subagent-driven-development

subagent-driven-development is a skill for Claude Code, Codex from s977043/PlanGate. It costs 114 tokens per session (1,452 once invoked), scanned A, original, MIT.

A workflow for delegating planned coding tasks to separate subagents and checking each result in two reviews: one for matching the specification and one for code quality. A subagent is a separate agent assigned to a focused task.

In plain words
What is it for?
Use it to split a large implementation into tasks, assign each task to an implementer, request specification and quality reviews, revise failed work, and perform a final integration review.
Why use it?
It reduces the risk of unreviewed changes by requiring every delegated task to pass both checks before it is considered complete.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/s977043/plangate/subagent-driven-development
Any agent
npx skills add s977043/PlanGate --skill subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/s977043/PlanGate

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for subagent-driven-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/s977043/plangate/subagent-driven-development.svg)](https://agentmods.dev/skills/s977043/plangate/subagent-driven-development)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,452 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00114 $0.01452
Opus 5 $0.00057 $0.00726
Sonnet 5 $0.00023 $0.00290
Haiku 4.5 $0.00011 $0.00145

Measured 3d ago against content hash 70eab6a0c30b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

.agents/skills/subagent-driven-development/SKILL.md · 135 lines

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

  1. plan.mdtodo.md を読む
  2. 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
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:

  1. 全変更ファイルの統合的なレビュー
  2. コンフリクトの確認
  3. プロジェクトの検証コマンド実行(lint/test/typecheck)
  4. todo.md の全チェック更新

Read the full file on GitHub · 135 lines

Changes

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.

  1. 3d ago First seen · 135 lines · 114 tokens per session scan A 70eab6a0c30b

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed 3d ago), licensed MIT. It adds 114 tokens to every session and 1,452 once invoked, about $0.0006 per session on Opus 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.

Related

Other skills, from other repositories

escalation-governance

Assess whether to escalate models. Use when evaluating reasoning depth.

athola/claude-night-market · 19 tokens

aidd-dev:07:debug

Reproduce and fix bugs systematically using test-driven workflow, root cause analysis, and hypothesis validation.

ai-driven-dev/framework · 27 tokens

audit-remediate

Macro workflow for auditing a single domain layer against its authoritative layer skill, applying fixes, and gating the result. Use when you need to prove a layer skill on real code, clean up an existing layer after a skill update, or verify that a layer is already compliant. Always captures a golden baseline before…

ai-driven-dev/framework · 110 tokens

feature

Macro workflow for building or changing a vertical slice of the CLI. Use as the entry point when adding a new end-to-end feature (domain → use-case → adapter → command → tests) or when a change touches multiple layers at once. Do NOT use for single-layer changes — use the layer skill directly (domain-model, use-case…

ai-driven-dev/framework · 82 tokens

aidd-vcs:03:release-tag

Cut a semver release by computing the next version from recent commits, generating annotated release notes from the template, validating with the user, then creating and pushing the git tag along with a bump commit. Use when the user says "release", "tag", "tag this release", "bump version", "release v1.2.0", "cut a…

ai-driven-dev/framework · 116 tokens

clipboard

Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".

CodeAlive-AI/ai-driven-development · 36 tokens