Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add s977043/PlanGate --skill subagent-driven-developmentgit clone --depth 1 https://github.com/s977043/PlanGateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/s977043/plangate/subagent-driven-development)<a href="https://agentmods.dev/skills/s977043/plangate/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/s977043/plangate/subagent-driven-development/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/s977043/plangate/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/s977043/plangate/subagent-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.01452 |
| Opus 5.5 | $0.00046 | $0.00581 |
| Sonnet 5.5 | $0.00023 | $0.00290 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
subagent-driven-development scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent-Driven Development
実装計画の各タスクを専門サブエージェントに委譲し、2段階レビュー(spec準拠+品質)で高品質な実装を高速に回す。
Iron Law
NO MERGE WITHOUT TWO-STAGE REVIEW
Spec Reviewerによる仕様準拠確認とQuality Reviewerによる品質確認の両方を通過しない限り、タスクを完了としない。
Common Rationalizations
| こう思ったら | 現実 |
|---|---|
| 「Spec Reviewは実装者を信頼してスキップ」 | 信頼とレビューは別。2段階は必須 |
| 「小さい修正だからQuality Review不要」 | 小さい修正こそバグが潜む。スキップ禁止 |
| 「前のタスクと同じパターンだからレビュー軽め」 | 各タスクは独立評価。前回の結果は根拠にならない |
核心原則: Fresh subagent per task + two-stage review = high quality, fast iteration
プロセス概要
Plan読み込み → タスク抽出 → 各タスクについて:
1. Implementerサブエージェント派遣
2. Spec Reviewerサブエージェント派遣
3. (問題あれば) Implementer修正 → 再レビュー
4. Quality Reviewerサブエージェント派遣
5. (問題あれば) Implementer修正 → 再レビュー
6. タスク完了 → 次のタスクへ
→ 全タスク完了後、最終統合レビュー
Step 1: 計画読み込みとタスク抽出
plan.mdとtodo.mdを読む- 各タスクに以下の情報を付与:
- 変更対象ファイル
- 受入基準(specから該当部分を抽出)
- 依存関係(前のタスクの完了が必要か)
- 推奨モデル(複雑度に応じて選択)
モデル選択ガイド
| タスク複雑度 | 推奨 | 例 |
|---|---|---|
| 低(機械的) | haiku | 単純なCRUD、テンプレート適用 |
| 中(統合) | sonnet | API連携、コンポーネント結合 |
| 高(設計判断) | opus | アーキテクチャ決定、複雑なロジック |
Step 2: Implementerサブエージェント派遣
各タスクに対して、以下の情報を含むプロンプトでサブエージェントを起動:
タスク: {タスク名}
スコープ: {変更対象ファイル}
受入基準: {具体的な基準}
既存パターン: {プロジェクトの既存実装パターン}
制約: {アーキテクチャ構造、依存方向、命名規則}
Implementerのルール:
- 不明点があれば実装前に質問する(推測で進めない)
- 既存パターンに従う
- テストを含める
- 実装後にセルフレビューを行う
Step 3: Spec Reviewerサブエージェント派遣
Implementerの成果物に対して、spec準拠レビューを実施:
チェック項目:
□ 受入基準を全て満たしているか
□ スコープ外の変更がないか
□ 既存のAPIコントラクトを破壊していないか
□ テストが受入基準をカバーしているか
判定: PASS / FAIL(修正必須箇所を明示)
FAIL → Implementerに差し戻し → 修正 → 再レビュー
Step 4: Quality Reviewerサブエージェント派遣
Spec PASSした成果物に対して、コード品質レビューを実施:
チェック項目:
□ アーキテクチャ原則の遵守(レイヤー間依存方向)
□ 命名の一貫性
□ エラーハンドリング
□ パフォーマンス(N+1クエリ、不要なデータ取得)
□ セキュリティ(入力バリデーション、認証・認可)
□ テスト品質(境界値、異常系)
判定: PASS / WARN(改善提案)/ FAIL(修正必須)
FAIL → Implementerに差し戻し → 修正 → 再レビュー
Step 5: 最終統合レビュー
全タスク完了後:
- 全変更ファイルの統合的なレビュー
- コンフリクトの確認
- プロジェクトの検証コマンド実行(lint/test/typecheck)
todo.mdの全チェック更新
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 135 lines · 114 tokens per session scan A 70eab6a0c30b
subagent-driven-development is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 1,452 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-maintenance
Automated skill maintenance tool (v6 — Unified Registry + Snapshots). Full scan: [Orphan] migrate misplaced skills from category dirs OR standalone skills/<name>/ to auto-generated/, [Sync] auto-generated/ vs registry lifecycle diff (new/deleted/revived + description auto-sync via lifecycle field), [Reg]…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.