takt: refactor-status-handling (#477)

Config:
- PersistedGlobalConfig → GlobalConfig にリネーム、互換エイリアス削除
- persisted-global-config.ts → config-types.ts にリネーム
- ProjectConfig → GlobalConfig extends Omit<ProjectConfig, ...> の継承構造に整理
- verbose/logLevel/log_level を削除（logging セクションに統一）
- migration 機構（migratedProjectLocalKeys 等）を削除

Supervisor ペルソナ:
- 後方互換コードの検出・その場しのぎの検出・ボーイスカウトルールを除去（review.md ポリシー / architecture.md ナレッジと重複）
- ピース全体の見直しを supervise.md インストラクションに移動

takt-default-team-leader:
- loop_monitor のインライン instruction_template を既存ファイル参照に変更
- implement の「判断できない」ルールを ai_review → plan に修正

.github/workflows/cc-resolve.yml

@@ -247,9 +247,19 @@ jobs:
           if [ "$AHEAD" -gt 0 ]; then
             echo "Pushing $AHEAD commit(s)"
             git push
+            echo "pushed=true" >> "$GITHUB_OUTPUT"
           else
             echo "Nothing to push"
+            echo "pushed=false" >> "$GITHUB_OUTPUT"
           fi
+        id: push
+
+      - name: Trigger CI
+        if: steps.push.outputs.pushed == 'true'
+        run: |
+          gh workflow run ci.yml --ref "${{ steps.pr.outputs.branch }}"
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Report result
         if: always()

.github/workflows/ci.yml

@@ -5,7 +5,7 @@ on:
     branches: [main]
     types: [opened, synchronize, ready_for_review]
   push:
-    branches: [main, "takt/**"]
+    branches: [main]
   workflow_dispatch:
 
 concurrency:

.gitignore

@@ -32,21 +32,7 @@ e2e/results/
 .env.*.local
 .envrc
 
-# TAKT config (user data)
+# TAKT runtime data (facets/pieces/config are managed by .takt/.gitignore)
-.takt/
-!.takt/config.yaml
-!.takt/pieces/
-!.takt/pieces/**
-!.takt/personas/
-!.takt/personas/**
-!.takt/policies/
-!.takt/policies/**
-!.takt/knowledge/
-!.takt/knowledge/**
-!.takt/instructions/
-!.takt/instructions/**
-!.takt/output-contracts/
-!.takt/output-contracts/**
 
 task_planning/
 

.takt/.gitignore

@@ -0,0 +1,22 @@
+# Ignore everything by default
+*
+
+# This file itself
+!.gitignore
+
+# Project configuration
+!config.yaml
+
+# Facets and pieces (version-controlled)
+!pieces/
+!pieces/**
+!personas/
+!personas/**
+!policies/
+!policies/**
+!knowledge/
+!knowledge/**
+!instructions/
+!instructions/**
+!output-contracts/
+!output-contracts/**

.takt/config.yaml

@@ -0,0 +1,11 @@
+piece_overrides:
+  movements:
+    implement:
+      quality_gates:
+        - "Run `npm run test:e2e:mock` and verify all E2E tests pass"
+    fix:
+      quality_gates:
+        - "Run `npm run test:e2e:mock` and verify all E2E tests pass"
+    ai_fix:
+      quality_gates:
+        - "Run `npm run test:e2e:mock` and verify all E2E tests pass"

CHANGELOG.md

@@ -6,6 +6,40 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
+## [0.30.0] - 2026-03-05
+
+### Added
+
+- トレースレポートの自動生成: piece 実行完了時に movement の遷移・フェーズ・ルール評価結果を Markdown レポートとして `.takt/runs/` に自動出力。`logging.trace: true` で全文モード、デフォルトは redacted モード (#467)
+- 使用量イベントログ: プロバイダー呼び出しごとのトークン使用量を NDJSON 形式で記録。`logging.usage_events: true` で有効化 (#470)
+- タスクリトライ時のピース再利用確認: `takt list` からリトライ・追加指示する際に、前回と同じピースを使うか選び直すかを選択可能に (#468)
+
+### Changed
+
+- BREAKING: `takt switch` コマンドを削除。ピース選択はインタラクティブモード起動時（`takt`）に毎回行う方式に変更 (#465)
+- Claude プロバイダーの `allowed_tools` をビルトインピースの YAML 定義からエグゼキューター側に移動し、ピース YAML の簡素化と保守性を向上 (#469)
+- 設定構造をリファクタリング: `globalConfig.ts` を `globalConfigCore.ts`・`globalConfigAccessors.ts`・`globalConfigResolvers.ts`・`globalConfigSerializer.ts` に分割。プロジェクトローカル設定（`.takt/config.yaml`）のフォールバック優先度を明確化 (#460)
+- observability モジュールを `core/logging/` に再編成: `providerEventLogger` と `usageEventLogger` を統一的なログ基盤として整理 (#466)
+- レビュアー全体に `coder-decisions.md` の参照を追加し、コーダーの設計判断を考慮したレビューで誤検知を抑制
+- レビュー↔修正ループの収束を支援: レポート履歴の参照、ループモニター、修正方針のガイドラインを整備
+
+### Fixed
+
+- runtime 環境の `XDG_CONFIG_HOME` 上書きで `gh` CLI の認証が失敗する問題を修正。`GH_CONFIG_DIR` を元の設定から保持するよう変更
+- `.takt/config.yaml` に `runtime.prepare` を記述するとエラーになる問題を修正（プロジェクトレベルでの runtime 設定を許可） (#464)
+- インタラクティブモードで iteration limit 到達時にプロンプトが表示されず、exceeded 状態が保持されない問題を修正
+- PR 作成失敗時のタスクステータスを `failed` から `pr_failed` に分離し、実行成功だが PR 作成のみ失敗したケースを区別可能に
+- リトライ時にタスクにピース情報が引き継がれるよう修正
+- `.gitignore` の `.takt/` ディレクトリ ignore を削除し `.takt/.gitignore` に委譲（プロジェクト設定ファイルの追跡を可能に）
+- CI: push トリガーから `takt/**` を削除し二重実行を防止
+- `cc-resolve` ワークフローで push 後に CI を自動トリガーするよう修正
+
+### Internal
+
+- deprecated config マイグレーション処理を削除
+- プロジェクトローカル設定の優先度に関する統合テストを追加
+- テストヘルパーとテストセットアップの改善
+
 ## [0.29.0] - 2026-03-04
 
 ### Added

CLAUDE.md

@@ -35,7 +35,6 @@ TAKT (TAKT Agent Koordination Topology) is a multi-agent orchestration system fo
 | `takt watch` | Watch `.takt/tasks/` and auto-execute tasks (resident process) |
 | `takt add [task]` | Add a new task via AI conversation |
 | `takt list` | List task branches (merge, delete, retry) |
-| `takt switch [piece]` | Switch piece interactively |
 | `takt clear` | Clear agent conversation sessions (reset state) |
 | `takt eject [type] [name]` | Copy builtin piece or facet for customization (`--global` for ~/.takt/) |
 | `takt prompt [piece]` | Preview assembled prompts for each movement and phase |
@@ -602,17 +601,24 @@ Implemented in `src/core/runtime/runtime-environment.ts`.
 
 ## Debugging
 
-**Debug logging:** Set `debug_enabled: true` in `~/.takt/config.yaml` or create a `.takt/debug.yaml` file:
+**Debug logging:** Set `logging.debug: true` in `~/.takt/config.yaml`:
 ```yaml
-enabled: true
+logging:
+  debug: true
 ```
 
-Debug logs are written to `.takt/logs/debug.log` (ndjson format). Log levels: `debug`, `info`, `warn`, `error`.
+Debug logs are written to `.takt/runs/debug-{timestamp}/logs/` in NDJSON format. Log levels: `debug`, `info`, `warn`, `error`.
 
-**Verbose mode:** Create `.takt/verbose` file (empty file) to enable verbose console output. This automatically enables debug logging and sets log level to `debug`.
+**Verbose mode:** Set `verbose: true` in `~/.takt/config.yaml` or `TAKT_VERBOSE=true` to enable verbose console output. This enables `logging.debug`, `logging.trace`, and sets `logging.level` to `debug`.
 
 **Session logs:** All piece executions are logged to `.takt/logs/{sessionId}.jsonl`. Use `tail -f .takt/logs/{sessionId}.jsonl` to monitor in real-time.
 
+**Environment variables:**
+
+- `TAKT_LOGGING_LEVEL=info`
+- `TAKT_LOGGING_PROVIDER_EVENTS=true`
+- `TAKT_VERBOSE=true`
+
 **Testing with mocks:** Use `--provider mock` to test pieces without calling real AI APIs. Mock responses are deterministic and configurable via test fixtures.
 
 ## Testing Notes

README.md

@@ -142,7 +142,6 @@ See the [Builtin Catalog](./docs/builtin-catalog.md) for all pieces and personas
 | `takt run` | Execute all pending tasks |
 | `takt list` | Manage task branches (merge, retry, instruct, delete) |
 | `takt #N` | Execute GitHub Issue as task |
-| `takt switch` | Switch active piece |
 | `takt eject` | Copy builtin pieces/facets for customization |
 | `takt repertoire add` | Install a repertoire package from GitHub |
 

builtins/en/config.yaml

@@ -2,24 +2,35 @@
 # Location: ~/.takt/config.yaml
 
 # =====================================
-# General settings (piece-independent)
+# General settings
 # =====================================
 language: en        # UI language: en | ja
-log_level: info     # Log level: debug | info | warn | error
+
-provider: claude    # Default provider: claude | codex | opencode | mock
+# Default provider and model
-# model: sonnet     # Optional model name passed to provider
+# provider: claude                    # Default provider: claude | codex | opencode | cursor | copilot | mock
+# model: sonnet                       # Default model (passed directly to provider)
 
 # Execution control
 # worktree_dir: ~/takt-worktrees   # Base directory for shared clone execution
-# auto_pr: false                   # Auto-create PR after worktree execution
-branch_name_strategy: ai      # Branch strategy: romaji | ai
-concurrency: 2                  # Concurrent task execution for takt run (1-10)
-# task_poll_interval_ms: 500       # Polling interval in ms during takt run (100-5000)
 # prevent_sleep: false             # Prevent macOS idle sleep while running
+# auto_fetch: false                # Fetch before clone to keep shared clones up-to-date
+# base_branch: main                # Base branch to clone from (default: current branch)
+# concurrency: 1                   # Number of tasks to run concurrently in takt run (1-10)
+# task_poll_interval_ms: 500       # Polling interval in ms for picking up new tasks (100-5000)
+
+# PR / branch
+# auto_pr: false                   # Auto-create PR after worktree execution
+# draft_pr: false                  # Create PR as draft
+# branch_name_strategy: romaji     # Branch name generation: romaji | ai
+
+# Pipeline execution
+# pipeline:
+#   default_branch_prefix: "takt/"         # Branch prefix for pipeline-created branches
+#   commit_message_template: "{title}"     # Commit message template. Variables: {title}, {issue}
+#   pr_body_template: "{report}"           # PR body template. Variables: {issue_body}, {report}, {issue}
 
 # Output / notifications
-# minimal_output: false            # Minimized output for CI logs
+# minimal_output: false            # Suppress detailed agent output
-# verbose: false                   # Verbose output mode
 # notification_sound: true         # Master switch for sounds
 # notification_sound_events:       # Per-event sound toggle (unset means true)
 #   iteration_limit: true
@@ -27,74 +38,86 @@ concurrency: 2                  # Concurrent task execution for takt run (1-10)
 #   piece_abort: true
 #   run_complete: true
 #   run_abort: true
-# observability:
+# logging:
+#   level: info                    # Log level for console and file output
+#   trace: true                    # Generate human-readable execution trace report (trace.md)
+#   debug: false                   # Enable debug.log + prompts.jsonl
 #   provider_events: false         # Persist provider stream events
+#   usage_events: false            # Persist usage event logs
+
+# Analytics
 # analytics:
-#   enabled: true                  # Enable analytics metrics collection
+#   enabled: true                  # Enable local analytics collection
-#   events_path: ~/.takt/analytics/events  # Analytics event directory
+#   events_path: ~/.takt/analytics/events  # Custom events directory
-#   retention_days: 30             # Analytics event retention (days)
+#   retention_days: 30             # Retention period for event files
+
+# Interactive mode
+# interactive_preview_movements: 3 # Number of movement previews in interactive mode (0-10)
+
+# Per-persona provider/model overrides
+# persona_providers:
+#   coder:
+#     provider: claude
+#     model: opus
+#   reviewer:
+#     provider: codex
+#     model: gpt-5.2-codex
+
+# Provider-specific options (lowest priority, overridden by piece/movement)
+# provider_options:
+#   codex:
+#     network_access: true
+#   claude:
+#     sandbox:
+#       allow_unsandboxed_commands: true
+
+# Provider permission profiles
+# provider_profiles:
+#   claude:
+#     default_permission_mode: edit
+#   codex:
+#     default_permission_mode: edit
+
+# Runtime environment preparation
+# runtime:
+#   prepare: [node, gradle, ./custom-script.sh]
+
+# Piece-level overrides
+# piece_overrides:
+#   quality_gates:
+#     - "All tests pass"
+#   quality_gates_edit_only: true
+#   movements:
+#     review:
+#       quality_gates:
+#         - "No security vulnerabilities"
+#   personas:
+#     coder:
+#       quality_gates:
+#         - "Code follows conventions"
 
 # Credentials (environment variables take priority)
 # anthropic_api_key: "sk-ant-..." # Claude API key
 # openai_api_key: "sk-..."         # Codex/OpenAI API key
+# gemini_api_key: "..."            # Gemini API key
+# google_api_key: "..."            # Google API key
+# groq_api_key: "..."              # Groq API key
+# openrouter_api_key: "..."        # OpenRouter API key
 # opencode_api_key: "..."          # OpenCode API key
-# codex_cli_path: "/absolute/path/to/codex"  # Absolute path to Codex CLI
+# cursor_api_key: "..."            # Cursor API key
 
-# Pipeline
+# CLI paths
-# pipeline:
+# codex_cli_path: "/absolute/path/to/codex"    # Absolute path to Codex CLI
-#   default_branch_prefix: "takt/"             # Prefix for pipeline-created branches
+# claude_cli_path: "/absolute/path/to/claude"  # Absolute path to Claude Code CLI
-#   commit_message_template: "feat: {title} (#{issue})"  # Commit template
+# cursor_cli_path: "/absolute/path/to/cursor"  # Absolute path to cursor-agent CLI
-#   pr_body_template: |                          # PR body template
+# copilot_cli_path: "/absolute/path/to/copilot" # Absolute path to Copilot CLI
-#     ## Summary
+# copilot_github_token: "ghp_..."              # Copilot GitHub token
-#     {issue_body}
-#     Closes #{issue}
 
 # Misc
 # bookmarks_file: ~/.takt/preferences/bookmarks.yaml  # Bookmark file location
 
-# =====================================
+# Piece list / categories
-# Piece-related settings (global defaults)
-# =====================================
-# 1) Route provider/model per persona
-# persona_providers:
-#   coder:
-#     provider: codex    # Run coder persona on Codex
-#     model: o3-mini     # Use o3-mini model (optional)
-#   reviewer:
-#     provider: claude   # Run reviewer persona on Claude
-
-# 2) Provider options
-#    Priority (for piece-capable keys such as provider/model/provider_options):
-#    global < piece < project < env
-# provider_options:
-#   codex:
-#     network_access: true      # Allow network access for Codex
-#   opencode:
-#     network_access: true      # Allow network access for OpenCode
-#   claude:
-#     sandbox:
-#       allow_unsandboxed_commands: false   # true allows unsandboxed execution for listed commands
-#       excluded_commands:
-#         - "npm publish"                  # Commands excluded from sandbox
-
-# 3) Movement permission policy
-# provider_profiles:
-#   codex:
-#     default_permission_mode: full         # Base permission: readonly | edit | full
-#     movement_permission_overrides:
-#       ai_review: readonly                 # Per-movement override
-#   claude:
-#     default_permission_mode: edit
-
-# 4) Runtime preparation before execution (recommended: enabled)
-runtime:
-  prepare:
-    - gradle      # Prepare Gradle cache/env under .runtime
-    - node        # Prepare npm cache/env under .runtime
-
-# 5) Piece list / categories
 # enable_builtin_pieces: true                             # Enable built-in pieces from builtins/{lang}/pieces
 # disabled_builtins:
 #   - magi                                                # Built-in piece names to disable
 # piece_categories_file: ~/.takt/preferences/piece-categories.yaml  # Category definition file
-# interactive_preview_movements: 3                        # Preview movement count in interactive mode (0-10)

builtins/en/facets/instructions/fix.md

@@ -1,10 +1,16 @@
-Address the reviewer's feedback.
+Use reports in the Report Directory and fix the issues raised by the reviewer.
-Use reports in the Report Directory shown in the Piece Context and fix the issues raised by the reviewer.
-Use files in the Report Directory as primary evidence. If additional context is needed, you may consult Previous Response and conversation history as secondary sources (Previous Response may be unavailable). If information conflicts, prioritize reports in the Report Directory and actual file contents.
 
-**Important**: After fixing, run both build and tests.
+**Report reference policy:**
-- Build verification is mandatory. Run the build (type check) and verify there are no type errors
+- Use the latest review reports in the Report Directory as primary evidence.
-- Running tests is mandatory. After build succeeds, always run tests and verify results
+- Past iteration reports are saved as `{filename}.{timestamp}` in the same directory (e.g., `architect-review.md.20260304T123456Z`). For each report, run Glob with a `{report-name}.*` pattern, read up to 2 files in descending timestamp order, and understand persists / reopened trends before starting fixes.
+
+**Completion criteria (all must be satisfied):**
+- All findings in this iteration (new / reopened) have been fixed
+- Potential occurrences of the same `family_tag` have been fixed simultaneously (no partial fixes that cause recurrence)
+- At least one regression test per `family_tag` has been added (mandatory for config-contract and boundary-check findings)
+- Findings with the same `family_tag` from multiple reviewers have been merged and addressed as one fix
+
+**Important**: After fixing, run the build (type check) and tests.
 
 **Required output (include headings)**
 ## Work results
@@ -15,5 +21,11 @@ Use files in the Report Directory as primary evidence. If additional context is
 - {Build execution results}
 ## Test results
 - {Test command executed and results}
+## Convergence gate
+| Metric | Count |
+|--------|-------|
+| new (fixed in this iteration) | {N} |
+| reopened (recurrence fixed) | {N} |
+| persists (carried over, not addressed this iteration) | {N} |
 ## Evidence
 - {List key points from files checked/searches/diffs/logs}

builtins/en/facets/instructions/loop-monitor-reviewers-fix.md

@@ -0,0 +1,9 @@
+The reviewers → fix loop has repeated {cycle_count} times.
+
+Review the latest review reports in the Report Directory and determine
+whether this loop is healthy (converging) or unproductive (diverging or oscillating).
+
+**Judgment criteria:**
+- Is the number of new / reopened findings decreasing each cycle?
+- Are the same family_tag findings not repeating (is persists not growing)?
+- Are fixes actually being applied to the code?

builtins/en/facets/instructions/review-arch.md

@@ -12,6 +12,12 @@ Do not review AI-specific issues (already covered by the ai_review movement).
 - Call chain verification
 - Scattered hardcoding of contract strings (file names, config key names)
 
+
+**Design decisions reference:**
+Review {report:coder-decisions.md} to understand the recorded design decisions.
+- Do not flag intentionally documented decisions as FP
+- However, also evaluate whether the design decisions themselves are sound, and flag any problems
+
 **Previous finding tracking (required):**
 - First, extract open findings from "Previous Response"
 - Assign `finding_id` to each finding and classify current status as `new / persists / resolved`

builtins/en/facets/instructions/review-cqrs-es.md

@@ -11,6 +11,12 @@ AI-specific issue review is not needed (already covered by the ai_review movemen
 **Note**: If this project does not use the CQRS+ES pattern,
 review from a general domain design perspective instead.
 
+
+**Design decisions reference:**
+Review {report:coder-decisions.md} to understand the recorded design decisions.
+- Do not flag intentionally documented decisions as FP
+- However, also evaluate whether the design decisions themselves are sound, and flag any problems
+
 ## Judgment Procedure
 
 1. Review the change diff and detect issues based on the CQRS and Event Sourcing criteria above

builtins/en/facets/instructions/review-frontend.md

@@ -11,6 +11,12 @@ Review the changes from a frontend development perspective.
 **Note**: If this project does not include a frontend,
 proceed as no issues found.
 
+
+**Design decisions reference:**
+Review {report:coder-decisions.md} to understand the recorded design decisions.
+- Do not flag intentionally documented decisions as FP
+- However, also evaluate whether the design decisions themselves are sound, and flag any problems
+
 ## Judgment Procedure
 
 1. Review the change diff and detect issues based on the frontend development criteria above

builtins/en/facets/instructions/review-qa.md

@@ -7,6 +7,12 @@ Review the changes from a quality assurance perspective.
 - Logging and monitoring
 - Maintainability
 
+
+**Design decisions reference:**
+Review {report:coder-decisions.md} to understand the recorded design decisions.
+- Do not flag intentionally documented decisions as FP
+- However, also evaluate whether the design decisions themselves are sound, and flag any problems
+
 **Previous finding tracking (required):**
 - First, extract open findings from "Previous Response"
 - Assign `finding_id` to each finding and classify current status as `new / persists / resolved`

builtins/en/facets/instructions/review-requirements.md

@@ -6,6 +6,12 @@ Review the changes from a requirements fulfillment perspective.
 - Whether changes outside the scope (scope creep) have crept in
 - Whether there are any partial or missing implementations
 
+
+**Design decisions reference:**
+Review {report:coder-decisions.md} to understand the recorded design decisions.
+- Do not flag intentionally documented decisions as FP
+- However, also evaluate whether the design decisions themselves are sound, and flag any problems
+
 **Previous finding tracking (required):**
 - First, extract open findings from "Previous Response"
 - Assign `finding_id` to each finding and classify current status as `new / persists / resolved`

builtins/en/facets/instructions/review-security.md

@@ -4,6 +4,12 @@ Review the changes from a security perspective. Check for the following vulnerab
 - Data exposure risks
 - Cryptographic weaknesses
 
+
+**Design decisions reference:**
+Review {report:coder-decisions.md} to understand the recorded design decisions.
+- Do not flag intentionally documented decisions as FP
+- However, also evaluate whether the design decisions themselves are sound, and flag any problems
+
 ## Judgment Procedure
 
 1. Review the change diff and detect issues based on the security criteria above

builtins/en/facets/instructions/review-terraform.md

@@ -11,6 +11,12 @@ Do not review AI-specific issues (already covered by the ai_review movement).
 - Cost trade-off documentation
 - Unused variables / outputs / data sources
 
+
+**Design decisions reference:**
+Review {report:coder-decisions.md} to understand the recorded design decisions.
+- Do not flag intentionally documented decisions as FP
+- However, also evaluate whether the design decisions themselves are sound, and flag any problems
+
 **Previous finding tracking (required):**
 - First, extract open findings from "Previous Response"
 - Assign `finding_id` to each finding and classify current status as `new / persists / resolved`

builtins/en/facets/instructions/review-test.md

@@ -7,6 +7,12 @@ Review the changes from a test quality perspective.
 - Completeness (unnecessary tests, missing cases)
 - Appropriateness of mocks and fixtures
 
+
+**Design decisions reference:**
+Review {report:coder-decisions.md} to understand the recorded design decisions.
+- Do not flag intentionally documented decisions as FP
+- However, also evaluate whether the design decisions themselves are sound, and flag any problems
+
 ## Judgment Procedure
 
 1. Cross-reference the test plan/test scope reports in the Report Directory with the implemented tests

builtins/en/facets/instructions/supervise.md

@@ -1,9 +1,11 @@
 Run tests, verify the build, and perform final approval.
 
 **Overall piece verification:**
-1. Whether the plan and implementation results are consistent
+1. Check all reports in the report directory and verify overall piece consistency
-2. Whether findings from each review movement have been addressed
+   - Does implementation match the plan?
-3. Whether each task spec requirement has been achieved
+   - Were all review movement findings properly addressed?
+   - Was the original task objective achieved?
+2. Whether each task spec requirement has been achieved
    - Extract requirements one by one from the task spec
    - For each requirement, identify the implementing code (file:line)
    - Verify the code actually fulfills the requirement (read the file, run the test)

builtins/en/facets/instructions/team-leader-implement.md

@@ -1,17 +1,19 @@
-Decompose the implementation task into subtasks by file ownership and execute them in parallel. Assign files exclusively to each part to prevent conflicts.
+Analyze the implementation task and, if decomposition is appropriate, split into multiple parts for parallel execution.
 
 **Important:** Reference the plan report: {report:plan.md}
 
 **Steps:**
 
-1. Identify files to create/modify
+1. Assess whether decomposition is appropriate
-   - Reference the plan report and test scope to list all files to change
+   - Identify files to change and check inter-file dependencies
-   - Review the actual codebase to fill in any missing information
+   - If cross-cutting concerns exist (shared types, IDs, events), implement in a single part
+   - If few files are involved, or the task is a rename/refactoring, implement in a single part
 
-2. Group files by layer/module
+2. If decomposing: 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
+   - Keep test files and implementation files in the same part
 
 3. Assign file ownership exclusively to each part
    - Each part's instruction must clearly state:

builtins/en/facets/knowledge/task-decomposition.md

@@ -0,0 +1,66 @@
+# Task Decomposition Knowledge
+
+## Decomposition Feasibility
+
+Before splitting a task into multiple parts, assess whether decomposition is appropriate. When decomposition is unsuitable, implementing in a single part is more efficient.
+
+| Criteria | Judgment |
+|----------|----------|
+| Changed files clearly separate into layers | Decompose |
+| Shared types/IDs span multiple parts | Single part |
+| Broad rename/refactoring | Single part |
+| Fewer than 5 files to change | Single part |
+| Same file needs editing by multiple parts | Single part |
+
+### Detecting Cross-Cutting Concerns
+
+When any of the following apply, independent parts cannot maintain consistency. Consolidate into a single part.
+
+- A new ID, key, or type is generated in one module and consumed in another
+- Both the event emitter and event receiver need changes
+- An existing interface signature changes, requiring updates to all call sites
+
+## File Exclusivity Principle
+
+When decomposing into multiple parts, each part's file ownership must be completely exclusive.
+
+| Criteria | Judgment |
+|----------|----------|
+| Same file edited by multiple parts | REJECT (causes conflicts) |
+| Type definition and consumer in different parts | Consolidate into the type definition part |
+| Test file and implementation file in different parts | Consolidate into the same part |
+
+### Grouping Priority
+
+1. **By dependency direction** — keep dependency source and target in the same part
+2. **By layer** — domain layer / infrastructure layer / API layer
+3. **By feature** — independent functional units
+
+## Failure Patterns
+
+### Part Overlap
+
+When two parts own the same file or feature, sub-agents overwrite each other's changes, causing repeated REJECT in reviews.
+
+```
+// NG: part-2 and part-3 own the same file
+part-2: taskInstructionActions.ts — instruct confirmation dialog
+part-3: taskInstructionActions.ts — requeue confirmation dialog
+
+// OK: consolidate into one part
+part-1: taskInstructionActions.ts — both instruct/requeue confirmation dialogs
+```
+
+### Shared Contract Mismatch
+
+When part A generates an ID that part B consumes, both parts implement independently, leading to mismatches in ID name, type, or passing mechanism.
+
+```
+// NG: shared contract across independent parts
+part-1: generates phaseExecutionId
+part-2: consumes phaseExecutionId
+→ part-1 uses string, part-2 expects number → integration error
+
+// OK: single part for consistent implementation
+part-1: implements phaseExecutionId from generation to consumption
+```

builtins/en/facets/output-contracts/ai-review.md

@@ -15,22 +15,27 @@
 | Scope | ✅ | - |
 
 ## Current Iteration Findings (new)
-| # | finding_id | Category | Location | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Category | Location | Issue | Fix Suggestion |
-|---|------------|----------|----------|-------|----------------|
+|---|------------|------------|----------|----------|-------|----------------|
-| 1 | AI-NEW-src-file-L23 | Hallucinated API | `src/file.ts:23` | Non-existent method | Replace with existing API |
+| 1 | AI-NEW-src-file-L23 | hallucination | Hallucinated API | `src/file.ts:23` | Non-existent method | Replace with existing API |
 
 ## Carry-over Findings (persists)
-| # | finding_id | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
-|---|------------|-------------------|------------------|-------|----------------|
+|---|------------|------------|-------------------|------------------|-------|----------------|
-| 1 | AI-PERSIST-src-file-L42 | `src/file.ts:42` | `src/file.ts:42` | Still unresolved | Apply prior fix plan |
+| 1 | AI-PERSIST-src-file-L42 | hallucination | `src/file.ts:42` | `src/file.ts:42` | Still unresolved | Apply prior fix plan |
 
 ## Resolved Findings (resolved)
 | finding_id | Resolution Evidence |
 |------------|---------------------|
 | AI-RESOLVED-src-file-L10 | `src/file.ts:10` no longer contains the issue |
 
+## Reopened Findings (reopened)
+| # | finding_id | family_tag | Prior Resolution Evidence | Recurrence Evidence | Issue | Fix Suggestion |
+|---|------------|------------|--------------------------|---------------------|-------|----------------|
+| 1 | AI-REOPENED-src-file-L55 | hallucination | `Previously fixed at src/file.ts:10` | `Recurred at src/file.ts:55` | Issue description | Fix approach |
+
 ## Rejection Gate
-- REJECT is valid only when at least one finding exists in `new` or `persists`
+- REJECT is valid only when at least one finding exists in `new`, `persists`, or `reopened`
 - Findings without `finding_id` are invalid
 ```
 

builtins/en/facets/output-contracts/architecture-review.md

@@ -15,24 +15,29 @@
 - [x] Call chain verification
 
 ## Current Iteration Findings (new)
-| # | finding_id | Scope | Location | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Scope | Location | Issue | Fix Suggestion |
-|---|------------|-------|----------|-------|----------------|
+|---|------------|------------|-------|----------|-------|----------------|
-| 1 | ARCH-NEW-src-file-L42 | In-scope | `src/file.ts:42` | Issue description | Fix approach |
+| 1 | ARCH-NEW-src-file-L42 | design-violation | In-scope | `src/file.ts:42` | Issue description | Fix approach |
 
 Scope: "In-scope" (fixable in this change) / "Out-of-scope" (existing issue, non-blocking)
 
 ## Carry-over Findings (persists)
-| # | finding_id | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
-|---|------------|-------------------|------------------|-------|----------------|
+|---|------------|------------|-------------------|------------------|-------|----------------|
-| 1 | ARCH-PERSIST-src-file-L77 | `src/file.ts:77` | `src/file.ts:77` | Still unresolved | Apply prior fix plan |
+| 1 | ARCH-PERSIST-src-file-L77 | design-violation | `src/file.ts:77` | `src/file.ts:77` | Still unresolved | Apply prior fix plan |
 
 ## Resolved Findings (resolved)
 | finding_id | Resolution Evidence |
 |------------|---------------------|
 | ARCH-RESOLVED-src-file-L10 | `src/file.ts:10` now satisfies the rule |
 
+## Reopened Findings (reopened)
+| # | finding_id | family_tag | Prior Resolution Evidence | Recurrence Evidence | Issue | Fix Suggestion |
+|---|------------|------------|--------------------------|---------------------|-------|----------------|
+| 1 | ARCH-REOPENED-src-file-L55 | design-violation | `Previously fixed at src/file.ts:10` | `Recurred at src/file.ts:55` | Issue description | Fix approach |
+
 ## Rejection Gate
-- REJECT is valid only when at least one finding exists in `new` or `persists`
+- REJECT is valid only when at least one finding exists in `new`, `persists`, or `reopened`
 - Findings without `finding_id` are invalid
 ```
 

builtins/en/facets/output-contracts/cqrs-es-review.md

@@ -15,13 +15,33 @@
 | Projections | ✅ | - |
 | Eventual consistency | ✅ | - |
 
-## Issues (if REJECT)
+## Current Iteration Findings (new)
-| # | Scope | Location | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Scope | Location | Issue | Fix Suggestion |
-|---|-------|----------|-------|----------------|
+|---|------------|------------|-------|----------|-------|----------------|
-| 1 | In-scope | `src/file.ts:42` | Issue description | Fix approach |
+| 1 | CQRS-NEW-src-file-L42 | cqrs-violation | In-scope | `src/file.ts:42` | Issue description | Fix approach |
 
 Scope: "In-scope" (fixable in this change) / "Out-of-scope" (existing issue, non-blocking)
 
-## Existing Issues (reference, non-blocking)
+## Carry-over Findings (persists)
-- {Record of existing issues unrelated to the current change}
+| # | finding_id | family_tag | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
+|---|------------|------------|-------------------|------------------|-------|----------------|
+| 1 | CQRS-PERSIST-src-file-L77 | cqrs-violation | `src/file.ts:77` | `src/file.ts:77` | Still unresolved | Apply prior fix plan |
+
+## Resolved Findings (resolved)
+| finding_id | Resolution Evidence |
+|------------|---------------------|
+| CQRS-RESOLVED-src-file-L10 | `src/file.ts:10` now satisfies the rule |
+
+## Reopened Findings (reopened)
+| # | finding_id | family_tag | Prior Resolution Evidence | Recurrence Evidence | Issue | Fix Suggestion |
+|---|------------|------------|--------------------------|---------------------|-------|----------------|
+| 1 | CQRS-REOPENED-src-file-L55 | cqrs-violation | `Previously fixed at src/file.ts:10` | `Recurred at src/file.ts:55` | Issue description | Fix approach |
+
+## Rejection Gate
+- REJECT is valid only when at least one finding exists in `new`, `persists`, or `reopened`
+- Findings without `finding_id` are invalid
 ```
+
+**Cognitive load reduction rules:**
+- APPROVE → Summary only (5 lines or fewer)
+- REJECT → Include only relevant finding rows (30 lines or fewer)

builtins/en/facets/output-contracts/frontend-review.md

@@ -15,8 +15,31 @@
 | Accessibility | ✅ | - |
 | Type safety | ✅ | - |
 
-## Issues (if REJECT)
+## Current Iteration Findings (new)
-| # | Location | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Location | Issue | Fix Suggestion |
-|---|----------|-------|----------------|
+|---|------------|------------|----------|-------|----------------|
-| 1 | `src/file.tsx:42` | Issue description | Fix approach |
+| 1 | FE-NEW-src-file-L42 | component-design | `src/file.tsx:42` | Issue description | Fix approach |
+
+## Carry-over Findings (persists)
+| # | finding_id | family_tag | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
+|---|------------|------------|-------------------|------------------|-------|----------------|
+| 1 | FE-PERSIST-src-file-L77 | component-design | `src/file.tsx:77` | `src/file.tsx:77` | Still unresolved | Apply prior fix plan |
+
+## Resolved Findings (resolved)
+| finding_id | Resolution Evidence |
+|------------|---------------------|
+| FE-RESOLVED-src-file-L10 | `src/file.tsx:10` now satisfies the rule |
+
+## Reopened Findings (reopened)
+| # | finding_id | family_tag | Prior Resolution Evidence | Recurrence Evidence | Issue | Fix Suggestion |
+|---|------------|------------|--------------------------|---------------------|-------|----------------|
+| 1 | FE-REOPENED-src-file-L55 | component-design | `Previously fixed at src/file.tsx:10` | `Recurred at src/file.tsx:55` | Issue description | Fix approach |
+
+## Rejection Gate
+- REJECT is valid only when at least one finding exists in `new`, `persists`, or `reopened`
+- Findings without `finding_id` are invalid
 ```
+
+**Cognitive load reduction rules:**
+- APPROVE → Summary only (5 lines or fewer)
+- REJECT → Include only relevant finding rows (30 lines or fewer)

builtins/en/facets/output-contracts/qa-review.md

@@ -16,21 +16,26 @@
 | Maintainability | ✅ | - |
 
 ## Current Iteration Findings (new)
-| # | finding_id | Category | Location | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Category | Location | Issue | Fix Suggestion |
-|---|------------|----------|----------|-------|----------------|
+|---|------------|------------|----------|----------|-------|----------------|
-| 1 | QA-NEW-src-test-L42 | Testing | `src/test.ts:42` | Missing negative test | Add failure-path test |
+| 1 | QA-NEW-src-test-L42 | test-coverage | Testing | `src/test.ts:42` | Missing negative test | Add failure-path test |
 
 ## Carry-over Findings (persists)
-| # | finding_id | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
-|---|------------|-------------------|------------------|-------|----------------|
+|---|------------|------------|-------------------|------------------|-------|----------------|
-| 1 | QA-PERSIST-src-test-L77 | `src/test.ts:77` | `src/test.ts:77` | Still flaky | Stabilize assertion & setup |
+| 1 | QA-PERSIST-src-test-L77 | test-coverage | `src/test.ts:77` | `src/test.ts:77` | Still flaky | Stabilize assertion & setup |
 
 ## Resolved Findings (resolved)
 | finding_id | Resolution Evidence |
 |------------|---------------------|
 | QA-RESOLVED-src-test-L10 | `src/test.ts:10` now covers error path |
 
+## Reopened Findings (reopened)
+| # | finding_id | family_tag | Prior Resolution Evidence | Recurrence Evidence | Issue | Fix Suggestion |
+|---|------------|------------|--------------------------|---------------------|-------|----------------|
+| 1 | QA-REOPENED-src-test-L55 | test-coverage | `Previously fixed at src/test.ts:10` | `Recurred at src/test.ts:55` | Issue description | Fix approach |
+
 ## Rejection Gate
-- REJECT is valid only when at least one finding exists in `new` or `persists`
+- REJECT is valid only when at least one finding exists in `new`, `persists`, or `reopened`
 - Findings without `finding_id` are invalid
 ```

builtins/en/facets/output-contracts/requirements-review.md

@@ -20,22 +20,27 @@
 | 1 | {change not in requirements} | `src/file.ts` | Justified/Unnecessary |
 
 ## Current Iteration Findings (new)
-| # | finding_id | Category | Location | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Category | Location | Issue | Fix Suggestion |
-|---|------------|----------|----------|-------|----------------|
+|---|------------|------------|----------|----------|-------|----------------|
-| 1 | REQ-NEW-src-file-L42 | Unimplemented | `src/file.ts:42` | Issue description | Fix suggestion |
+| 1 | REQ-NEW-src-file-L42 | req-gap | Unimplemented | `src/file.ts:42` | Issue description | Fix suggestion |
 
 ## Carry-over Findings (persists)
-| # | finding_id | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
-|---|------------|-------------------|------------------|-------|----------------|
+|---|------------|------------|-------------------|------------------|-------|----------------|
-| 1 | REQ-PERSIST-src-file-L77 | `file:line` | `file:line` | Unresolved | Fix suggestion |
+| 1 | REQ-PERSIST-src-file-L77 | req-gap | `file:line` | `file:line` | Unresolved | Fix suggestion |
 
 ## Resolved Findings (resolved)
 | finding_id | Resolution Evidence |
 |------------|---------------------|
 | REQ-RESOLVED-src-file-L10 | `file:line` now satisfies the requirement |
 
+## Reopened Findings (reopened)
+| # | finding_id | family_tag | Prior Resolution Evidence | Recurrence Evidence | Issue | Fix Suggestion |
+|---|------------|------------|--------------------------|---------------------|-------|----------------|
+| 1 | REQ-REOPENED-src-file-L55 | req-gap | `Previously fixed at file:line` | `Recurred at file:line` | Issue description | Fix approach |
+
 ## Rejection Gate
-- REJECT is valid only when at least one finding exists in `new` or `persists`
+- REJECT is valid only when at least one finding exists in `new`, `persists`, or `reopened`
 - Findings without `finding_id` are invalid
 ```
 

builtins/en/facets/output-contracts/security-review.md

@@ -14,25 +14,30 @@
 | Dependencies | ✅ | - |
 
 ## Current Iteration Findings (new)
-| # | finding_id | Severity | Type | Location | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Severity | Type | Location | Issue | Fix Suggestion |
-|---|------------|----------|------|----------|-------|----------------|
+|---|------------|------------|----------|------|----------|-------|----------------|
-| 1 | SEC-NEW-src-db-L42 | High | SQLi | `src/db.ts:42` | Raw query string | Use parameterized queries |
+| 1 | SEC-NEW-src-db-L42 | injection-risk | High | SQLi | `src/db.ts:42` | Raw query string | Use parameterized queries |
 
 ## Carry-over Findings (persists)
-| # | finding_id | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
-|---|------------|-------------------|------------------|-------|----------------|
+|---|------------|------------|-------------------|------------------|-------|----------------|
-| 1 | SEC-PERSIST-src-auth-L18 | `src/auth.ts:18` | `src/auth.ts:18` | Weak validation persists | Harden validation |
+| 1 | SEC-PERSIST-src-auth-L18 | injection-risk | `src/auth.ts:18` | `src/auth.ts:18` | Weak validation persists | Harden validation |
 
 ## Resolved Findings (resolved)
 | finding_id | Resolution Evidence |
 |------------|---------------------|
 | SEC-RESOLVED-src-db-L10 | `src/db.ts:10` now uses bound parameters |
 
+## Reopened Findings (reopened)
+| # | finding_id | family_tag | Prior Resolution Evidence | Recurrence Evidence | Issue | Fix Suggestion |
+|---|------------|------------|--------------------------|---------------------|-------|----------------|
+| 1 | SEC-REOPENED-src-auth-L55 | injection-risk | `Previously fixed at src/auth.ts:20` | `Recurred at src/auth.ts:55` | Issue description | Fix approach |
+
 ## Warnings (non-blocking)
 - {Security recommendations}
 
 ## Rejection Gate
-- REJECT is valid only when at least one finding exists in `new` or `persists`
+- REJECT is valid only when at least one finding exists in `new`, `persists`, or `reopened`
 - Findings without `finding_id` are invalid
 ```
 

builtins/en/facets/output-contracts/terraform-review.md

@@ -4,39 +4,44 @@
 ## Result: APPROVE / REJECT
 
 ## Summary
-{1-2 sentences summarizing the result}
+{Summarize the result in 1-2 sentences}
 
 ## Reviewed Aspects
 - [x] Variable declarations (type, description, sensitive)
 - [x] Resource naming (name_prefix pattern)
-- [x] File organization (one file per concern)
+- [x] File structure (one concern per file)
-- [x] Security configurations
+- [x] Security settings
 - [x] Tag management
-- [x] Lifecycle rules
+- [x] lifecycle rules
 - [x] Cost trade-off documentation
 
-## New Findings (new)
+## Current Iteration Findings (new)
-| # | finding_id | Scope | Location | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Scope | Location | Issue | Fix Suggestion |
-|---|------------|-------|----------|-------|---------------|
+|---|------------|------------|-------|----------|-------|----------------|
-| 1 | TF-NEW-file-L42 | In scope | `modules/example/main.tf:42` | Issue description | How to fix |
+| 1 | TF-NEW-file-L42 | tf-convention | In-scope | `modules/example/main.tf:42` | Issue description | Fix approach |
 
-Scope: "In scope" (fixable now) / "Out of scope" (existing issue, non-blocking)
+Scope: "In-scope" (fixable in this change) / "Out-of-scope" (existing issue, non-blocking)
 
-## Persisting Findings (persists)
+## Carry-over Findings (persists)
-| # | finding_id | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
-|---|------------|-------------------|------------------|-------|---------------|
+|---|------------|------------|-------------------|------------------|-------|----------------|
-| 1 | TF-PERSIST-file-L77 | `file.tf:77` | `file.tf:77` | Unresolved | Apply existing fix plan |
+| 1 | TF-PERSIST-file-L77 | tf-convention | `file.tf:77` | `file.tf:77` | Still unresolved | Apply prior fix plan |
 
-## Resolved
+## Resolved Findings (resolved)
 | finding_id | Resolution Evidence |
-|------------|-------------------|
+|------------|---------------------|
-| TF-RESOLVED-file-L10 | `file.tf:10` meets conventions |
+| TF-RESOLVED-file-L10 | `file.tf:10` now satisfies the convention |
 
-## REJECT Criteria
+## Reopened Findings (reopened)
-- REJECT only if 1+ `new` or `persists` findings exist
+| # | finding_id | family_tag | Prior Resolution Evidence | Recurrence Evidence | Issue | Fix Suggestion |
+|---|------------|------------|--------------------------|---------------------|-------|----------------|
+| 1 | TF-REOPENED-file-L55 | tf-convention | `Previously fixed at file.tf:10` | `Recurred at file.tf:55` | Issue description | Fix approach |
+
+## Rejection Gate
+- REJECT is valid only when at least one finding exists in `new`, `persists`, or `reopened`
 - Findings without `finding_id` are invalid
 ```
 
 **Cognitive load reduction rules:**
-- APPROVE → Summary only (5 lines or less)
+- APPROVE → Summary only (5 lines or fewer)
-- REJECT → Only relevant findings in table (30 lines or less)
+- REJECT → Include only relevant finding rows (30 lines or fewer)

builtins/en/facets/output-contracts/testing-review.md

@@ -17,22 +17,27 @@
 | Test strategy (unit/integration/E2E) | ✅ | - |
 
 ## Current Iteration Findings (new)
-| # | finding_id | Category | Location | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Category | Location | Issue | Fix Suggestion |
-|---|------------|----------|----------|-------|----------------|
+|---|------------|------------|----------|----------|-------|----------------|
-| 1 | TEST-NEW-src-test-L42 | Coverage | `src/test.ts:42` | Issue description | Fix suggestion |
+| 1 | TEST-NEW-src-test-L42 | test-structure | Coverage | `src/test.ts:42` | Issue description | Fix suggestion |
 
 ## Carry-over Findings (persists)
-| # | finding_id | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
+| # | finding_id | family_tag | Previous Evidence | Current Evidence | Issue | Fix Suggestion |
-|---|------------|-------------------|------------------|-------|----------------|
+|---|------------|------------|-------------------|------------------|-------|----------------|
-| 1 | TEST-PERSIST-src-test-L77 | `src/test.ts:77` | `src/test.ts:77` | Unresolved | Fix suggestion |
+| 1 | TEST-PERSIST-src-test-L77 | test-structure | `src/test.ts:77` | `src/test.ts:77` | Unresolved | Fix suggestion |
 
 ## Resolved Findings (resolved)
 | finding_id | Resolution Evidence |
 |------------|---------------------|
 | TEST-RESOLVED-src-test-L10 | `src/test.ts:10` now has sufficient coverage |
 
+## Reopened Findings (reopened)
+| # | finding_id | family_tag | Prior Resolution Evidence | Recurrence Evidence | Issue | Fix Suggestion |
+|---|------------|------------|--------------------------|---------------------|-------|----------------|
+| 1 | TEST-REOPENED-src-test-L55 | test-structure | `Previously fixed at src/test.ts:10` | `Recurred at src/test.ts:55` | Issue description | Fix approach |
+
 ## Rejection Gate
-- REJECT is valid only when at least one finding exists in `new` or `persists`
+- REJECT is valid only when at least one finding exists in `new`, `persists`, or `reopened`
 - Findings without `finding_id` are invalid
 ```
 

builtins/en/facets/personas/supervisor.md

@@ -81,15 +81,7 @@ You are the **human proxy** in the automated piece. Before approval, verify the
 | Production ready | No mock/stub/TODO remaining? |
 | Operation | Actually works as expected? |
 
-### 6. Backward Compatibility Code Detection
+### 6. Spec Compliance Final Check
-
-**Backward compatibility code is unnecessary unless explicitly instructed.** REJECT if found:
-
-- Unused re-exports, `_var` renames, `// removed` comments
-- Fallbacks, old API maintenance, migration code
-- Legacy support kept "just in case"
-
-### 7. Spec Compliance Final Check
 
 **Final verification that changes comply with the project's documented specifications.**
 
@@ -115,66 +107,6 @@ Additions can be reverted, but restoring deleted flows is difficult.
 - A "UI fix" task includes structural changes to backend domain models
 - A "display change" task rewrites business logic flows
 
-### 8. Piece Overall Review
-
-**Check all reports in the report directory and verify overall piece consistency.**
-
-Check:
-- Does implementation match the plan (00-plan.md)?
-- Were all review step issues properly addressed?
-- Was the original task objective achieved?
-
-**Piece-wide issues:**
-| Issue | Action |
-|-------|--------|
-| Plan-implementation gap | REJECT - Request plan revision or implementation fix |
-| Unaddressed review feedback | REJECT - Point out specific unaddressed items |
-| Deviation from original purpose | REJECT - Request return to objective |
-| Scope creep | REJECT - Deletions outside task order must be reverted |
-
-### 9. Improvement Suggestion Check
-
-**Check review reports for unaddressed improvement suggestions.**
-
-Check:
-- "Improvement Suggestions" section in Architect report
-- Warnings and suggestions in AI Reviewer report
-- Recommendations in Security report
-
-**If there are unaddressed improvement suggestions:**
-- Judge if the improvement should be addressed in this task
-- If it should be addressed, **REJECT** and request fix
-- If it should be addressed in next task, record as "technical debt" in report
-
-**Judgment criteria:**
-| Type of suggestion | Decision |
-|--------------------|----------|
-| Minor fix in same file | Address now (REJECT) |
-| Fixable in seconds to minutes | Address now (REJECT) |
-| Redundant code / unnecessary expression removal | Address now (REJECT) |
-| Affects other features | Address in next task (record only) |
-| External impact (API changes, etc.) | Address in next task (record only) |
-| Requires significant refactoring (large scope) | Address in next task (record only) |
-
-### Boy Scout Rule
-
-**"Functionally harmless" is not a free pass.** Classifying a near-zero-cost fix as "non-blocking" or "next task" is a compromise. There is no guarantee it will be addressed in a future task, and it accumulates as technical debt.
-
-**Principle:** If a reviewer found it and it can be fixed in minutes, make the coder fix it now. Do not settle for recording it as a "non-blocking improvement suggestion."
-
-## Workaround Detection
-
-**REJECT** if any of the following remain:
-
-| Pattern | Example |
-|---------|---------|
-| TODO/FIXME | `// TODO: implement later` |
-| Commented out | Code that should be deleted remains |
-| Hardcoded | Values that should be config are hardcoded |
-| Mock data | Dummy data unusable in production |
-| console.log | Forgotten debug output |
-| Skipped tests | `@Disabled`, `.skip()` |
-
 ## Important
 
 - **Actually run**: Don't just look at files, execute and verify

builtins/en/pieces/backend-cqrs-mini.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 20
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix_both
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: fix_both
+        - condition: unproductive (same findings repeating)
+          next: supervise_fix
 movements:
   - name: plan
     edit: false
@@ -17,6 +30,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -47,6 +62,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -81,6 +98,8 @@ movements:
         policy:
           - review
           - ai-antipattern
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -104,6 +123,8 @@ movements:
           - cqrs-es
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -144,6 +165,8 @@ movements:
           - cqrs-es
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -169,6 +192,8 @@ movements:
           - cqrs-es
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -198,6 +223,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -228,6 +255,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/backend-cqrs-review-fix.yaml

@@ -15,7 +15,7 @@ loop_monitors:
     threshold: 3
     judge:
       persona: supervisor
-      instruction_template: loop-monitor-ai-fix
+      instruction_template: loop-monitor-reviewers-fix
       rules:
         - condition: Healthy (progress being made)
           next: reviewers
@@ -26,6 +26,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -53,6 +55,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -75,6 +79,8 @@ movements:
         knowledge:
           - cqrs-es
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -95,6 +101,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -116,6 +124,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -148,6 +158,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -170,6 +182,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -202,6 +216,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/backend-cqrs-review.yaml

@@ -13,6 +13,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -40,6 +42,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -62,6 +66,8 @@ movements:
         knowledge:
           - cqrs-es
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -82,6 +88,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -103,6 +111,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -128,6 +138,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/backend-cqrs.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 30
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: reviewers
+        - condition: unproductive (same findings repeating)
+          next: supervise
 movements:
   - name: plan
     edit: false
@@ -16,6 +29,8 @@ movements:
       - backend
       - cqrs-es
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -45,6 +60,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -78,6 +95,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -106,6 +125,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -128,6 +149,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -147,6 +170,8 @@ movements:
         knowledge:
           - cqrs-es
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -166,6 +191,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -186,6 +213,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -216,6 +245,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -237,6 +268,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -268,6 +301,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/backend-mini.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 20
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix_both
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: fix_both
+        - condition: unproductive (same findings repeating)
+          next: supervise_fix
 movements:
   - name: plan
     edit: false
@@ -16,6 +29,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -45,6 +60,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -79,6 +96,8 @@ movements:
         policy:
           - review
           - ai-antipattern
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -101,6 +120,8 @@ movements:
           - backend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -140,6 +161,8 @@ movements:
           - backend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -164,6 +187,8 @@ movements:
           - backend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -192,6 +217,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -221,6 +248,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/backend-review-fix.yaml

@@ -15,7 +15,7 @@ loop_monitors:
     threshold: 3
     judge:
       persona: supervisor
-      instruction_template: loop-monitor-ai-fix
+      instruction_template: loop-monitor-reviewers-fix
       rules:
         - condition: Healthy (progress being made)
           next: reviewers
@@ -26,6 +26,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -53,6 +55,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -73,6 +77,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -94,6 +100,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -125,6 +133,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -147,6 +157,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -178,6 +190,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/backend-review.yaml

@@ -13,6 +13,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -40,6 +42,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -60,6 +64,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -81,6 +87,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -106,6 +114,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/backend.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 30
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: reviewers
+        - condition: unproductive (same findings repeating)
+          next: supervise
 movements:
   - name: plan
     edit: false
@@ -15,6 +28,8 @@ movements:
     knowledge:
       - backend
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -43,6 +58,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -76,6 +93,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -103,6 +122,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -125,6 +146,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -144,6 +167,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -163,6 +188,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -183,6 +210,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -212,6 +241,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -233,6 +264,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -263,6 +296,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/compound-eye.yaml

@@ -17,6 +17,8 @@ movements:
         provider: claude
         session: refresh
         knowledge: architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -56,6 +58,8 @@ movements:
         provider: codex
         session: refresh
         knowledge: architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -95,6 +99,8 @@ movements:
   - name: synthesize
     edit: false
     persona: supervisor
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/deep-research.yaml

@@ -14,6 +14,8 @@ movements:
     policy: research
     knowledge: research
     instruction: research-plan
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -43,6 +45,8 @@ movements:
         - Grep
         - WebSearch
         - WebFetch
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Write
@@ -62,6 +66,8 @@ movements:
     knowledge: research
     instruction: research-analyze
     edit: true
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Write
@@ -79,6 +85,8 @@ movements:
     policy: research
     knowledge: research
     instruction: research-supervise
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/default.yaml

@@ -33,11 +33,25 @@ loop_monitors:
           next: ai_review
         - condition: Unproductive (no improvement)
           next: reviewers
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: reviewers
+        - condition: unproductive (same findings repeating)
+          next: ABORT
 movements:
   - name: plan
     edit: false
     persona: planner
     knowledge: architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -69,6 +83,8 @@ movements:
       - testing
     knowledge:
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -106,6 +122,8 @@ movements:
     session: refresh
     knowledge:
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -140,6 +158,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -165,6 +185,8 @@ movements:
     session: refresh
     knowledge:
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -191,6 +213,8 @@ movements:
         persona: architecture-reviewer
         policy: review
         knowledge: architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -209,6 +233,8 @@ movements:
         edit: false
         persona: supervisor
         policy: review
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -240,6 +266,8 @@ movements:
       - testing
     knowledge:
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/dual-cqrs-mini.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 20
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix_both
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: fix_both
+        - condition: unproductive (same findings repeating)
+          next: supervise_fix
 movements:
   - name: plan
     edit: false
@@ -18,6 +31,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -49,6 +64,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -83,6 +100,8 @@ movements:
         policy:
           - review
           - ai-antipattern
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -107,6 +126,8 @@ movements:
           - cqrs-es
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -148,6 +169,8 @@ movements:
           - cqrs-es
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -174,6 +197,8 @@ movements:
           - cqrs-es
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -204,6 +229,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -235,6 +262,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/dual-cqrs-review-fix.yaml

@@ -15,7 +15,7 @@ loop_monitors:
     threshold: 3
     judge:
       persona: supervisor
-      instruction_template: loop-monitor-ai-fix
+      instruction_template: loop-monitor-reviewers-fix
       rules:
         - condition: Healthy (progress being made)
           next: reviewers
@@ -26,6 +26,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -54,6 +56,8 @@ movements:
           - architecture
           - frontend
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -76,6 +80,8 @@ movements:
         knowledge:
           - cqrs-es
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -96,6 +102,8 @@ movements:
         persona: frontend-reviewer
         policy: review
         knowledge: frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -116,6 +124,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -137,6 +147,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -170,6 +182,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -192,6 +206,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -225,6 +241,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/dual-cqrs-review.yaml

@@ -13,6 +13,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -41,6 +43,8 @@ movements:
           - architecture
           - frontend
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -63,6 +67,8 @@ movements:
         knowledge:
           - cqrs-es
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -83,6 +89,8 @@ movements:
         persona: frontend-reviewer
         policy: review
         knowledge: frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -103,6 +111,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -124,6 +134,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -149,6 +161,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/dual-cqrs.yaml

@@ -21,6 +21,18 @@ loop_monitors:
           next: ai_review
         - condition: Unproductive (same findings repeated or fixes not reflected)
           next: ai_no_fix
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: Healthy (findings decreasing, fixes applied)
+          next: reviewers
+        - condition: Unproductive (same findings repeating)
+          next: supervise
 movements:
   - name: plan
     edit: false
@@ -30,6 +42,8 @@ movements:
       - backend
       - cqrs-es
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -60,6 +74,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -93,6 +109,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -122,6 +140,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -144,6 +164,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -163,6 +185,8 @@ movements:
         knowledge:
           - cqrs-es
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -182,6 +206,8 @@ movements:
         persona: frontend-reviewer
         policy: review
         knowledge: frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -201,6 +227,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -221,6 +249,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -252,6 +282,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -273,6 +305,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -305,6 +339,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/dual-mini.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 20
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix_both
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: fix_both
+        - condition: unproductive (same findings repeating)
+          next: supervise_fix
 movements:
   - name: plan
     edit: false
@@ -17,6 +30,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -47,6 +62,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -81,6 +98,8 @@ movements:
         policy:
           - review
           - ai-antipattern
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -104,6 +123,8 @@ movements:
           - backend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -144,6 +165,8 @@ movements:
           - backend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -169,6 +192,8 @@ movements:
           - backend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -198,6 +223,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -228,6 +255,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/dual-review-fix.yaml

@@ -15,7 +15,7 @@ loop_monitors:
     threshold: 3
     judge:
       persona: supervisor
-      instruction_template: loop-monitor-ai-fix
+      instruction_template: loop-monitor-reviewers-fix
       rules:
         - condition: Healthy (progress being made)
           next: reviewers
@@ -26,6 +26,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -54,6 +56,8 @@ movements:
           - architecture
           - frontend
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -74,6 +78,8 @@ movements:
         persona: frontend-reviewer
         policy: review
         knowledge: frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -94,6 +100,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -115,6 +123,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -147,6 +157,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -169,6 +181,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -201,6 +215,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/dual-review.yaml

@@ -13,6 +13,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -41,6 +43,8 @@ movements:
           - architecture
           - frontend
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -61,6 +65,8 @@ movements:
         persona: frontend-reviewer
         policy: review
         knowledge: frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -81,6 +87,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -102,6 +110,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -127,6 +137,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/dual.yaml

@@ -21,6 +21,18 @@ loop_monitors:
           next: ai_review
         - condition: Unproductive (same findings repeated or fixes not reflected)
           next: ai_no_fix
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: reviewers
+        - condition: unproductive (same findings repeating)
+          next: supervise
 movements:
   - name: plan
     edit: false
@@ -29,6 +41,8 @@ movements:
       - frontend
       - backend
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -58,6 +72,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -91,6 +107,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -119,6 +137,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -141,6 +161,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -160,6 +182,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -179,6 +203,8 @@ movements:
         persona: frontend-reviewer
         policy: review
         knowledge: frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -198,6 +224,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -218,6 +246,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -248,6 +278,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -269,6 +301,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -300,6 +334,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/e2e-test.yaml

@@ -41,6 +41,8 @@ movements:
     knowledge:
       - architecture
       - backend
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -74,6 +76,8 @@ movements:
     knowledge:
       - backend
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -108,6 +112,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -134,6 +140,8 @@ movements:
     knowledge:
       - backend
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -157,6 +165,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -173,6 +183,8 @@ movements:
     policy:
       - review
       - qa
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -199,6 +211,8 @@ movements:
     knowledge:
       - backend
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -220,6 +234,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/frontend-mini.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 20
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix_both
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: fix_both
+        - condition: unproductive (same findings repeating)
+          next: supervise_fix
 movements:
   - name: plan
     edit: false
@@ -16,6 +29,8 @@ movements:
       - frontend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -45,6 +60,8 @@ movements:
       - frontend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -79,6 +96,8 @@ movements:
         policy:
           - review
           - ai-antipattern
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -101,6 +120,8 @@ movements:
           - frontend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -140,6 +161,8 @@ movements:
           - frontend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -164,6 +187,8 @@ movements:
           - frontend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -192,6 +217,8 @@ movements:
       - frontend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -221,6 +248,8 @@ movements:
       - frontend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/frontend-review-fix.yaml

@@ -15,7 +15,7 @@ loop_monitors:
     threshold: 3
     judge:
       persona: supervisor
-      instruction_template: loop-monitor-ai-fix
+      instruction_template: loop-monitor-reviewers-fix
       rules:
         - condition: Healthy (progress being made)
           next: reviewers
@@ -26,6 +26,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -53,6 +55,8 @@ movements:
         knowledge:
           - architecture
           - frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -73,6 +77,8 @@ movements:
         persona: frontend-reviewer
         policy: review
         knowledge: frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -93,6 +99,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -114,6 +122,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -145,6 +155,8 @@ movements:
       - frontend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -167,6 +179,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -198,6 +212,8 @@ movements:
       - frontend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/frontend-review.yaml

@@ -13,6 +13,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -40,6 +42,8 @@ movements:
         knowledge:
           - architecture
           - frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -60,6 +64,8 @@ movements:
         persona: frontend-reviewer
         policy: review
         knowledge: frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -80,6 +86,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -101,6 +109,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -126,6 +136,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/frontend.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 30
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: converging (findings decreasing, fixes applied)
+          next: reviewers
+        - condition: unproductive (same findings repeating)
+          next: supervise
 movements:
   - name: plan
     edit: false
@@ -15,6 +28,8 @@ movements:
     knowledge:
       - frontend
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -43,6 +58,8 @@ movements:
       - frontend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -76,6 +93,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -103,6 +122,8 @@ movements:
       - frontend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -125,6 +146,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -144,6 +167,8 @@ movements:
         knowledge:
           - architecture
           - frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -163,6 +188,8 @@ movements:
         persona: frontend-reviewer
         policy: review
         knowledge: frontend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -182,6 +209,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -202,6 +231,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -231,6 +262,8 @@ movements:
       - frontend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -252,6 +285,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -282,6 +317,8 @@ movements:
       - frontend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/magi.yaml

@@ -2,6 +2,13 @@ name: magi
 description: MAGI Deliberation System - Analyze from 3 perspectives and decide by majority
 piece_config:
   provider_options:
+    claude:
+      allowed_tools:
+        - Read
+        - Glob
+        - Grep
+        - WebSearch
+        - WebFetch
     codex:
       network_access: true
     opencode:
@@ -11,12 +18,6 @@ initial_movement: melchior
 movements:
   - name: melchior
     persona: melchior
-    allowed_tools:
-      - Read
-      - Glob
-      - Grep
-      - WebSearch
-      - WebFetch
     instruction_template: |
       # MAGI System Initiated
 
@@ -47,12 +48,6 @@ movements:
         next: balthasar
   - name: balthasar
     persona: balthasar
-    allowed_tools:
-      - Read
-      - Glob
-      - Grep
-      - WebSearch
-      - WebFetch
     instruction_template: |
       # MAGI System Continuing
 
@@ -87,12 +82,6 @@ movements:
         next: casper
   - name: casper
     persona: casper
-    allowed_tools:
-      - Read
-      - Glob
-      - Grep
-      - WebSearch
-      - WebFetch
     instruction_template: |
       # MAGI System Final Deliberation
 

builtins/en/pieces/research.yaml

@@ -2,6 +2,13 @@ name: research
 description: Research piece - autonomously executes research without asking questions
 piece_config:
   provider_options:
+    claude:
+      allowed_tools:
+        - Read
+        - Glob
+        - Grep
+        - WebSearch
+        - WebFetch
     codex:
       network_access: true
     opencode:
@@ -14,12 +21,6 @@ movements:
     policy: research
     knowledge: research
     instruction: research-plan
-    allowed_tools:
-      - Read
-      - Glob
-      - Grep
-      - WebSearch
-      - WebFetch
     rules:
       - condition: Planning is complete
         next: dig
@@ -30,12 +31,6 @@ movements:
     policy: research
     knowledge: research
     instruction: research-dig
-    allowed_tools:
-      - Read
-      - Glob
-      - Grep
-      - WebSearch
-      - WebFetch
     rules:
       - condition: Research is complete
         next: supervise
@@ -46,12 +41,6 @@ movements:
     policy: research
     knowledge: research
     instruction: research-supervise
-    allowed_tools:
-      - Read
-      - Glob
-      - Grep
-      - WebSearch
-      - WebFetch
     rules:
       - condition: Research results adequately answer the original request
         next: COMPLETE

builtins/en/pieces/review-fix.yaml

@@ -15,7 +15,7 @@ loop_monitors:
     threshold: 3
     judge:
       persona: supervisor
-      instruction_template: loop-monitor-ai-fix
+      instruction_template: loop-monitor-reviewers-fix
       rules:
         - condition: Healthy (progress being made)
           next: reviewers
@@ -26,6 +26,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -55,6 +57,8 @@ movements:
         persona: architecture-reviewer
         policy: review
         knowledge: architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -76,6 +80,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -98,6 +104,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -120,6 +128,8 @@ movements:
         policy:
           - review
           - testing
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -140,6 +150,8 @@ movements:
         edit: false
         persona: requirements-reviewer
         policy: review
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -171,6 +183,8 @@ movements:
     knowledge:
       - architecture
       - security
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -193,6 +207,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -223,6 +239,8 @@ movements:
     knowledge:
       - architecture
       - security
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/review.yaml

@@ -13,6 +13,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -42,6 +44,8 @@ movements:
         persona: architecture-reviewer
         policy: review
         knowledge: architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -63,6 +67,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -85,6 +91,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -107,6 +115,8 @@ movements:
         policy:
           - review
           - testing
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -127,6 +137,8 @@ movements:
         edit: false
         persona: requirements-reviewer
         policy: review
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -153,6 +165,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/takt-default-review-fix.yaml

@@ -15,7 +15,7 @@ loop_monitors:
     threshold: 3
     judge:
       persona: supervisor
-      instruction_template: loop-monitor-ai-fix
+      instruction_template: loop-monitor-reviewers-fix
       rules:
         - condition: Healthy (progress being made)
           next: reviewers
@@ -26,6 +26,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -57,6 +59,8 @@ movements:
         knowledge:
           - architecture
           - takt
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -78,6 +82,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -100,6 +106,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -122,6 +130,8 @@ movements:
         policy:
           - review
           - testing
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -142,6 +152,8 @@ movements:
         edit: false
         persona: requirements-reviewer
         policy: review
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -174,6 +186,8 @@ movements:
       - takt
       - architecture
       - security
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -196,6 +210,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/takt-default-team-leader.yaml

@@ -15,29 +15,31 @@ loop_monitors:
     threshold: 3
     judge:
       persona: supervisor
-      instruction_template: |
+      instruction_template: loop-monitor-ai-fix
-        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
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: Healthy (findings decreasing, fixes applied)
+          next: reviewers
+        - condition: Unproductive (same findings repeating)
+          next: supervise
 movements:
   - name: plan
     edit: false
     persona: planner
     knowledge: architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -70,6 +72,8 @@ movements:
     knowledge:
       - takt
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -108,6 +112,9 @@ movements:
     knowledge:
       - takt
       - architecture
+      - task-decomposition
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -139,7 +146,7 @@ movements:
       - condition: No implementation (report only)
         next: ai_review
       - condition: Cannot proceed, insufficient info
-        next: ai_review
+        next: plan
       - condition: User input required
         next: implement
         requires_user_input: true
@@ -156,6 +163,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -182,6 +191,8 @@ movements:
     knowledge:
       - takt
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -205,6 +216,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -224,6 +237,8 @@ movements:
         knowledge:
           - architecture
           - takt
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -244,6 +259,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -265,6 +282,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -286,6 +305,8 @@ movements:
         policy:
           - review
           - testing
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -305,6 +326,8 @@ movements:
         edit: false
         persona: requirements-reviewer
         policy: review
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -334,6 +357,8 @@ movements:
     knowledge:
       - takt
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -355,6 +380,9 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    knowledge: architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/takt-default.yaml

@@ -33,11 +33,25 @@ loop_monitors:
           next: ai_review
         - condition: Unproductive (no improvement)
           next: reviewers
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: Healthy (findings decreasing, fixes applied)
+          next: reviewers
+        - condition: Unproductive (same findings repeating)
+          next: supervise
 movements:
   - name: plan
     edit: false
     persona: planner
     knowledge: architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -70,6 +84,8 @@ movements:
     knowledge:
       - takt
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -108,6 +124,8 @@ movements:
     knowledge:
       - takt
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -142,6 +160,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -168,6 +188,8 @@ movements:
     knowledge:
       - takt
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -191,6 +213,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -210,6 +234,8 @@ movements:
         knowledge:
           - architecture
           - takt
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -230,6 +256,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -251,6 +279,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -272,6 +302,8 @@ movements:
         policy:
           - review
           - testing
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -291,6 +323,8 @@ movements:
         edit: false
         persona: requirements-reviewer
         policy: review
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -320,6 +354,8 @@ movements:
     knowledge:
       - takt
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -341,6 +377,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/terraform.yaml

@@ -13,6 +13,8 @@ movements:
     edit: false
     persona: planner
     knowledge: terraform-aws
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -38,6 +40,8 @@ movements:
     policy:
       - terraform
     knowledge: terraform-aws
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -77,6 +81,8 @@ movements:
           - review
           - terraform
         knowledge: terraform-aws
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -98,6 +104,8 @@ movements:
         policy:
           - review
           - ai-antipattern
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -122,6 +130,8 @@ movements:
     persona: supervisor
     policy: review
     knowledge: terraform-aws
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -156,6 +166,8 @@ movements:
         policy:
           - terraform
         knowledge: terraform-aws
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -176,6 +188,8 @@ movements:
         policy:
           - terraform
         knowledge: terraform-aws
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -200,6 +214,8 @@ movements:
     policy:
       - terraform
     knowledge: terraform-aws
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -225,6 +241,8 @@ movements:
     policy:
       - terraform
     knowledge: terraform-aws
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/en/pieces/unit-test.yaml

@@ -41,6 +41,8 @@ movements:
     knowledge:
       - architecture
       - backend
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -74,6 +76,8 @@ movements:
     knowledge:
       - backend
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -108,6 +112,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -134,6 +140,8 @@ movements:
     knowledge:
       - backend
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -157,6 +165,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -173,6 +183,8 @@ movements:
     policy:
       - review
       - qa
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -199,6 +211,8 @@ movements:
     knowledge:
       - backend
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -220,6 +234,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/config.yaml

@@ -2,24 +2,35 @@
 # 配置場所: ~/.takt/config.yaml
 
 # =====================================
-# 通常設定（ピース非依存）
+# 通常設定
 # =====================================
 language: ja         # 表示言語: ja | en
-log_level: info      # ログレベル: debug | info | warn | error
+
-provider: claude     # デフォルト実行プロバイダー: claude | codex | opencode | mock
+# デフォルトプロバイダー・モデル
-# model: sonnet      # 省略可。providerに渡すモデル名
+# provider: claude                    # デフォルトプロバイダー: claude | codex | opencode | cursor | copilot | mock
+# model: sonnet                       # デフォルトモデル（プロバイダーにそのまま渡される）
 
 # 実行制御
 # worktree_dir: ~/takt-worktrees   # 共有clone作成先ディレクトリ
-# auto_pr: false                   # worktree実行後に自動PR作成するか
-branch_name_strategy: ai       # ブランチ名生成: romaji | ai
-concurrency: 2               # takt run の同時実行数（1-10）
-# task_poll_interval_ms: 500       # takt run のタスク監視間隔ms（100-5000）
 # prevent_sleep: false             # macOS実行中のスリープ防止（caffeinate）
+# auto_fetch: false                # clone前にfetchして最新化するか
+# base_branch: main                # cloneのベースブランチ（デフォルト: カレントブランチ）
+# concurrency: 1                   # takt run の同時実行タスク数 (1-10)
+# task_poll_interval_ms: 500       # 新規タスク検出のポーリング間隔（ms, 100-5000）
+
+# PR / ブランチ
+# auto_pr: false                   # worktree実行後にPR自動作成
+# draft_pr: false                  # ドラフトPRとして作成
+# branch_name_strategy: romaji     # ブランチ名生成: romaji | ai
+
+# パイプライン実行
+# pipeline:
+#   default_branch_prefix: "takt/"         # パイプラインで作成するブランチのプレフィックス
+#   commit_message_template: "{title}"     # コミットメッセージテンプレート。変数: {title}, {issue}
+#   pr_body_template: "{report}"           # PR本文テンプレート。変数: {issue_body}, {report}, {issue}
 
 # 出力・通知
-# minimal_output: false            # 出力を最小化（CI向け）
+# minimal_output: false            # エージェント詳細出力を抑制
-# verbose: false                   # 詳細ログを有効化
 # notification_sound: true         # 通知音全体のON/OFF
 # notification_sound_events:       # イベント別通知音（未指定はtrue扱い）
 #   iteration_limit: true
@@ -27,74 +38,86 @@ concurrency: 2               # takt run の同時実行数（1-10）
 #   piece_abort: true
 #   run_complete: true
 #   run_abort: true
-# observability:
+# logging:
+#   level: info                    # ログレベル: debug | info | warn | error
+#   trace: true                    # trace.md 実行レポート生成
+#   debug: false                   # debug.log + prompts.jsonl を有効化
 #   provider_events: false         # providerイベントログを記録
+#   usage_events: false            # 使用量イベントログを記録
+
+# アナリティクス
 # analytics:
-#   enabled: true                  # 分析メトリクスの収集を有効化
+#   enabled: true                  # ローカルアナリティクス収集を有効化
-#   events_path: ~/.takt/analytics/events  # 分析イベント保存先
+#   events_path: ~/.takt/analytics/events  # イベントディレクトリのカスタムパス
-#   retention_days: 30             # 分析イベント保持日数
+#   retention_days: 30             # イベントファイルの保持期間（日）
+
+# インタラクティブモード
+# interactive_preview_movements: 3 # インタラクティブモードでのムーブメントプレビュー数 (0-10)
+
+# ペルソナ別プロバイダー・モデル指定
+# persona_providers:
+#   coder:
+#     provider: claude
+#     model: opus
+#   reviewer:
+#     provider: codex
+#     model: gpt-5.2-codex
+
+# プロバイダー固有オプション（最低優先度、ピース/ムーブメントで上書き可能）
+# provider_options:
+#   codex:
+#     network_access: true
+#   claude:
+#     sandbox:
+#       allow_unsandboxed_commands: true
+
+# プロバイダー権限プロファイル
+# provider_profiles:
+#   claude:
+#     default_permission_mode: edit
+#   codex:
+#     default_permission_mode: edit
+
+# ランタイム環境の準備
+# runtime:
+#   prepare: [node, gradle, ./custom-script.sh]
+
+# ピースレベルのオーバーライド
+# piece_overrides:
+#   quality_gates:
+#     - "All tests pass"
+#   quality_gates_edit_only: true
+#   movements:
+#     review:
+#       quality_gates:
+#         - "No security vulnerabilities"
+#   personas:
+#     coder:
+#       quality_gates:
+#         - "Code follows conventions"
 
 # 認証情報（環境変数優先）
 # anthropic_api_key: "sk-ant-..." # Claude APIキー
 # openai_api_key: "sk-..."         # Codex APIキー
+# gemini_api_key: "..."            # Gemini APIキー
+# google_api_key: "..."            # Google APIキー
+# groq_api_key: "..."              # Groq APIキー
+# openrouter_api_key: "..."        # OpenRouter APIキー
 # opencode_api_key: "..."          # OpenCode APIキー
-# codex_cli_path: "/absolute/path/to/codex"  # Codex CLI絶対パス
+# cursor_api_key: "..."            # Cursor APIキー
 
-# パイプライン
+# CLIパス
-# pipeline:
+# codex_cli_path: "/absolute/path/to/codex"    # Codex CLI絶対パス
-#   default_branch_prefix: "takt/"             # pipeline作成ブランチの接頭辞
+# claude_cli_path: "/absolute/path/to/claude"  # Claude Code CLI絶対パス
-#   commit_message_template: "feat: {title} (#{issue})"  # コミット文テンプレート
+# cursor_cli_path: "/absolute/path/to/cursor"  # cursor-agent CLI絶対パス
-#   pr_body_template: |                          # PR本文テンプレート
+# copilot_cli_path: "/absolute/path/to/copilot" # Copilot CLI絶対パス
-#     ## Summary
+# copilot_github_token: "ghp_..."              # Copilot GitHubトークン
-#     {issue_body}
-#     Closes #{issue}
 
 # その他
 # bookmarks_file: ~/.takt/preferences/bookmarks.yaml   # ブックマーク保存先
 
-# =====================================
+# ピース一覧/カテゴリ
-# ピースにも関わる設定（global defaults）
-# =====================================
-# 1) ペルソナ単位でプロバイダー・モデルを切り替える
-# persona_providers:
-#   coder:
-#     provider: codex    # coderペルソナはcodexで実行
-#     model: o3-mini     # 使用モデル（省略可）
-#   reviewer:
-#     provider: claude   # reviewerペルソナはclaudeで実行
-
-# 2) provider 固有オプション
-#    優先順位（provider/model/provider_options 等の piece 対応キー）:
-#    global < piece < project < env
-# provider_options:
-#   codex:
-#     network_access: true      # Codex実行時のネットワークアクセス許可
-#   opencode:
-#     network_access: true      # OpenCode実行時のネットワークアクセス許可
-#   claude:
-#     sandbox:
-#       allow_unsandboxed_commands: false   # trueで対象コマンドを非サンドボックス実行
-#       excluded_commands:
-#         - "npm publish"                  # 非サンドボックス対象コマンド
-
-# 3) movement の権限ポリシー
-# provider_profiles:
-#   codex:
-#     default_permission_mode: full         # 既定権限: readonly | edit | full
-#     movement_permission_overrides:
-#       ai_review: readonly                 # movement単位の上書き
-#   claude:
-#     default_permission_mode: edit
-
-# 4) 実行前のランタイム準備（推奨: 有効化）
-runtime:
-  prepare:
-    - gradle      # Gradleキャッシュ/環境を .runtime 配下に準備
-    - node        # npmキャッシュ/環境を .runtime 配下に準備
-
-# 5) ピース一覧/カテゴリ
 # enable_builtin_pieces: true                             # builtins/{lang}/pieces を有効化
 # disabled_builtins:
 #   - magi                                                # 無効化するビルトインピース名
 # piece_categories_file: ~/.takt/preferences/piece-categories.yaml  # カテゴリ定義ファイル
-# interactive_preview_movements: 3                        # 対話モードのプレビュー件数（0-10）

builtins/ja/facets/instructions/fix.md

@@ -1,10 +1,16 @@
-レビュアーのフィードバックに対応してください。
+Report Directory内のレビューレポートを確認し、指摘事項を修正してください。
-Piece Contextに示されたReport Directory内のレポートを確認し、レビュアーの指摘事項を修正してください。
-必要な根拠はReport Directory内のファイルを一次情報として取得してください。不足情報の補完が必要な場合に限り、Previous Responseや会話履歴を補助的に参照して構いません（Previous Responseは提供されない場合があります）。情報が競合する場合は、Report Directory内のレポートと実際のファイル内容を優先してください。
 
-**重要**: 修正後、ビルドとテストの両方を実行してください。
+**レポート参照方針:**
-- ビルド確認は必須。ビルド（型チェック）を実行し、型エラーがないことを確認
+- Report Directory内の最新レビューレポートを一次情報として参照してください。
-- テスト実行は必須。ビルド成功後、必ずテストを実行して結果を確認
+- 過去イテレーションのレポートは `{ファイル名}.{タイムスタンプ}` 形式で同ディレクトリに保存されています（例: `architect-review.md.20260304T123456Z`）。各レポートについて `{レポート名}.*` パターンで Glob を実行し、タイムスタンプ降順で最大2件まで読み、persists / reopened の傾向を把握してから修正に入ること。
+
+**完了条件（以下をすべて満たすこと）:**
+- 今回受け取った全指摘（new / reopened）を修正したこと
+- 同一 `family_tag` の潜在箇所を同時に修正したこと（部分修正で再発させない）
+- `family_tag` ごとに最低1件の再発防止テストを追加したこと（config契約/境界チェック系は必須）
+- 複数レビュアーから同一 `family_tag` の指摘が届いている場合は1件に統合して対応したこと
+
+**重要**: 修正後、ビルド（型チェック）とテストを必ず実行してください。
 
 **必須出力（見出しを含める）**
 ## 作業結果
@@ -15,5 +21,11 @@ Piece Contextに示されたReport Directory内のレポートを確認し、レ
 - {ビルド実行結果}
 ## テスト結果
 - {テスト実行コマンドと結果}
+## 収束ゲート
+| 指標 | 件数 |
+|------|------|
+| new（今回修正） | {N} |
+| reopened（再発修正） | {N} |
+| persists（前回から継続、今回未着手） | {N} |
 ## 証拠
 - {確認したファイル/検索/差分/ログの要点を列挙}

builtins/ja/facets/instructions/loop-monitor-reviewers-fix.md

@@ -0,0 +1,9 @@
+reviewers → fix のループが {cycle_count} 回繰り返されました。
+
+Report Directory 内の最新レビューレポートを確認し、
+このループが健全（収束傾向）か非生産的（発散・振動）かを判断してください。
+
+**判断基準:**
+- 各サイクルで new / reopened の指摘件数が減少しているか
+- 同じ family_tag の指摘が繰り返されていないか（persists が増えていないか）
+- 修正が実際にコードに反映されているか

builtins/ja/facets/instructions/review-arch.md

@@ -12,6 +12,12 @@ AI特有の問題はレビューしないでください（ai_reviewムーブメ
 - 呼び出しチェーン検証
 - 契約文字列（ファイル名・設定キー名）のハードコード散在
 
+
+**設計判断の参照:**
+{report:coder-decisions.md} を確認し、記録された設計判断を把握してください。
+- 記録された意図的な判断は FP として指摘しない
+- ただし設計判断自体の妥当性も評価し、問題がある場合は指摘する
+
 **前回指摘の追跡（必須）:**
 - まず「Previous Response」から前回の open findings を抽出する
 - 各 finding に `finding_id` を付け、今回の状態を `new / persists / resolved` で判定する

builtins/ja/facets/instructions/review-cqrs-es.md

@@ -11,6 +11,12 @@ CQRS（コマンドクエリ責務分離）とEvent Sourcing（イベントソ
 **注意**: このプロジェクトがCQRS+ESパターンを使用していない場合は、
 一般的なドメイン設計の観点からレビューしてください。
 
+
+**設計判断の参照:**
+{report:coder-decisions.md} を確認し、記録された設計判断を把握してください。
+- 記録された意図的な判断は FP として指摘しない
+- ただし設計判断自体の妥当性も評価し、問題がある場合は指摘する
+
 ## 判定手順
 
 1. 変更差分を確認し、CQRS・イベントソーシングの観点に基づいて問題を検出する

builtins/ja/facets/instructions/review-frontend.md

@@ -11,6 +11,12 @@
 **注意**: このプロジェクトがフロントエンドを含まない場合は、
 問題なしとして次に進んでください。
 
+
+**設計判断の参照:**
+{report:coder-decisions.md} を確認し、記録された設計判断を把握してください。
+- 記録された意図的な判断は FP として指摘しない
+- ただし設計判断自体の妥当性も評価し、問題がある場合は指摘する
+
 ## 判定手順
 
 1. 変更差分を確認し、フロントエンド開発の観点に基づいて問題を検出する

builtins/ja/facets/instructions/review-qa.md

@@ -7,6 +7,12 @@
 - ログとモニタリング
 - 保守性
 
+
+**設計判断の参照:**
+{report:coder-decisions.md} を確認し、記録された設計判断を把握してください。
+- 記録された意図的な判断は FP として指摘しない
+- ただし設計判断自体の妥当性も評価し、問題がある場合は指摘する
+
 **前回指摘の追跡（必須）:**
 - まず「Previous Response」から前回の open findings を抽出する
 - 各 finding に `finding_id` を付け、今回の状態を `new / persists / resolved` で判定する

builtins/ja/facets/instructions/review-requirements.md

@@ -6,6 +6,12 @@
 - 要求にない変更（スコープクリープ）が紛れていないか
 - 部分実装や未実装がないか
 
+
+**設計判断の参照:**
+{report:coder-decisions.md} を確認し、記録された設計判断を把握してください。
+- 記録された意図的な判断は FP として指摘しない
+- ただし設計判断自体の妥当性も評価し、問題がある場合は指摘する
+
 **前回指摘の追跡（必須）:**
 - まず「Previous Response」から前回の open findings を抽出する
 - 各 finding に `finding_id` を付け、今回の状態を `new / persists / resolved` で判定する

builtins/ja/facets/instructions/review-security.md

@@ -4,6 +4,12 @@
 - データ露出リスク
 - 暗号化の弱点
 
+
+**設計判断の参照:**
+{report:coder-decisions.md} を確認し、記録された設計判断を把握してください。
+- 記録された意図的な判断は FP として指摘しない
+- ただし設計判断自体の妥当性も評価し、問題がある場合は指摘する
+
 ## 判定手順
 
 1. 変更差分を確認し、セキュリティの観点に基づいて問題を検出する

builtins/ja/facets/instructions/review-terraform.md

@@ -11,6 +11,12 @@ AI特有の問題はレビューしないでください（ai_reviewムーブメ
 - コストトレードオフの文書化
 - 未使用の variable / output / data source
 
+
+**設計判断の参照:**
+{report:coder-decisions.md} を確認し、記録された設計判断を把握してください。
+- 記録された意図的な判断は FP として指摘しない
+- ただし設計判断自体の妥当性も評価し、問題がある場合は指摘する
+
 **前回指摘の追跡（必須）:**
 - まず「Previous Response」から前回の open findings を抽出する
 - 各 finding に `finding_id` を付け、今回の状態を `new / persists / resolved` で判定する

builtins/ja/facets/instructions/review-test.md

@@ -7,6 +7,12 @@
 - 過不足（不要なテスト、足りないケース）
 - モック・フィクスチャの適切さ
 
+
+**設計判断の参照:**
+{report:coder-decisions.md} を確認し、記録された設計判断を把握してください。
+- 記録された意図的な判断は FP として指摘しない
+- ただし設計判断自体の妥当性も評価し、問題がある場合は指摘する
+
 ## 判定手順
 
 1. Report Directory内のテスト計画・テストスコープに関するレポートと実装されたテストを突合する

builtins/ja/facets/instructions/supervise.md

@@ -1,9 +1,11 @@
 テスト実行、ビルド確認、最終承認を行ってください。
 
 **ピース全体の確認:**
-1. 計画と実装結果が一致しているか
+1. レポートディレクトリ内の全レポートを確認し、ピース全体の整合性をチェックする
-2. 各レビュームーブメントの指摘が対応されているか
+   - 計画と実装結果が一致しているか
-3. タスク指示書の各要件が達成されているか
+   - 各レビュームーブメントの指摘が適切に対応されているか
+   - タスクの本来の目的が達成されているか
+2. タスク指示書の各要件が達成されているか
    - タスク指示書から要件を1つずつ抽出する
    - 各要件について、実装されたコード（ファイル:行）を特定する
    - コードが要件を満たしていることを実際に確認する（ファイルを読む、テストを実行する）

builtins/ja/facets/instructions/team-leader-implement.md

@@ -1,17 +1,19 @@
-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。
+実装タスクを分析し、分解が適切なら複数パートに分けて並列実行してください。
 
 **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
+1. 分解の可否を判断する
-   - 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
+   - 変更対象ファイルを特定し、ファイル間の依存関係を確認する
-   - 実際のコードベースを確認して不明点を補完する
+   - 横断的関心事（共有型・ID・イベント）がある場合は分解せず1パートで実装する
+   - 変更ファイル数が少ない場合、リファクタ・リネーム系の場合も1パートで実装する
 
-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
+2. 分解する場合: 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
+   - テストファイルと実装ファイルは同じパートにまとめる
 
 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：

builtins/ja/facets/knowledge/task-decomposition.md

@@ -0,0 +1,66 @@
+# タスク分解知識
+
+## 分解の可否判断
+
+タスクを複数パートに分解する前に、分解が適切かを判断する。分解が不適切なケースでは1パートで実装する方が効率的。
+
+| 基準 | 判定 |
+|------|------|
+| 変更ファイルが明確にレイヤー分離できる | 分解可 |
+| 共有する型・IDが複数パートをまたぐ | 1パートで実装 |
+| 広範囲のリネーム・リファクタ | 1パートで実装 |
+| 変更ファイル数が5未満 | 1パートで実装 |
+| 同一ファイルを複数パートが触る必要がある | 1パートで実装 |
+
+### 横断的関心事の検出
+
+以下に該当する場合、独立パートでは整合性を保てない。1パートにまとめる。
+
+- 新しいID・キー・型を生成し、別のモジュールで消費するフロー
+- イベント発火側と受信側の両方を変更する
+- 既存インターフェースのシグネチャを変更し、全呼び出し元を更新する
+
+## ファイル排他の原則
+
+複数パートに分解する場合、各パートの担当ファイルは完全に排他的でなければならない。
+
+| 基準 | 判定 |
+|------|------|
+| 同一ファイルを複数パートが編集 | REJECT（コンフリクトの原因） |
+| 型定義と利用側が別パート | 型定義側のパートにまとめる |
+| テストファイルと実装ファイルが別パート | 同じパートにまとめる |
+
+### グループ化の優先順位
+
+1. **依存方向で分ける** — 依存元と依存先は同じパートに
+2. **レイヤーで分ける** — ドメイン層 / インフラ層 / API層
+3. **機能で分ける** — 独立した機能単位
+
+## 失敗パターン
+
+### パート重複
+
+2つのパートが同じファイルや同じ機能を担当すると、サブエージェントが互いの変更を上書きし、レビューで繰り返しREJECTされる。
+
+```
+// NG: part-2 と part-3 が同じファイルを担当
+part-2: taskInstructionActions.ts — instruct機能の確認ダイアログ
+part-3: taskInstructionActions.ts — requeue機能の確認ダイアログ
+
+// OK: 1パートにまとめる
+part-1: taskInstructionActions.ts — instruct/requeue両方の確認ダイアログ
+```
+
+### 共有契約の不整合
+
+パートAが生成するIDをパートBが消費する設計では、両パートが独立に実装するため、ID名・型・受け渡し方法に不整合が生じる。
+
+```
+// NG: 独立パートで共有契約
+part-1: phaseExecutionId を生成
+part-2: phaseExecutionId を受け取って使う
+→ part-1 は string、part-2 は number を期待 → 統合エラー
+
+// OK: 1パートで一貫実装
+part-1: phaseExecutionId の生成から消費まで一貫して実装
+```

builtins/ja/facets/output-contracts/ai-review.md

@@ -15,22 +15,27 @@
 | スコープ | ✅ | - |
 
 ## 今回の指摘（new）
-| # | finding_id | カテゴリ | 場所 | 問題 | 修正案 |
+| # | finding_id | family_tag | カテゴリ | 場所 | 問題 | 修正案 |
-|---|------------|---------|------|------|--------|
+|---|------------|------------|---------|------|------|--------|
-| 1 | AI-NEW-src-file-L23 | 幻覚API | `src/file.ts:23` | 存在しないメソッド | 実在APIへ置換 |
+| 1 | AI-NEW-src-file-L23 | hallucination | 幻覚API | `src/file.ts:23` | 存在しないメソッド | 実在APIへ置換 |
 
 ## 継続指摘（persists）
-| # | finding_id | 前回根拠 | 今回根拠 | 問題 | 修正案 |
+| # | finding_id | family_tag | 前回根拠 | 今回根拠 | 問題 | 修正案 |
-|---|------------|----------|----------|------|--------|
+|---|------------|------------|----------|----------|------|--------|
-| 1 | AI-PERSIST-src-file-L42 | `src/file.ts:42` | `src/file.ts:42` | 未解消 | 既存修正方針を適用 |
+| 1 | AI-PERSIST-src-file-L42 | hallucination | `src/file.ts:42` | `src/file.ts:42` | 未解消 | 既存修正方針を適用 |
 
 ## 解消済み（resolved）
 | finding_id | 解消根拠 |
 |------------|----------|
 | AI-RESOLVED-src-file-L10 | `src/file.ts:10` に該当問題なし |
 
+## 再開指摘（reopened）
+| # | finding_id | family_tag | 解消根拠（前回） | 再発根拠 | 問題 | 修正案 |
+|---|------------|------------|----------------|---------|------|--------|
+| 1 | AI-REOPENED-src-file-L55 | hallucination | `前回: src/file.ts:10 で修正済み` | `src/file.ts:55 で再発` | 問題の説明 | 修正方法 |
+
 ## REJECT判定条件
-- `new` または `persists` が1件以上ある場合のみ REJECT 可
+- `new`、`persists`、または `reopened` が1件以上ある場合のみ REJECT 可
 - `finding_id` なしの指摘は無効
 ```
 

builtins/ja/facets/output-contracts/architecture-review.md

@@ -15,24 +15,29 @@
 - [x] 呼び出しチェーン検証
 
 ## 今回の指摘（new）
-| # | finding_id | スコープ | 場所 | 問題 | 修正案 |
+| # | finding_id | family_tag | スコープ | 場所 | 問題 | 修正案 |
-|---|------------|---------|------|------|--------|
+|---|------------|------------|---------|------|------|--------|
-| 1 | ARCH-NEW-src-file-L42 | スコープ内 | `src/file.ts:42` | 問題の説明 | 修正方法 |
+| 1 | ARCH-NEW-src-file-L42 | design-violation | スコープ内 | `src/file.ts:42` | 問題の説明 | 修正方法 |
 
 スコープ: 「スコープ内」（今回修正可能）/ 「スコープ外」（既存問題・非ブロッキング）
 
 ## 継続指摘（persists）
-| # | finding_id | 前回根拠 | 今回根拠 | 問題 | 修正案 |
+| # | finding_id | family_tag | 前回根拠 | 今回根拠 | 問題 | 修正案 |
-|---|------------|----------|----------|------|--------|
+|---|------------|------------|----------|----------|------|--------|
-| 1 | ARCH-PERSIST-src-file-L77 | `src/file.ts:77` | `src/file.ts:77` | 未解消 | 既存修正方針を適用 |
+| 1 | ARCH-PERSIST-src-file-L77 | design-violation | `src/file.ts:77` | `src/file.ts:77` | 未解消 | 既存修正方針を適用 |
 
 ## 解消済み（resolved）
 | finding_id | 解消根拠 |
 |------------|----------|
 | ARCH-RESOLVED-src-file-L10 | `src/file.ts:10` は規約を満たす |
 
+## 再開指摘（reopened）
+| # | finding_id | family_tag | 解消根拠（前回） | 再発根拠 | 問題 | 修正案 |
+|---|------------|------------|----------------|---------|------|--------|
+| 1 | ARCH-REOPENED-src-file-L55 | design-violation | `前回: src/file.ts:10 で修正済み` | `src/file.ts:55 で再発` | 問題の説明 | 修正方法 |
+
 ## REJECT判定条件
-- `new` または `persists` が1件以上ある場合のみ REJECT 可
+- `new`、`persists`、または `reopened` が1件以上ある場合のみ REJECT 可
 - `finding_id` なしの指摘は無効
 ```
 

builtins/ja/facets/output-contracts/cqrs-es-review.md

@@ -15,13 +15,33 @@
 | プロジェクション | ✅ | - |
 | 結果整合性 | ✅ | - |
 
-## 問題点（REJECTの場合）
+## 今回の指摘（new）
-| # | スコープ | 場所 | 問題 | 修正案 |
+| # | finding_id | family_tag | スコープ | 場所 | 問題 | 修正案 |
-|---|---------|------|------|--------|
+|---|------------|------------|---------|------|------|--------|
-| 1 | スコープ内 | `src/file.ts:42` | 問題の説明 | 修正方法 |
+| 1 | CQRS-NEW-src-file-L42 | cqrs-violation | スコープ内 | `src/file.ts:42` | 問題の説明 | 修正方法 |
 
 スコープ: 「スコープ内」（今回修正可能）/ 「スコープ外」（既存問題・非ブロッキング）
 
-## 既存問題（参考・非ブロッキング）
+## 継続指摘（persists）
-- {既存問題の記録。今回の変更と無関係な問題}
+| # | finding_id | family_tag | 前回根拠 | 今回根拠 | 問題 | 修正案 |
+|---|------------|------------|----------|----------|------|--------|
+| 1 | CQRS-PERSIST-src-file-L77 | cqrs-violation | `src/file.ts:77` | `src/file.ts:77` | 未解消 | 既存修正方針を適用 |
+
+## 解消済み（resolved）
+| finding_id | 解消根拠 |
+|------------|----------|
+| CQRS-RESOLVED-src-file-L10 | `src/file.ts:10` は規約を満たす |
+
+## 再開指摘（reopened）
+| # | finding_id | family_tag | 解消根拠（前回） | 再発根拠 | 問題 | 修正案 |
+|---|------------|------------|----------------|---------|------|--------|
+| 1 | CQRS-REOPENED-src-file-L55 | cqrs-violation | `前回: src/file.ts:10 で修正済み` | `src/file.ts:55 で再発` | 問題の説明 | 修正方法 |
+
+## REJECT判定条件
+- `new`、`persists`、または `reopened` が1件以上ある場合のみ REJECT 可
+- `finding_id` なしの指摘は無効
 ```
+
+**認知負荷軽減ルール:**
+- APPROVE → サマリーのみ（5行以内）
+- REJECT → 該当指摘のみ表で記載（30行以内）

builtins/ja/facets/output-contracts/frontend-review.md

@@ -15,8 +15,31 @@
 | アクセシビリティ | ✅ | - |
 | 型安全性 | ✅ | - |
 
-## 問題点（REJECTの場合）
+## 今回の指摘（new）
-| # | 場所 | 問題 | 修正案 |
+| # | finding_id | family_tag | 場所 | 問題 | 修正案 |
-|---|------|------|--------|
+|---|------------|------------|------|------|--------|
-| 1 | `src/file.tsx:42` | 問題の説明 | 修正方法 |
+| 1 | FE-NEW-src-file-L42 | component-design | `src/file.tsx:42` | 問題の説明 | 修正方法 |
+
+## 継続指摘（persists）
+| # | finding_id | family_tag | 前回根拠 | 今回根拠 | 問題 | 修正案 |
+|---|------------|------------|----------|----------|------|--------|
+| 1 | FE-PERSIST-src-file-L77 | component-design | `src/file.tsx:77` | `src/file.tsx:77` | 未解消 | 既存修正方針を適用 |
+
+## 解消済み（resolved）
+| finding_id | 解消根拠 |
+|------------|----------|
+| FE-RESOLVED-src-file-L10 | `src/file.tsx:10` は規約を満たす |
+
+## 再開指摘（reopened）
+| # | finding_id | family_tag | 解消根拠（前回） | 再発根拠 | 問題 | 修正案 |
+|---|------------|------------|----------------|---------|------|--------|
+| 1 | FE-REOPENED-src-file-L55 | component-design | `前回: src/file.tsx:10 で修正済み` | `src/file.tsx:55 で再発` | 問題の説明 | 修正方法 |
+
+## REJECT判定条件
+- `new`、`persists`、または `reopened` が1件以上ある場合のみ REJECT 可
+- `finding_id` なしの指摘は無効
 ```
+
+**認知負荷軽減ルール:**
+- APPROVE → サマリーのみ（5行以内）
+- REJECT → 該当指摘のみ表で記載（30行以内）

builtins/ja/facets/output-contracts/qa-review.md

@@ -16,21 +16,26 @@
 | 保守性 | ✅ | - |
 
 ## 今回の指摘（new）
-| # | finding_id | カテゴリ | 場所 | 問題 | 修正案 |
+| # | finding_id | family_tag | カテゴリ | 場所 | 問題 | 修正案 |
-|---|------------|---------|------|------|--------|
+|---|------------|------------|---------|------|------|--------|
-| 1 | QA-NEW-src-test-L42 | テスト | `src/test.ts:42` | 異常系テスト不足 | 失敗系ケースを追加 |
+| 1 | QA-NEW-src-test-L42 | test-coverage | テスト | `src/test.ts:42` | 異常系テスト不足 | 失敗系ケースを追加 |
 
 ## 継続指摘（persists）
-| # | finding_id | 前回根拠 | 今回根拠 | 問題 | 修正案 |
+| # | finding_id | family_tag | 前回根拠 | 今回根拠 | 問題 | 修正案 |
-|---|------------|----------|----------|------|--------|
+|---|------------|------------|----------|----------|------|--------|
-| 1 | QA-PERSIST-src-test-L77 | `src/test.ts:77` | `src/test.ts:77` | 不安定なまま | アサーションとセットアップを安定化 |
+| 1 | QA-PERSIST-src-test-L77 | test-coverage | `src/test.ts:77` | `src/test.ts:77` | 不安定なまま | アサーションとセットアップを安定化 |
 
 ## 解消済み（resolved）
 | finding_id | 解消根拠 |
 |------------|----------|
 | QA-RESOLVED-src-test-L10 | `src/test.ts:10` で異常系が網羅済み |
 
+## 再開指摘（reopened）
+| # | finding_id | family_tag | 解消根拠（前回） | 再発根拠 | 問題 | 修正案 |
+|---|------------|------------|----------------|---------|------|--------|
+| 1 | QA-REOPENED-src-test-L55 | test-coverage | `前回: src/test.ts:10 で修正済み` | `src/test.ts:55 で再発` | 問題の説明 | 修正方法 |
+
 ## REJECT判定条件
-- `new` または `persists` が1件以上ある場合のみ REJECT 可
+- `new`、`persists`、または `reopened` が1件以上ある場合のみ REJECT 可
 - `finding_id` なしの指摘は無効
 ```

builtins/ja/facets/output-contracts/requirements-review.md

@@ -20,22 +20,27 @@
 | 1 | {要求にない変更} | `src/file.ts` | 妥当/不要 |
 
 ## 今回の指摘（new）
-| # | finding_id | カテゴリ | 場所 | 問題 | 修正案 |
+| # | finding_id | family_tag | カテゴリ | 場所 | 問題 | 修正案 |
-|---|------------|---------|------|------|--------|
+|---|------------|------------|---------|------|------|--------|
-| 1 | REQ-NEW-src-file-L42 | 未実装 | `src/file.ts:42` | 問題の説明 | 修正方法 |
+| 1 | REQ-NEW-src-file-L42 | req-gap | 未実装 | `src/file.ts:42` | 問題の説明 | 修正方法 |
 
 ## 継続指摘（persists）
-| # | finding_id | 前回根拠 | 今回根拠 | 問題 | 修正案 |
+| # | finding_id | family_tag | 前回根拠 | 今回根拠 | 問題 | 修正案 |
-|---|------------|----------|----------|------|--------|
+|---|------------|------------|----------|----------|------|--------|
-| 1 | REQ-PERSIST-src-file-L77 | `file:line` | `file:line` | 未解消 | 修正方法 |
+| 1 | REQ-PERSIST-src-file-L77 | req-gap | `file:line` | `file:line` | 未解消 | 修正方法 |
 
 ## 解消済み（resolved）
 | finding_id | 解消根拠 |
 |------------|----------|
 | REQ-RESOLVED-src-file-L10 | `file:line` は要件を充足 |
 
+## 再開指摘（reopened）
+| # | finding_id | family_tag | 解消根拠（前回） | 再発根拠 | 問題 | 修正案 |
+|---|------------|------------|----------------|---------|------|--------|
+| 1 | REQ-REOPENED-src-file-L55 | req-gap | `前回: file:line で修正済み` | `file:line で再発` | 問題の説明 | 修正方法 |
+
 ## REJECT判定条件
-- `new` または `persists` が1件以上ある場合のみ REJECT 可
+- `new`、`persists`、または `reopened` が1件以上ある場合のみ REJECT 可
 - `finding_id` なしの指摘は無効
 ```
 

builtins/ja/facets/output-contracts/security-review.md

@@ -14,25 +14,30 @@
 | 依存関係 | ✅ | - |
 
 ## 今回の指摘（new）
-| # | finding_id | 重大度 | 種類 | 場所 | 問題 | 修正案 |
+| # | finding_id | family_tag | 重大度 | 種類 | 場所 | 問題 | 修正案 |
-|---|------------|--------|------|------|------|--------|
+|---|------------|------------|--------|------|------|------|--------|
-| 1 | SEC-NEW-src-db-L42 | High | SQLi | `src/db.ts:42` | 生SQL文字列 | パラメータ化クエリを使用 |
+| 1 | SEC-NEW-src-db-L42 | injection-risk | High | SQLi | `src/db.ts:42` | 生SQL文字列 | パラメータ化クエリを使用 |
 
 ## 継続指摘（persists）
-| # | finding_id | 前回根拠 | 今回根拠 | 問題 | 修正案 |
+| # | finding_id | family_tag | 前回根拠 | 今回根拠 | 問題 | 修正案 |
-|---|------------|----------|----------|------|--------|
+|---|------------|------------|----------|----------|------|--------|
-| 1 | SEC-PERSIST-src-auth-L18 | `src/auth.ts:18` | `src/auth.ts:18` | 未解消 | バリデーションを強化 |
+| 1 | SEC-PERSIST-src-auth-L18 | injection-risk | `src/auth.ts:18` | `src/auth.ts:18` | 未解消 | バリデーションを強化 |
 
 ## 解消済み（resolved）
 | finding_id | 解消根拠 |
 |------------|----------|
 | SEC-RESOLVED-src-db-L10 | `src/db.ts:10` はバインド変数化済み |
 
+## 再開指摘（reopened）
+| # | finding_id | family_tag | 解消根拠（前回） | 再発根拠 | 問題 | 修正案 |
+|---|------------|------------|----------------|---------|------|--------|
+| 1 | SEC-REOPENED-src-auth-L55 | injection-risk | `前回: src/auth.ts:20 で修正済み` | `src/auth.ts:55 で再発` | 問題の説明 | 修正方法 |
+
 ## 警告（非ブロッキング）
 - {セキュリティに関する推奨事項}
 
 ## REJECT判定条件
-- `new` または `persists` が1件以上ある場合のみ REJECT 可
+- `new`、`persists`、または `reopened` が1件以上ある場合のみ REJECT 可
 - `finding_id` なしの指摘は無効
 ```
 

builtins/ja/facets/output-contracts/terraform-review.md

@@ -16,24 +16,29 @@
 - [x] コストトレードオフ文書化
 
 ## 今回の指摘（new）
-| # | finding_id | スコープ | 場所 | 問題 | 修正案 |
+| # | finding_id | family_tag | スコープ | 場所 | 問題 | 修正案 |
-|---|------------|---------|------|------|--------|
+|---|------------|------------|---------|------|------|--------|
-| 1 | TF-NEW-file-L42 | スコープ内 | `modules/example/main.tf:42` | 問題の説明 | 修正方法 |
+| 1 | TF-NEW-file-L42 | tf-convention | スコープ内 | `modules/example/main.tf:42` | 問題の説明 | 修正方法 |
 
 スコープ: 「スコープ内」（今回修正可能）/ 「スコープ外」（既存問題・非ブロッキング）
 
 ## 継続指摘（persists）
-| # | finding_id | 前回根拠 | 今回根拠 | 問題 | 修正案 |
+| # | finding_id | family_tag | 前回根拠 | 今回根拠 | 問題 | 修正案 |
-|---|------------|----------|----------|------|--------|
+|---|------------|------------|----------|----------|------|--------|
-| 1 | TF-PERSIST-file-L77 | `file.tf:77` | `file.tf:77` | 未解消 | 既存修正方針を適用 |
+| 1 | TF-PERSIST-file-L77 | tf-convention | `file.tf:77` | `file.tf:77` | 未解消 | 既存修正方針を適用 |
 
 ## 解消済み（resolved）
 | finding_id | 解消根拠 |
 |------------|----------|
 | TF-RESOLVED-file-L10 | `file.tf:10` は規約を満たす |
 
+## 再開指摘（reopened）
+| # | finding_id | family_tag | 解消根拠（前回） | 再発根拠 | 問題 | 修正案 |
+|---|------------|------------|----------------|---------|------|--------|
+| 1 | TF-REOPENED-file-L55 | tf-convention | `前回: file.tf:10 で修正済み` | `file.tf:55 で再発` | 問題の説明 | 修正方法 |
+
 ## REJECT判定条件
-- `new` または `persists` が1件以上ある場合のみ REJECT 可
+- `new`、`persists`、または `reopened` が1件以上ある場合のみ REJECT 可
 - `finding_id` なしの指摘は無効
 ```
 

builtins/ja/facets/output-contracts/testing-review.md

@@ -17,22 +17,27 @@
 | テスト戦略（ユニット/統合/E2E） | ✅ | - |
 
 ## 今回の指摘（new）
-| # | finding_id | カテゴリ | 場所 | 問題 | 修正案 |
+| # | finding_id | family_tag | カテゴリ | 場所 | 問題 | 修正案 |
-|---|------------|---------|------|------|--------|
+|---|------------|------------|---------|------|------|--------|
-| 1 | TEST-NEW-src-test-L42 | カバレッジ | `src/test.ts:42` | 問題の説明 | 修正方法 |
+| 1 | TEST-NEW-src-test-L42 | test-structure | カバレッジ | `src/test.ts:42` | 問題の説明 | 修正方法 |
 
 ## 継続指摘（persists）
-| # | finding_id | 前回根拠 | 今回根拠 | 問題 | 修正案 |
+| # | finding_id | family_tag | 前回根拠 | 今回根拠 | 問題 | 修正案 |
-|---|------------|----------|----------|------|--------|
+|---|------------|------------|----------|----------|------|--------|
-| 1 | TEST-PERSIST-src-test-L77 | `src/test.ts:77` | `src/test.ts:77` | 未解消 | 修正方法 |
+| 1 | TEST-PERSIST-src-test-L77 | test-structure | `src/test.ts:77` | `src/test.ts:77` | 未解消 | 修正方法 |
 
 ## 解消済み（resolved）
 | finding_id | 解消根拠 |
 |------------|----------|
 | TEST-RESOLVED-src-test-L10 | `src/test.ts:10` でカバレッジ充足 |
 
+## 再開指摘（reopened）
+| # | finding_id | family_tag | 解消根拠（前回） | 再発根拠 | 問題 | 修正案 |
+|---|------------|------------|----------------|---------|------|--------|
+| 1 | TEST-REOPENED-src-test-L55 | test-structure | `前回: src/test.ts:10 で修正済み` | `src/test.ts:55 で再発` | 問題の説明 | 修正方法 |
+
 ## REJECT判定条件
-- `new` または `persists` が1件以上ある場合のみ REJECT 可
+- `new`、`persists`、または `reopened` が1件以上ある場合のみ REJECT 可
 - `finding_id` なしの指摘は無効
 ```
 

builtins/ja/facets/personas/supervisor.md

@@ -79,31 +79,6 @@
 | 本番 Ready | モック・スタブ・TODO が残っていないか |
 | 動作 | 実際に期待通り動くか |
 
-### 後方互換コードの検出
-
-明示的な指示がない限り、後方互換コードは不要。以下を見つけたら REJECT。
-
-- 未使用の re-export、`_var` リネーム、`// removed` コメント
-- フォールバック、古い API 維持、移行期コード
-- 「念のため」残されたレガシー対応
-
-### その場しのぎの検出
-
-以下が残っていたら REJECT。
-
-| パターン | 例 |
-|---------|-----|
-| TODO/FIXME | `// TODO: implement later` |
-| コメントアウト | 消すべきコードが残っている |
-| ハードコード | 本来設定値であるべきものが直書き |
-| モックデータ | 本番で使えないダミーデータ |
-| console.log | デバッグ出力の消し忘れ |
-| スキップされたテスト | `@Disabled`、`.skip()` |
-
-### ボーイスカウトルール
-
-「機能的に無害」は免罪符ではない。修正コストがほぼゼロの指摘を「非ブロッキング」「次回タスク」に分類することは妥協である。レビュアーが発見し、数分以内に修正できる問題は今回のタスクで修正させる。
-
 ### スコープクリープの検出（削除は最重要チェック）
 
 ファイルの**削除**と既存機能の**除去**はスコープクリープの最も危険な形態。
@@ -119,10 +94,3 @@
 - 「UI修正」タスクでバックエンドのドメインモデルが構造変更されている
 - 「表示変更」タスクでビジネスロジックのフローが書き換えられている
 
-### ピース全体の見直し
-
-レポートディレクトリ内の全レポートを確認し、ピース全体の整合性をチェックする。
-
-- 計画と実装結果が一致しているか
-- 各レビュームーブメントの指摘が適切に対応されているか
-- タスクの本来の目的が達成されているか

builtins/ja/pieces/backend-cqrs-mini.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 20
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix_both
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: 健全（指摘数が減少、修正が反映されている）
+          next: fix_both
+        - condition: 非生産的（同じ指摘が繰り返される）
+          next: supervise_fix
 movements:
   - name: plan
     edit: false
@@ -17,6 +30,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -47,6 +62,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -81,6 +98,8 @@ movements:
         policy:
           - review
           - ai-antipattern
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -104,6 +123,8 @@ movements:
           - cqrs-es
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -144,6 +165,8 @@ movements:
           - cqrs-es
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -169,6 +192,8 @@ movements:
           - cqrs-es
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -198,6 +223,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -228,6 +255,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/pieces/backend-cqrs-review-fix.yaml

@@ -15,7 +15,7 @@ loop_monitors:
     threshold: 3
     judge:
       persona: supervisor
-      instruction_template: loop-monitor-ai-fix
+      instruction_template: loop-monitor-reviewers-fix
       rules:
         - condition: 健全（進捗あり）
           next: reviewers
@@ -26,6 +26,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -53,6 +55,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -75,6 +79,8 @@ movements:
         knowledge:
           - cqrs-es
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -95,6 +101,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -116,6 +124,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -148,6 +158,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -170,6 +182,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -202,6 +216,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/pieces/backend-cqrs-review.yaml

@@ -13,6 +13,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -40,6 +42,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -62,6 +66,8 @@ movements:
         knowledge:
           - cqrs-es
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -82,6 +88,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -103,6 +111,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -128,6 +138,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/pieces/backend-cqrs.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 30
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: 健全（指摘数が減少、修正が反映されている）
+          next: reviewers
+        - condition: 非生産的（同じ指摘が繰り返される）
+          next: supervise
 movements:
   - name: plan
     edit: false
@@ -16,6 +29,8 @@ movements:
       - backend
       - cqrs-es
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -45,6 +60,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -78,6 +95,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -106,6 +125,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -128,6 +149,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -147,6 +170,8 @@ movements:
         knowledge:
           - cqrs-es
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -166,6 +191,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -186,6 +213,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -216,6 +245,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -237,6 +268,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -268,6 +301,8 @@ movements:
       - cqrs-es
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/pieces/backend-mini.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 20
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix_both
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: 健全（指摘数が減少、修正が反映されている）
+          next: fix_both
+        - condition: 非生産的（同じ指摘が繰り返される）
+          next: supervise_fix
 movements:
   - name: plan
     edit: false
@@ -16,6 +29,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -45,6 +60,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -79,6 +96,8 @@ movements:
         policy:
           - review
           - ai-antipattern
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -101,6 +120,8 @@ movements:
           - backend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -140,6 +161,8 @@ movements:
           - backend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -164,6 +187,8 @@ movements:
           - backend
           - security
           - architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -192,6 +217,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -221,6 +248,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/pieces/backend-review-fix.yaml

@@ -15,7 +15,7 @@ loop_monitors:
     threshold: 3
     judge:
       persona: supervisor
-      instruction_template: loop-monitor-ai-fix
+      instruction_template: loop-monitor-reviewers-fix
       rules:
         - condition: 健全（進捗あり）
           next: reviewers
@@ -26,6 +26,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -53,6 +55,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -73,6 +77,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -94,6 +100,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -125,6 +133,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -147,6 +157,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -178,6 +190,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/pieces/backend-review.yaml

@@ -13,6 +13,8 @@ movements:
   - name: gather
     edit: false
     persona: planner
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -40,6 +42,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -60,6 +64,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -81,6 +87,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -106,6 +114,8 @@ movements:
     edit: false
     persona: supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/pieces/backend.yaml

@@ -8,6 +8,19 @@ piece_config:
       network_access: true
 max_movements: 30
 initial_movement: plan
+loop_monitors:
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: 健全（指摘数が減少、修正が反映されている）
+          next: reviewers
+        - condition: 非生産的（同じ指摘が繰り返される）
+          next: supervise
 movements:
   - name: plan
     edit: false
@@ -15,6 +28,8 @@ movements:
     knowledge:
       - backend
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -43,6 +58,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -76,6 +93,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -103,6 +122,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -125,6 +146,8 @@ movements:
     edit: false
     persona: architecture-reviewer
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -144,6 +167,8 @@ movements:
         knowledge:
           - architecture
           - backend
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -163,6 +188,8 @@ movements:
         persona: security-reviewer
         policy: review
         knowledge: security
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -183,6 +210,8 @@ movements:
         policy:
           - review
           - qa
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -212,6 +241,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -233,6 +264,8 @@ movements:
     edit: false
     persona: dual-supervisor
     policy: review
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -263,6 +296,8 @@ movements:
       - backend
       - security
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/pieces/compound-eye.yaml

@@ -16,6 +16,8 @@ movements:
         persona: coder
         provider: claude
         knowledge: architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -54,6 +56,8 @@ movements:
         persona: coder
         provider: codex
         knowledge: architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -93,6 +97,8 @@ movements:
   - name: synthesize
     edit: false
     persona: supervisor
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/pieces/deep-research.yaml

@@ -14,6 +14,8 @@ movements:
     policy: research
     knowledge: research
     instruction: research-plan
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -43,6 +45,8 @@ movements:
         - Grep
         - WebSearch
         - WebFetch
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Write
@@ -62,6 +66,8 @@ movements:
     knowledge: research
     instruction: research-analyze
     edit: true
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Write
@@ -79,6 +85,8 @@ movements:
     policy: research
     knowledge: research
     instruction: research-supervise
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob

builtins/ja/pieces/default.yaml

@@ -33,11 +33,25 @@ loop_monitors:
           next: ai_review
         - condition: 非生産的（改善なし）
           next: reviewers
+  - cycle:
+      - reviewers
+      - fix
+    threshold: 3
+    judge:
+      persona: supervisor
+      instruction_template: loop-monitor-reviewers-fix
+      rules:
+        - condition: 健全（指摘数が減少、修正が反映されている）
+          next: reviewers
+        - condition: 非生産的（同じ指摘が繰り返される）
+          next: ABORT
 movements:
   - name: plan
     edit: false
     persona: planner
     knowledge: architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -69,6 +83,8 @@ movements:
       - testing
     knowledge:
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -106,6 +122,8 @@ movements:
     session: refresh
     knowledge:
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -140,6 +158,8 @@ movements:
     policy:
       - review
       - ai-antipattern
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -165,6 +185,8 @@ movements:
     session: refresh
     knowledge:
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob
@@ -191,6 +213,8 @@ movements:
         persona: architecture-reviewer
         policy: review
         knowledge: architecture
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -209,6 +233,8 @@ movements:
         edit: false
         persona: supervisor
         policy: review
+        provider_options:
+          claude:
             allowed_tools:
               - Read
               - Glob
@@ -240,6 +266,8 @@ movements:
       - testing
     knowledge:
       - architecture
+    provider_options:
+      claude:
         allowed_tools:
           - Read
           - Glob