pm-auto-issue2dev

An automated project workflow that takes a GitHub issue through review, design, planning, and implementation. It uses TDD, or test-driven development, where tests guide the code changes.

In plain words
What is it for?
Use it to review an issue, update its description, create or check a design plan, prepare the work plan, and carry out the implementation.
Why use it?
It removes the need to coordinate each development stage manually and helps improve the issue before coding begins.

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-issue2dev
Clone the repo
git clone --depth 1 https://github.com/Kewton/CommandMate

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,647 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00030 $0.02647
Opus 5 $0.00015 $0.01324
Sonnet 5 $0.00006 $0.00529
Haiku 4.5 $0.00003 $0.00265

Measured yesterday against content hash cdff1bbe794e, 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-issue2dev 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.

Origin

This is a copy

86% identical to pm-auto-design2dev — 140 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/pm-auto-issue2dev.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM自動 Issue→開発スキル

概要

Issueレビューから実装完了までの全工程(Issueレビュー → 設計レビュー → 作業計画立案 → TDD実装)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、Issueの品質向上から開発完了まで自律的に実行します。

アーキテクチャ: 4つの既存コマンドを順次実行し、各フェーズの成果物を次フェーズに引き継ぎます。

使用方法

  • /pm-auto-issue2dev [Issue番号]
  • 「Issue #XXXをIssueレビューから開発まで自動実行してください」

実行内容

あなたはプロジェクトマネージャーとして、Issueレビューから開発までの全工程を統括します。以下のフェーズを順次実行し、各フェーズの完了を確認しながら進めてください。

パラメータ

  • issue_number: 開発対象のIssue番号(必須)

サブエージェントモデル指定

各サブコマンド内で個別にモデル指定されています(レビュー・TDD系=opus、反映・報告系=sonnet継承)。


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: マルチステージIssueレビュー
- [ ] Phase 2: 設計方針書確認・作成
- [ ] Phase 3: マルチステージ設計レビュー
- [ ] Phase 4: 作業計画立案
- [ ] Phase 5: TDD自動開発
- [ ] Phase 6: 完了報告

Phase 1: マルチステージIssueレビュー

1-1. Issueレビュー実行

/multi-stage-issue-review コマンドを実行:

/multi-stage-issue-review {issue_number}

このフェーズで行われること:

  • 仮説検証(コードベース照合)
  • 1st Iteration: 通常レビュー → 指摘反映 → 影響範囲レビュー → 指摘反映
  • 2nd Iteration: 通常レビュー → 指摘反映 → 影響範囲レビュー → 指摘反映
  • GitHubのIssue本文が更新される
1-2. 完了確認
  • サマリーレポートが生成されていること
  • GitHubのIssueが更新されていること

出力ファイル: dev-reports/issue/{issue_number}/issue-review/summary-report.md


Phase 2: 設計方針書の確認・作成

2-1. 設計方針書の存在確認
ls dev-reports/design/issue-{issue_number}-*-design-policy.md 2>/dev/null
2-2. 設計方針書がない場合

設計方針書が存在しない場合は、/design-policy コマンドを実行して作成:

/design-policy {issue_number}

Phase 3: マルチステージ設計レビュー

3-1. 設計レビュー実行

/multi-stage-design-review コマンドを実行:

/multi-stage-design-review {issue_number}

このフェーズで行われること:

  • Stage 1: 通常レビュー(設計原則)
  • Stage 2: 整合性レビュー
  • Stage 3: 影響分析レビュー
  • Stage 4: セキュリティレビュー
  • 各ステージの指摘事項を設計方針書に反映
3-2. 完了確認
  • サマリーレポートが生成されていること
  • 設計方針書が更新されていること

出力ファイル: dev-reports/issue/{issue_number}/multi-stage-design-review/summary-report.md


Phase 4: 作業計画立案

4-1. 作業計画作成

/work-plan コマンドを実行:

/work-plan {issue_number}

このフェーズで行われること:

  • 設計方針書に基づいたタスク分解
  • 依存関係の整理
  • 実装順序の決定

Read the full file on GitHub · 312 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 · 312 lines · 30 tokens per session scan A cdff1bbe794e

Subscribe to this mod's changes

pm-auto-issue2dev is a command published in the GitHub repository Kewton/CommandMate (39 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 2,647 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to pm-auto-design2dev, differing in 140 lines, and is treated as a copy.