stored at | Mutability |
 |---|---|---|---|
-| `promptLanguage` | Interactive prompts during a pipeline run (account picker, project picker, dev-context picker, base-branch picker, branch-name picker, maturity ack, channels picker, Phase 5 test prompt, Phase 6 local-checkout prompt) | `prefs.global.promptLanguage` | **Fixed to `en`**  -  never toggled by this skill |
+| `promptLanguage` | Interactive prompts during a pipeline run (account picker, project picker, dev-context picker, base-branch picker, branch-name picker, maturity ack, channels picker, Phase 3 test prompt, Phase 4 local-checkout prompt) | `prefs.global.promptLanguage` | **Fixed to `en`**  -  never toggled by this skill |
 | `outputLanguage` | Assistant's explanations, status updates, error messages, and pipeline-generated reports rendered to the user (NOT external payloads) | `prefs.global.outputLanguage` | Toggled by this skill |
 
 **Why promptLanguage is fixed:** it governs the picker's structural chrome only  -  the `AskUserQuestion` `header` chip, host error UI, and internal contract identifiers. The chip stays English because it is capped at 12 characters and most Turkish equivalents overflow it. Everything a user actually reads follows `outputLanguage`: the picker `question`, each option's `label`, and each option's `description`, per the canonical per-field matrix in `multi-agent-refs/rules.md`. A picker whose question or buttons are English on a Turkish run is a bug, not the contract. The host's own **Other** row is injected by the CLI and stays English on every run; nothing in the pipeline can localize it.
@@ -83,5 +83,5 @@ Render in the new outputLanguage:
 
 - `multi-agent-setup`  -  first-run language picker (asks only outputLanguage; promptLanguage seeded as `en`)
 - `prefs.schema.json`  -  `global.promptLanguage` (fixed `"en"`) and `global.outputLanguage`
-- Phase 5 / Phase 6  -  interactive prompts follow the per-field matrix: `question` + `label` + `description` in `outputLanguage`, `header` English
+- Phase 5 / Phase 4  -  interactive prompts follow the per-field matrix: `question` + `label` + `description` in `outputLanguage`, `header` English
 - `multi-agent-help`  -  reads outputLanguage for its own copy