diff --git a/builtins/en/facets/instructions/team-leader-implement.md b/builtins/en/facets/instructions/team-leader-implement.md
new file mode 100644
index 0000000..e598dc0
--- /dev/null
+++ b/builtins/en/facets/instructions/team-leader-implement.md
@@ -0,0 +1,27 @@
+Decompose the implementation task into subtasks by file ownership and execute them in parallel. Assign files exclusively to each part to prevent conflicts.
+
+**Important:** Reference the plan report: {report:plan.md}
+
+**Steps:**
+
+1. Identify files to create/modify
+   - Reference the plan report and test scope to list all files to change
+   - Review the actual codebase to fill in any missing information
+
+2. Group files by layer/module
+   - Create groups based on high cohesion (e.g., Domain layer / Infrastructure layer / API layer)
+   - If there are type or interface dependencies, keep both sides in the same group
+   - Never assign the same file to multiple parts
+
+3. Assign file ownership exclusively to each part
+   - Each part's instruction must clearly state:
+     - **Responsible files** (list of files to create/modify)
+     - **Reference-only files** (read-only, modification prohibited)
+     - **Implementation task** (what and how to implement)
+     - **Completion criteria** (implementation of responsible files is complete)
+   - If tests are already written, instruct parts to implement so existing tests pass
+   - Do not include build checks (all parts complete first, then build is verified together)
+
+**Constraints:**
+- Parts do not run tests (handled by subsequent movements)
+- Do not modify files outside your responsibility (causes conflicts)
diff --git a/builtins/en/facets/knowledge/takt.md b/builtins/en/facets/knowledge/takt.md
new file mode 100644
index 0000000..806a6f0
--- /dev/null
+++ b/builtins/en/facets/knowledge/takt.md
@@ -0,0 +1,151 @@
+# TAKT Architecture Knowledge
+
+## Core Structure
+
+PieceEngine is a state machine. It manages movement transitions via EventEmitter.
+
+```
+CLI → PieceEngine → Runner (4 types) → RuleEvaluator → next movement
+```
+
+| Runner | Purpose | When to Use |
+|--------|---------|-------------|
+| MovementExecutor | Standard 3-phase execution | Default |
+| ParallelRunner | Concurrent sub-movements | parallel block |
+| ArpeggioRunner | Data-driven batch processing | arpeggio block |
+| TeamLeaderRunner | Task decomposition → parallel sub-agents | team_leader block |
+
+Runners are mutually exclusive. Do not specify multiple runner types on a single movement.
+
+### 3-Phase Execution Model
+
+Normal movements execute in up to 3 phases. Sessions persist across phases.
+
+| Phase | Purpose | Tools | Condition |
+|-------|---------|-------|-----------|
+| Phase 1 | Main work | Movement's allowed_tools | Always |
+| Phase 2 | Report output | Write only | When output_contracts defined |
+| Phase 3 | Status judgment | None (judgment only) | When tag-based rules exist |
+
+## Rule Evaluation
+
+RuleEvaluator determines the next movement via 5-stage fallback. Earlier match takes priority.
+
+| Priority | Method | Target |
+|----------|--------|--------|
+| 1 | aggregate | parallel parent (all/any) |
+| 2 | Phase 3 tag | `[STEP:N]` output |
+| 3 | Phase 1 tag | `[STEP:N]` output (fallback) |
+| 4 | ai() judge | ai("condition") rules |
+| 5 | AI fallback | AI evaluates all conditions |
+
+When multiple tags appear in output, the **last match** wins.
+
+### Condition Syntax
+
+| Syntax | Parsing | Regex |
+|--------|---------|-------|
+| `ai("...")` | AI condition evaluation | `AI_CONDITION_REGEX` |
+| `all("...")` / `any("...")` | Aggregate condition | `AGGREGATE_CONDITION_REGEX` |
+| Plain string | Tag or AI fallback | — |
+
+Adding new special syntax requires updating both pieceParser.ts regex and RuleEvaluator.
+
+## Provider Integration
+
+Abstracted through the Provider interface. SDK-specific details are encapsulated within each provider.
+
+```
+Provider.setup(AgentSetup) → ProviderAgent
+ProviderAgent.call(prompt, options) → AgentResponse
+```
+
+| Criteria | Judgment |
+|----------|----------|
+| SDK-specific error handling leaking outside Provider | REJECT |
+| Errors not propagated to AgentResponse.error | REJECT |
+| Session key collision between providers | REJECT |
+| Session key format `{persona}:{provider}` | OK |
+
+### Model Resolution
+
+Models resolve through 5-level priority. Higher takes precedence.
+
+1. persona_providers model specification
+2. Movement model field
+3. CLI `--model` override
+4. config.yaml (when resolved provider matches)
+5. Provider default
+
+## Facet Assembly
+
+The faceted-prompting module is independent from TAKT core.
+
+```
+compose(facets, options) → ComposedPrompt { systemPrompt, userMessage }
+```
+
+| Criteria | Judgment |
+|----------|----------|
+| Import from faceted-prompting to TAKT core | REJECT |
+| TAKT core depending on faceted-prompting | OK |
+| Facet path resolution logic outside faceted-prompting | Warning |
+
+### 3-Layer Facet Resolution Priority
+
+Project `.takt/` → User `~/.takt/` → Builtin `builtins/{lang}/`
+
+Same-named facets are overridden by higher-priority layers. Customize builtins by overriding in upper layers.
+
+## Testing Patterns
+
+Uses vitest. Test file naming conventions distinguish test types.
+
+| Prefix | Type | Content |
+|--------|------|---------|
+| None | Unit test | Individual function/class verification |
+| `it-` | Integration test | Piece execution simulation |
+| `engine-` | Engine test | PieceEngine scenario verification |
+
+### Mock Provider
+
+`--provider mock` returns deterministic responses. Scenario queues compose multi-turn tests.
+
+```typescript
+// NG - Calling real API in tests
+const response = await callClaude(prompt)
+
+// OK - Set up scenario with mock provider
+setMockScenario([
+  { persona: 'coder', status: 'done', content: '[STEP:1]\nDone.' },
+  { persona: 'reviewer', status: 'done', content: '[STEP:1]\napproved' },
+])
+```
+
+### Test Isolation
+
+| Criteria | Judgment |
+|----------|----------|
+| Tests sharing global state | REJECT |
+| Environment variables not cleared in test setup | Warning |
+| E2E tests assuming real API | Isolate via `provider` config |
+
+## Error Propagation
+
+Provider errors propagate through: `AgentResponse.error` → session log → console output.
+
+| Criteria | Judgment |
+|----------|----------|
+| SDK error results in empty `blocked` status | REJECT |
+| Error details not recorded in session log | REJECT |
+| No ABORT transition defined for error cases | Warning |
+
+## Session Management
+
+Agent sessions are stored per-cwd. Session resume is skipped during worktree/clone execution.
+
+| Criteria | Judgment |
+|----------|----------|
+| Session resuming when `cwd !== projectCwd` | REJECT (cross-project contamination) |
+| Session key missing provider identifier | REJECT (cross-provider contamination) |
+| Session broken between phases | REJECT (context loss) |
diff --git a/builtins/en/piece-categories.yaml b/builtins/en/piece-categories.yaml
index d2fb133..7f72c39 100644
--- a/builtins/en/piece-categories.yaml
+++ b/builtins/en/piece-categories.yaml
@@ -47,6 +47,10 @@ piece_categories:
   ✅ Test First:
     pieces:
       - default-test-first-mini
+  🎵 TAKT Development:
+    pieces:
+      - takt-default
+      - takt-default-team-leader
   Others:
     pieces:
       - research
diff --git a/builtins/en/pieces/takt-default-team-leader.yaml b/builtins/en/pieces/takt-default-team-leader.yaml
new file mode 100644
index 0000000..e549e4f
--- /dev/null
+++ b/builtins/en/pieces/takt-default-team-leader.yaml
@@ -0,0 +1,378 @@
+name: takt-default-team-leader
+description: TAKT development piece with team leader (plan → write tests → team-leader implement → AI review → 5-parallel review → fix → supervise → complete)
+piece_config:
+  provider_options:
+    codex:
+      network_access: true
+    opencode:
+      network_access: true
+max_movements: 30
+initial_movement: plan
+loop_monitors:
+  - cycle:
+      - ai_review
+      - ai_fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: |
+        The ai_review ↔ ai_fix loop has repeated {cycle_count} times.
+
+        Review the reports from each cycle and determine whether this loop
+        is healthy (making progress) or unproductive (repeating the same issues).
+
+        **Reports to reference:**
+        - AI Review results: {report:ai-review.md}
+
+        **Judgment criteria:**
+        - Are new issues being found/fixed in each cycle?
+        - Are the same findings being repeated?
+        - Are fixes actually being applied?
+      rules:
+        - condition: Healthy (making progress)
+          next: ai_review
+        - condition: Unproductive (no improvement)
+          next: reviewers
+movements:
+  - name: plan
+    edit: false
+    persona: planner
+    knowledge: architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Bash
+      - WebSearch
+      - WebFetch
+    rules:
+      - condition: Requirements are clear and implementable
+        next: write_tests
+      - condition: User is asking a question (not an implementation task)
+        next: COMPLETE
+      - condition: Requirements unclear, insufficient info
+        next: ABORT
+        appendix: |
+          Clarifications needed:
+          - {Question 1}
+          - {Question 2}
+    instruction: plan
+    output_contracts:
+      report:
+        - name: plan.md
+          format: plan
+  - name: write_tests
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    instruction: write-tests-first
+    rules:
+      - condition: Tests written successfully
+        next: implement
+      - condition: Cannot proceed because the test target is not implemented yet, so skip test writing
+        next: implement
+      - condition: Cannot proceed with test writing
+        next: ABORT
+      - condition: User input needed for clarification
+        next: write_tests
+        requires_user_input: true
+        interactive_only: true
+    output_contracts:
+      report:
+        - name: test-scope.md
+          format: coder-scope
+        - name: test-decisions.md
+          format: coder-decisions
+  - name: implement
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    session: refresh
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    team_leader:
+      max_parts: 2
+      part_persona: coder
+      part_edit: true
+      part_permission_mode: edit
+      part_allowed_tools:
+        - Read
+        - Glob
+        - Grep
+        - Edit
+        - Write
+        - Bash
+        - WebSearch
+        - WebFetch
+    instruction: team-leader-implement
+    rules:
+      - condition: Implementation complete
+        next: ai_review
+      - condition: No implementation (report only)
+        next: ai_review
+      - condition: Cannot proceed, insufficient info
+        next: ai_review
+      - condition: User input required
+        next: implement
+        requires_user_input: true
+        interactive_only: true
+    output_contracts:
+      report:
+        - name: coder-scope.md
+          format: coder-scope
+        - name: coder-decisions.md
+          format: coder-decisions
+  - name: ai_review
+    edit: false
+    persona: ai-antipattern-reviewer
+    policy:
+      - review
+      - ai-antipattern
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - WebSearch
+      - WebFetch
+    rules:
+      - condition: No AI-specific issues
+        next: reviewers
+      - condition: AI-specific issues found
+        next: ai_fix
+    instruction: ai-review
+    output_contracts:
+      report:
+        - name: ai-review.md
+          format: ai-review
+  - name: ai_fix
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    session: refresh
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    pass_previous_response: false
+    rules:
+      - condition: AI issues fixed
+        next: ai_review
+      - condition: No fix needed (verified target files/spec)
+        next: ai_no_fix
+      - condition: Cannot proceed, insufficient info
+        next: ai_no_fix
+    instruction: ai-fix
+  - name: ai_no_fix
+    edit: false
+    persona: architecture-reviewer
+    policy: review
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+    rules:
+      - condition: ai_review's findings are valid (fix required)
+        next: ai_fix
+      - condition: ai_fix's judgment is valid (no fix needed)
+        next: reviewers
+    instruction: arbitrate
+  - name: reviewers
+    parallel:
+      - name: arch-review
+        edit: false
+        persona: architecture-reviewer
+        policy: review
+        knowledge:
+          - architecture
+          - takt
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-arch
+        output_contracts:
+          report:
+            - name: architect-review.md
+              format: architecture-review
+      - name: security-review
+        edit: false
+        persona: security-reviewer
+        policy: review
+        knowledge: security
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-security
+        output_contracts:
+          report:
+            - name: security-review.md
+              format: security-review
+      - name: qa-review
+        edit: false
+        persona: qa-reviewer
+        policy:
+          - review
+          - qa
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-qa
+        output_contracts:
+          report:
+            - name: qa-review.md
+              format: qa-review
+      - name: testing-review
+        edit: false
+        persona: testing-reviewer
+        policy:
+          - review
+          - testing
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-test
+        output_contracts:
+          report:
+            - name: testing-review.md
+              format: testing-review
+      - name: requirements-review
+        edit: false
+        persona: requirements-reviewer
+        policy: review
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-requirements
+        output_contracts:
+          report:
+            - name: requirements-review.md
+              format: requirements-review
+    rules:
+      - condition: all("approved")
+        next: supervise
+      - condition: any("needs_fix")
+        next: fix
+  - name: fix
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    pass_previous_response: false
+    rules:
+      - condition: Fix complete
+        next: reviewers
+      - condition: Cannot proceed, insufficient info
+        next: plan
+    instruction: fix
+  - name: supervise
+    edit: false
+    persona: supervisor
+    policy: review
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Bash
+      - WebSearch
+      - WebFetch
+    pass_previous_response: false
+    rules:
+      - condition: All checks passed
+        next: COMPLETE
+      - condition: Requirements unmet, tests failing, build errors
+        next: plan
+    instruction: supervise
+    output_contracts:
+      report:
+        - name: supervisor-validation.md
+          format: supervisor-validation
+        - name: summary.md
+          format: summary
+          use_judge: false
diff --git a/builtins/en/pieces/takt-default.yaml b/builtins/en/pieces/takt-default.yaml
new file mode 100644
index 0000000..65d8ac8
--- /dev/null
+++ b/builtins/en/pieces/takt-default.yaml
@@ -0,0 +1,364 @@
+name: takt-default
+description: TAKT development piece (plan → write tests → implement → AI review → 5-parallel review → fix → supervise → complete)
+piece_config:
+  provider_options:
+    codex:
+      network_access: true
+    opencode:
+      network_access: true
+max_movements: 30
+initial_movement: plan
+loop_monitors:
+  - cycle:
+      - ai_review
+      - ai_fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: |
+        The ai_review ↔ ai_fix loop has repeated {cycle_count} times.
+
+        Review the reports from each cycle and determine whether this loop
+        is healthy (making progress) or unproductive (repeating the same issues).
+
+        **Reports to reference:**
+        - AI Review results: {report:ai-review.md}
+
+        **Judgment criteria:**
+        - Are new issues being found/fixed in each cycle?
+        - Are the same findings being repeated?
+        - Are fixes actually being applied?
+      rules:
+        - condition: Healthy (making progress)
+          next: ai_review
+        - condition: Unproductive (no improvement)
+          next: reviewers
+movements:
+  - name: plan
+    edit: false
+    persona: planner
+    knowledge: architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Bash
+      - WebSearch
+      - WebFetch
+    rules:
+      - condition: Requirements are clear and implementable
+        next: write_tests
+      - condition: User is asking a question (not an implementation task)
+        next: COMPLETE
+      - condition: Requirements unclear, insufficient info
+        next: ABORT
+        appendix: |
+          Clarifications needed:
+          - {Question 1}
+          - {Question 2}
+    instruction: plan
+    output_contracts:
+      report:
+        - name: plan.md
+          format: plan
+  - name: write_tests
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    instruction: write-tests-first
+    rules:
+      - condition: Tests written successfully
+        next: implement
+      - condition: Cannot proceed because the test target is not implemented yet, so skip test writing
+        next: implement
+      - condition: Cannot proceed with test writing
+        next: ABORT
+      - condition: User input needed for clarification
+        next: write_tests
+        requires_user_input: true
+        interactive_only: true
+    output_contracts:
+      report:
+        - name: test-scope.md
+          format: coder-scope
+        - name: test-decisions.md
+          format: coder-decisions
+  - name: implement
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    session: refresh
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    rules:
+      - condition: Implementation complete
+        next: ai_review
+      - condition: No implementation (report only)
+        next: ai_review
+      - condition: Cannot proceed, insufficient info
+        next: ai_review
+      - condition: User input required
+        next: implement
+        requires_user_input: true
+        interactive_only: true
+    instruction: implement-after-tests
+    output_contracts:
+      report:
+        - name: coder-scope.md
+          format: coder-scope
+        - name: coder-decisions.md
+          format: coder-decisions
+  - name: ai_review
+    edit: false
+    persona: ai-antipattern-reviewer
+    policy:
+      - review
+      - ai-antipattern
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - WebSearch
+      - WebFetch
+    rules:
+      - condition: No AI-specific issues
+        next: reviewers
+      - condition: AI-specific issues found
+        next: ai_fix
+    instruction: ai-review
+    output_contracts:
+      report:
+        - name: ai-review.md
+          format: ai-review
+  - name: ai_fix
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    session: refresh
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    pass_previous_response: false
+    rules:
+      - condition: AI issues fixed
+        next: ai_review
+      - condition: No fix needed (verified target files/spec)
+        next: ai_no_fix
+      - condition: Cannot proceed, insufficient info
+        next: ai_no_fix
+    instruction: ai-fix
+  - name: ai_no_fix
+    edit: false
+    persona: architecture-reviewer
+    policy: review
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+    rules:
+      - condition: ai_review's findings are valid (fix required)
+        next: ai_fix
+      - condition: ai_fix's judgment is valid (no fix needed)
+        next: reviewers
+    instruction: arbitrate
+  - name: reviewers
+    parallel:
+      - name: arch-review
+        edit: false
+        persona: architecture-reviewer
+        policy: review
+        knowledge:
+          - architecture
+          - takt
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-arch
+        output_contracts:
+          report:
+            - name: architect-review.md
+              format: architecture-review
+      - name: security-review
+        edit: false
+        persona: security-reviewer
+        policy: review
+        knowledge: security
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-security
+        output_contracts:
+          report:
+            - name: security-review.md
+              format: security-review
+      - name: qa-review
+        edit: false
+        persona: qa-reviewer
+        policy:
+          - review
+          - qa
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-qa
+        output_contracts:
+          report:
+            - name: qa-review.md
+              format: qa-review
+      - name: testing-review
+        edit: false
+        persona: testing-reviewer
+        policy:
+          - review
+          - testing
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-test
+        output_contracts:
+          report:
+            - name: testing-review.md
+              format: testing-review
+      - name: requirements-review
+        edit: false
+        persona: requirements-reviewer
+        policy: review
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-requirements
+        output_contracts:
+          report:
+            - name: requirements-review.md
+              format: requirements-review
+    rules:
+      - condition: all("approved")
+        next: supervise
+      - condition: any("needs_fix")
+        next: fix
+  - name: fix
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    pass_previous_response: false
+    rules:
+      - condition: Fix complete
+        next: reviewers
+      - condition: Cannot proceed, insufficient info
+        next: plan
+    instruction: fix
+  - name: supervise
+    edit: false
+    persona: supervisor
+    policy: review
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Bash
+      - WebSearch
+      - WebFetch
+    pass_previous_response: false
+    rules:
+      - condition: All checks passed
+        next: COMPLETE
+      - condition: Requirements unmet, tests failing, build errors
+        next: plan
+    instruction: supervise
+    output_contracts:
+      report:
+        - name: supervisor-validation.md
+          format: supervisor-validation
+        - name: summary.md
+          format: summary
+          use_judge: false
diff --git a/builtins/ja/facets/instructions/team-leader-implement.md b/builtins/ja/facets/instructions/team-leader-implement.md
new file mode 100644
index 0000000..80351c0
--- /dev/null
+++ b/builtins/ja/facets/instructions/team-leader-implement.md
@@ -0,0 +1,27 @@
+実装タスクをファイル担当単位でサブタスクに分解し、並列実行してください。各パートが担当するファイルが重複しないよう排他的に割り当てます。
+
+**重要:** 計画レポートを参照してください: {report:plan.md}
+
+**やること:**
+
+1. 変更対象ファイルを特定する
+   - 計画レポートとテストスコープを参照して変更・作成するファイルを洗い出す
+   - 実際のコードベースを確認して不明点を補完する
+
+2. ファイルをレイヤー/モジュール単位でグループ化する
+   - 凝集度の高い単位でグループを作る（例: ドメイン層 / インフラ層 / API層）
+   - 型・インターフェースの依存がある場合は、依存元と依存先を同じグループにまとめる
+   - 1つのファイルを複数のパートに割り当てない
+
+3. 各パートに排他的なファイル担当を割り当てる
+   - 各パートの instruction に以下を必ず明記する：
+     - **担当ファイル**（作成・変更する対象ファイルのパス一覧）
+     - **参照専用ファイル**（変更禁止、読み取りのみ可）
+     - **実装内容**（何をどのように実装するか）
+     - **完了基準**（担当ファイルの実装が完了したこと）
+   - テスト済みの場合は「既存テストがパスするよう実装する」と明記する
+   - ビルドチェックは指示しない（他パートのファイルが揃ってから全体でまとめて確認するため）
+
+**制約:**
+- 各パートはテスト実行を行わない（後続ムーブメントで実施する）
+- 担当外のファイルを変更しない（コンフリクトの原因になる）
diff --git a/builtins/ja/facets/knowledge/takt.md b/builtins/ja/facets/knowledge/takt.md
new file mode 100644
index 0000000..a84ce4a
--- /dev/null
+++ b/builtins/ja/facets/knowledge/takt.md
@@ -0,0 +1,151 @@
+# TAKT アーキテクチャ知識
+
+## コア構造
+
+PieceEngine は状態機械。movement 間の遷移を EventEmitter ベースで管理する。
+
+```
+CLI → PieceEngine → Runner（4種） → RuleEvaluator → 次の movement
+```
+
+| Runner | 用途 | 使い分け |
+|--------|------|---------|
+| MovementExecutor | 通常の3フェーズ実行 | デフォルト |
+| ParallelRunner | 並列サブムーブメント | parallel ブロック |
+| ArpeggioRunner | データ駆動バッチ処理 | arpeggio ブロック |
+| TeamLeaderRunner | タスク分解 → サブエージェント並列 | team_leader ブロック |
+
+各 Runner は排他。1つの movement に複数の Runner タイプを指定しない。
+
+### 3フェーズ実行モデル
+
+通常 movement は最大3フェーズで実行される。セッションはフェーズ間で維持される。
+
+| フェーズ | 目的 | ツール | 条件 |
+|---------|------|--------|------|
+| Phase 1 | メイン作業 | movement の allowed_tools | 常に |
+| Phase 2 | レポート出力 | Write のみ | output_contracts 定義時 |
+| Phase 3 | ステータス判定 | なし（判定のみ） | タグベースルール時 |
+
+## ルール評価
+
+RuleEvaluator は5段階フォールバックで遷移先を決定する。先にマッチした方法が優先される。
+
+| 優先度 | 方法 | 対象 |
+|--------|------|------|
+| 1 | aggregate | parallel 親（all/any） |
+| 2 | Phase 3 タグ | `[STEP:N]` 出力 |
+| 3 | Phase 1 タグ | `[STEP:N]` 出力（フォールバック） |
+| 4 | ai() judge | ai("条件") ルール |
+| 5 | AI fallback | 全条件を AI が判定 |
+
+タグが複数出現した場合は**最後のマッチ**が採用される。
+
+### Condition の記法
+
+| 記法 | パース | 正規表現 |
+|------|--------|---------|
+| `ai("...")` | AI 条件評価 | `AI_CONDITION_REGEX` |
+| `all("...")` / `any("...")` | 集約条件 | `AGGREGATE_CONDITION_REGEX` |
+| 文字列 | タグまたは AI フォールバック | — |
+
+新しい特殊構文を追加する場合は pieceParser.ts の正規表現と RuleEvaluator の両方を更新する。
+
+## プロバイダー統合
+
+Provider インターフェースで抽象化。具体的な SDK の差異は各プロバイダー内に閉じ込める。
+
+```
+Provider.setup(AgentSetup) → ProviderAgent
+ProviderAgent.call(prompt, options) → AgentResponse
+```
+
+| 基準 | 判定 |
+|------|------|
+| SDK 固有のエラーハンドリングが Provider 外に漏れている | REJECT |
+| AgentResponse.error にエラーを伝播していない | REJECT |
+| プロバイダー間でセッションキーが衝突する | REJECT |
+| セッションキー形式 `{persona}:{provider}` | OK |
+
+### モデル解決
+
+5段階の優先順位でモデルを解決する。上位が優先。
+
+1. persona_providers のモデル指定
+2. movement の model フィールド
+3. CLI `--model` オーバーライド
+4. config.yaml（プロバイダー一致時）
+5. プロバイダーデフォルト
+
+## ファセット組み立て
+
+faceted-prompting モジュールは TAKT 本体に依存しない独立モジュール。
+
+```
+compose(facets, options) → ComposedPrompt { systemPrompt, userMessage }
+```
+
+| 基準 | 判定 |
+|------|------|
+| faceted-prompting から TAKT コアへの import | REJECT |
+| TAKT コアから faceted-prompting への依存 | OK |
+| ファセットパス解決のロジックが faceted-prompting 外にある | 警告 |
+
+### ファセット解決の3層優先順位
+
+プロジェクト `.takt/` → ユーザー `~/.takt/` → ビルトイン `builtins/{lang}/`
+
+同名ファセットは上位が優先。ビルトインのカスタマイズは上位層でオーバーライドする。
+
+## テストパターン
+
+vitest を使用。テストファイルの命名規約で種別を区別する。
+
+| プレフィックス | 種別 | 内容 |
+|--------------|------|------|
+| なし | ユニットテスト | 個別関数・クラスの検証 |
+| `it-` | 統合テスト | ピース実行のシミュレーション |
+| `engine-` | エンジンテスト | PieceEngine シナリオ検証 |
+
+### Mock プロバイダー
+
+`--provider mock` でテスト用の決定論的レスポンスを返す。シナリオキューで複数ターンのテストを構成する。
+
+```typescript
+// NG - テストでリアル API を呼ぶ
+const response = await callClaude(prompt)
+
+// OK - Mock プロバイダーでシナリオを設定
+setMockScenario([
+  { persona: 'coder', status: 'done', content: '[STEP:1]\nDone.' },
+  { persona: 'reviewer', status: 'done', content: '[STEP:1]\napproved' },
+])
+```
+
+### テストの分離
+
+| 基準 | 判定 |
+|------|------|
+| テスト間でグローバル状態を共有 | REJECT |
+| 環境変数をテストセットアップでクリアしていない | 警告 |
+| E2E テストで実 API を前提としている | `provider` 指定の config で分離 |
+
+## エラー伝播
+
+プロバイダーエラーは `AgentResponse.error` → セッションログ → コンソール出力の経路で伝播する。
+
+| 基準 | 判定 |
+|------|------|
+| SDK エラーが空の `blocked` ステータスになる | REJECT |
+| エラー詳細がセッションログに記録されない | REJECT |
+| エラー時に ABORT 遷移が定義されていない | 警告 |
+
+## セッション管理
+
+エージェントセッションは cwd ごとに保存される。worktree/clone 実行時はセッション再開をスキップする。
+
+| 基準 | 判定 |
+|------|------|
+| `cwd !== projectCwd` でセッション再開している | REJECT |
+| セッションキーにプロバイダーが含まれない | REJECT（クロスプロバイダー汚染） |
+| Phase 間でセッションが切れている | REJECT（コンテキスト喪失） |
diff --git a/builtins/ja/piece-categories.yaml b/builtins/ja/piece-categories.yaml
index 94264f1..45cdd99 100644
--- a/builtins/ja/piece-categories.yaml
+++ b/builtins/ja/piece-categories.yaml
@@ -47,6 +47,10 @@ piece_categories:
   ✅ テストファースト:
     pieces:
       - default-test-first-mini
+  🎵 TAKT開発:
+    pieces:
+      - takt-default
+      - takt-default-team-leader
   その他:
     pieces:
       - research
diff --git a/builtins/ja/pieces/takt-default-team-leader.yaml b/builtins/ja/pieces/takt-default-team-leader.yaml
new file mode 100644
index 0000000..a77d2bd
--- /dev/null
+++ b/builtins/ja/pieces/takt-default-team-leader.yaml
@@ -0,0 +1,378 @@
+name: takt-default-team-leader
+description: TAKT開発ピース（チームリーダー版）（計画 → テスト作成 → チームリーダー実装 → AIレビュー → 5並列レビュー → 修正 → 監督 → 完了）
+piece_config:
+  provider_options:
+    codex:
+      network_access: true
+    opencode:
+      network_access: true
+max_movements: 30
+initial_movement: plan
+loop_monitors:
+  - cycle:
+      - ai_review
+      - ai_fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: |
+        ai_review と ai_fix のループが {cycle_count} 回繰り返されました。
+
+        各サイクルのレポートを確認し、このループが健全（進捗がある）か、
+        非生産的（同じ問題を繰り返している）かを判断してください。
+
+        **参照するレポート:**
+        - AIレビュー結果: {report:ai-review.md}
+
+        **判断基準:**
+        - 各サイクルで新しい問題が発見・修正されているか
+        - 同じ指摘が繰り返されていないか
+        - 修正が実際に反映されているか
+      rules:
+        - condition: 健全（進捗あり）
+          next: ai_review
+        - condition: 非生産的（改善なし）
+          next: reviewers
+movements:
+  - name: plan
+    edit: false
+    persona: planner
+    knowledge: architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Bash
+      - WebSearch
+      - WebFetch
+    rules:
+      - condition: 要件が明確で実装可能
+        next: write_tests
+      - condition: ユーザーが質問をしている（実装タスクではない）
+        next: COMPLETE
+      - condition: 要件が不明確、情報不足
+        next: ABORT
+        appendix: |
+          確認事項:
+          - {質問1}
+          - {質問2}
+    instruction: plan
+    output_contracts:
+      report:
+        - name: plan.md
+          format: plan
+  - name: write_tests
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    instruction: write-tests-first
+    rules:
+      - condition: テスト作成が完了した
+        next: implement
+      - condition: テスト対象が未実装のためテスト作成をスキップする
+        next: implement
+      - condition: テスト作成を進行できない
+        next: ABORT
+      - condition: ユーザーへの確認事項があるためユーザー入力が必要
+        next: write_tests
+        requires_user_input: true
+        interactive_only: true
+    output_contracts:
+      report:
+        - name: test-scope.md
+          format: coder-scope
+        - name: test-decisions.md
+          format: coder-decisions
+  - name: implement
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    session: refresh
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    team_leader:
+      max_parts: 2
+      part_persona: coder
+      part_edit: true
+      part_permission_mode: edit
+      part_allowed_tools:
+        - Read
+        - Glob
+        - Grep
+        - Edit
+        - Write
+        - Bash
+        - WebSearch
+        - WebFetch
+    instruction: team-leader-implement
+    rules:
+      - condition: 実装完了
+        next: ai_review
+      - condition: 実装未着手（レポートのみ）
+        next: ai_review
+      - condition: 判断できない、情報不足
+        next: ai_review
+      - condition: ユーザー入力が必要
+        next: implement
+        requires_user_input: true
+        interactive_only: true
+    output_contracts:
+      report:
+        - name: coder-scope.md
+          format: coder-scope
+        - name: coder-decisions.md
+          format: coder-decisions
+  - name: ai_review
+    edit: false
+    persona: ai-antipattern-reviewer
+    policy:
+      - review
+      - ai-antipattern
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - WebSearch
+      - WebFetch
+    rules:
+      - condition: AI特有の問題なし
+        next: reviewers
+      - condition: AI特有の問題あり
+        next: ai_fix
+    instruction: ai-review
+    output_contracts:
+      report:
+        - name: ai-review.md
+          format: ai-review
+  - name: ai_fix
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    session: refresh
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    pass_previous_response: false
+    rules:
+      - condition: AI問題の修正完了
+        next: ai_review
+      - condition: 修正不要（指摘対象ファイル/仕様の確認済み）
+        next: ai_no_fix
+      - condition: 判断できない、情報不足
+        next: ai_no_fix
+    instruction: ai-fix
+  - name: ai_no_fix
+    edit: false
+    persona: architecture-reviewer
+    policy: review
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+    rules:
+      - condition: ai_reviewの指摘が妥当（修正すべき）
+        next: ai_fix
+      - condition: ai_fixの判断が妥当（修正不要）
+        next: reviewers
+    instruction: arbitrate
+  - name: reviewers
+    parallel:
+      - name: arch-review
+        edit: false
+        persona: architecture-reviewer
+        policy: review
+        knowledge:
+          - architecture
+          - takt
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-arch
+        output_contracts:
+          report:
+            - name: architect-review.md
+              format: architecture-review
+      - name: security-review
+        edit: false
+        persona: security-reviewer
+        policy: review
+        knowledge: security
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-security
+        output_contracts:
+          report:
+            - name: security-review.md
+              format: security-review
+      - name: qa-review
+        edit: false
+        persona: qa-reviewer
+        policy:
+          - review
+          - qa
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-qa
+        output_contracts:
+          report:
+            - name: qa-review.md
+              format: qa-review
+      - name: testing-review
+        edit: false
+        persona: testing-reviewer
+        policy:
+          - review
+          - testing
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-test
+        output_contracts:
+          report:
+            - name: testing-review.md
+              format: testing-review
+      - name: requirements-review
+        edit: false
+        persona: requirements-reviewer
+        policy: review
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-requirements
+        output_contracts:
+          report:
+            - name: requirements-review.md
+              format: requirements-review
+    rules:
+      - condition: all("approved")
+        next: supervise
+      - condition: any("needs_fix")
+        next: fix
+  - name: fix
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    pass_previous_response: false
+    rules:
+      - condition: 修正完了
+        next: reviewers
+      - condition: 判断できない、情報不足
+        next: plan
+    instruction: fix
+  - name: supervise
+    edit: false
+    persona: supervisor
+    policy: review
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Bash
+      - WebSearch
+      - WebFetch
+    pass_previous_response: false
+    rules:
+      - condition: すべて問題なし
+        next: COMPLETE
+      - condition: 要求未達成、テスト失敗、ビルドエラー
+        next: plan
+    instruction: supervise
+    output_contracts:
+      report:
+        - name: supervisor-validation.md
+          format: supervisor-validation
+        - name: summary.md
+          format: summary
+          use_judge: false
diff --git a/builtins/ja/pieces/takt-default.yaml b/builtins/ja/pieces/takt-default.yaml
new file mode 100644
index 0000000..0e7efe8
--- /dev/null
+++ b/builtins/ja/pieces/takt-default.yaml
@@ -0,0 +1,364 @@
+name: takt-default
+description: TAKT開発ピース（計画 → テスト作成 → 実装 → AIレビュー → 5並列レビュー → 修正 → 監督 → 完了）
+piece_config:
+  provider_options:
+    codex:
+      network_access: true
+    opencode:
+      network_access: true
+max_movements: 30
+initial_movement: plan
+loop_monitors:
+  - cycle:
+      - ai_review
+      - ai_fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: |
+        ai_review と ai_fix のループが {cycle_count} 回繰り返されました。
+
+        各サイクルのレポートを確認し、このループが健全（進捗がある）か、
+        非生産的（同じ問題を繰り返している）かを判断してください。
+
+        **参照するレポート:**
+        - AIレビュー結果: {report:ai-review.md}
+
+        **判断基準:**
+        - 各サイクルで新しい問題が発見・修正されているか
+        - 同じ指摘が繰り返されていないか
+        - 修正が実際に反映されているか
+      rules:
+        - condition: 健全（進捗あり）
+          next: ai_review
+        - condition: 非生産的（改善なし）
+          next: reviewers
+movements:
+  - name: plan
+    edit: false
+    persona: planner
+    knowledge: architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Bash
+      - WebSearch
+      - WebFetch
+    rules:
+      - condition: 要件が明確で実装可能
+        next: write_tests
+      - condition: ユーザーが質問をしている（実装タスクではない）
+        next: COMPLETE
+      - condition: 要件が不明確、情報不足
+        next: ABORT
+        appendix: |
+          確認事項:
+          - {質問1}
+          - {質問2}
+    instruction: plan
+    output_contracts:
+      report:
+        - name: plan.md
+          format: plan
+  - name: write_tests
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    instruction: write-tests-first
+    rules:
+      - condition: テスト作成が完了した
+        next: implement
+      - condition: テスト対象が未実装のためテスト作成をスキップする
+        next: implement
+      - condition: テスト作成を進行できない
+        next: ABORT
+      - condition: ユーザーへの確認事項があるためユーザー入力が必要
+        next: write_tests
+        requires_user_input: true
+        interactive_only: true
+    output_contracts:
+      report:
+        - name: test-scope.md
+          format: coder-scope
+        - name: test-decisions.md
+          format: coder-decisions
+  - name: implement
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    session: refresh
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    rules:
+      - condition: 実装完了
+        next: ai_review
+      - condition: 実装未着手（レポートのみ）
+        next: ai_review
+      - condition: 判断できない、情報不足
+        next: ai_review
+      - condition: ユーザー入力が必要
+        next: implement
+        requires_user_input: true
+        interactive_only: true
+    instruction: implement-after-tests
+    output_contracts:
+      report:
+        - name: coder-scope.md
+          format: coder-scope
+        - name: coder-decisions.md
+          format: coder-decisions
+  - name: ai_review
+    edit: false
+    persona: ai-antipattern-reviewer
+    policy:
+      - review
+      - ai-antipattern
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - WebSearch
+      - WebFetch
+    rules:
+      - condition: AI特有の問題なし
+        next: reviewers
+      - condition: AI特有の問題あり
+        next: ai_fix
+    instruction: ai-review
+    output_contracts:
+      report:
+        - name: ai-review.md
+          format: ai-review
+  - name: ai_fix
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    session: refresh
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    pass_previous_response: false
+    rules:
+      - condition: AI問題の修正完了
+        next: ai_review
+      - condition: 修正不要（指摘対象ファイル/仕様の確認済み）
+        next: ai_no_fix
+      - condition: 判断できない、情報不足
+        next: ai_no_fix
+    instruction: ai-fix
+  - name: ai_no_fix
+    edit: false
+    persona: architecture-reviewer
+    policy: review
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+    rules:
+      - condition: ai_reviewの指摘が妥当（修正すべき）
+        next: ai_fix
+      - condition: ai_fixの判断が妥当（修正不要）
+        next: reviewers
+    instruction: arbitrate
+  - name: reviewers
+    parallel:
+      - name: arch-review
+        edit: false
+        persona: architecture-reviewer
+        policy: review
+        knowledge:
+          - architecture
+          - takt
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-arch
+        output_contracts:
+          report:
+            - name: architect-review.md
+              format: architecture-review
+      - name: security-review
+        edit: false
+        persona: security-reviewer
+        policy: review
+        knowledge: security
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-security
+        output_contracts:
+          report:
+            - name: security-review.md
+              format: security-review
+      - name: qa-review
+        edit: false
+        persona: qa-reviewer
+        policy:
+          - review
+          - qa
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-qa
+        output_contracts:
+          report:
+            - name: qa-review.md
+              format: qa-review
+      - name: testing-review
+        edit: false
+        persona: testing-reviewer
+        policy:
+          - review
+          - testing
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-test
+        output_contracts:
+          report:
+            - name: testing-review.md
+              format: testing-review
+      - name: requirements-review
+        edit: false
+        persona: requirements-reviewer
+        policy: review
+        allowed_tools:
+          - Read
+          - Glob
+          - Grep
+          - Bash
+          - WebSearch
+          - WebFetch
+        rules:
+          - condition: approved
+          - condition: needs_fix
+        instruction: review-requirements
+        output_contracts:
+          report:
+            - name: requirements-review.md
+              format: requirements-review
+    rules:
+      - condition: all("approved")
+        next: supervise
+      - condition: any("needs_fix")
+        next: fix
+  - name: fix
+    edit: true
+    persona: coder
+    policy:
+      - coding
+      - testing
+    knowledge:
+      - takt
+      - architecture
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Edit
+      - Write
+      - Bash
+      - WebSearch
+      - WebFetch
+    required_permission_mode: edit
+    pass_previous_response: false
+    rules:
+      - condition: 修正完了
+        next: reviewers
+      - condition: 判断できない、情報不足
+        next: plan
+    instruction: fix
+  - name: supervise
+    edit: false
+    persona: supervisor
+    policy: review
+    allowed_tools:
+      - Read
+      - Glob
+      - Grep
+      - Bash
+      - WebSearch
+      - WebFetch
+    pass_previous_response: false
+    rules:
+      - condition: すべて問題なし
+        next: COMPLETE
+      - condition: 要求未達成、テスト失敗、ビルドエラー
+        next: plan
+    instruction: supervise
+    output_contracts:
+      report:
+        - name: supervisor-validation.md
+          format: supervisor-validation
+        - name: summary.md
+          format: summary
+          use_judge: false