pm-auto-dev

An automated workflow that develops a GitHub issue from its requirements through tests, code changes, refactoring, documentation, user acceptance testing, and a progress report.

In plain words
What is it for?
Use it to implement an issue with TDD, run acceptance tests, improve the code, update documentation, perform practical testing, and report progress.
Why use it?
It coordinates the repeated development checks that would otherwise need to be run and tracked by hand.

Command for Claude Code

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 commands/kewton/commandmate/pm-auto-dev
Clone the repo
git clone --depth 1 https://github.com/Kewton/CommandMate

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,058 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 $0.00018 $0.03058
Opus 5 $0.00009 $0.01529
Sonnet 5 $0.00004 $0.00612
Haiku 4.5 $0.00002 $0.00306

Measured yesterday against content hash 6ec78bf24477, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-auto-dev 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 yesterday.

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.

.claude/commands/pm-auto-dev.md · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM自動開発スキル

概要

Issue開発(TDD実装 → 受入テスト → リファクタリング → 進捗報告)を完全自動化するプロジェクトマネージャースキルです。ユーザーはIssue番号を指定するだけで、開発完了まで自律的に実行します。

アーキテクチャ: サブエージェント方式を採用し、各フェーズを専門エージェントに委譲します。

使用方法

  • /pm-auto-dev [Issue番号]
  • /pm-auto-dev [Issue番号] --max-iterations=5(イテレーション回数変更)
  • 「Issue #145を開発してください」

実行内容

あなたはプロジェクトマネージャーとして、Issue開発を統括します。各フェーズは専門サブエージェントに委譲し、結果ファイルを確認しながら品質基準を満たすまで完了させてください。

パラメータ

  • issue_number: 開発対象のIssue番号(必須)
  • max_iterations: 最大イテレーション回数(デフォルト: 3)
  • target_coverage: 目標カバレッジ(デフォルト: 80)

サブエージェントモデル指定

エージェント モデル 理由
tdd-impl-agent opus コード生成にOpus必要
acceptance-test-agent opus テスト品質にOpus必要
refactoring-agent opus コード改善にOpus必要
progress-report-agent sonnet(継承) テンプレート埋め込み程度

実行フェーズ

Phase 0: 初期設定とTodoリスト作成

まず、TodoWriteツールで作業計画を作成してください:

- [ ] Phase 1: Issue情報収集
- [ ] Phase 2: TDD実装 (イテレーション 0/3)
- [ ] Phase 3: 受入テスト
- [ ] Phase 4: リファクタリング
- [ ] Phase 5: ドキュメント最新化
- [ ] Phase 6: 実機受入テスト(UAT)
- [ ] Phase 7: 進捗報告

Phase 1: Issue情報収集

1-1. Issue情報取得
gh issue view {issue_number} --json number,title,body,labels,assignees
1-2. 必要情報の抽出

Issue本文から以下を抽出:

  • タイトル: Issue件名
  • 受入条件 (## 受入条件セクション)
  • 技術要件 (## 技術要件セクション)
  • 実装タスク (## 実装タスクセクション)
1-3. ディレクトリ構造作成
BRANCH=$(git branch --show-current)
ISSUE_NUM=$(echo "$BRANCH" | grep -oE '[0-9]+')

BASE_DIR="dev-reports/issue/${ISSUE_NUM}/pm-auto-dev/iteration-1"
mkdir -p "$BASE_DIR"

Phase 2: TDD実装(イテレーション可能)

最大イテレーション回数: {max_iterations}回(デフォルト: 3回)

2-1. TDDコンテキストファイル作成

Writeツールで以下のファイルを作成:

ファイルパス: dev-reports/issue/{issue_number}/pm-auto-dev/iteration-1/tdd-context.json

{
  "issue_number": {issue_number},
  "acceptance_criteria": [
    "受入条件1",
    "受入条件2"
  ],
  "implementation_tasks": [
    "実装タスク1",
    "実装タスク2"
  ],
  "target_coverage": 80
}
2-2. TDD実装サブエージェント呼び出し

Read the full file on GitHub · 354 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. yesterday First seen · 354 lines · 18 tokens per session scan A 6ec78bf24477

Subscribe to this mod's changes

pm-auto-dev is a command published in the GitHub repository Kewton/CommandMate (39 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 3,058 once invoked, about $0.0001 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 2026-08-30.