work-plan

An issue-based planning command that reads a GitHub Issue and turns it into a detailed implementation plan. It breaks the work into coding, testing, documentation, and dependency steps.

In plain words
What is it for?
Use it to plan data models, APIs, user interfaces, unit tests, integration tests, and related documentation for one issue.
Why use it?
It replaces a broad request with an ordered list of concrete tasks and expected files or outputs.

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

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,375 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 $0.00013 $0.02375
Opus 5 $0.00006 $0.01188
Sonnet 5 $0.00003 $0.00475
Haiku 4.5 $0.00001 $0.00237

Measured 2d ago against content hash 3c3c9a9872f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

work-plan 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 2d 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.

.claude/commands/work-plan.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

作業計画立案スキル(Issue単位)

概要

Issue単位での具体的な作業計画を立案し、実装タスクの詳細化を策定するスキルです。

使用方法

  • /work-plan [Issue番号または概要]
  • 「Issue #123の作業計画を立案してください」

前提条件

  • 対象Issueの概要と要件が明確
  • GitHubリポジトリにアクセス可能

実行内容

あなたはテックリードです。1つのIssue実装のための具体的な作業計画を立案してください:

1. Issue概要の確認

まずIssue情報を取得します:

gh issue view {issue_number} --json number,title,body,labels,assignees

以下の形式で概要をまとめます:

## Issue: [タイトル]
**Issue番号**: #XXX
**サイズ**: S/M/L
**優先度**: High/Medium/Low
**依存Issue**: #YYY(あれば)

2. 詳細タスク分解

実装タスク(Phase 1)
  • Task 1.1: データモデル/型定義

    • 成果物: src/types/xxx.ts
    • 依存: なし
  • Task 1.2: APIエンドポイント実装

    • 成果物: src/app/api/xxx/route.ts
    • 依存: Task 1.1
  • Task 1.3: UIコンポーネント実装

    • 成果物: src/components/xxx.tsx
    • 依存: Task 1.2
テストタスク(Phase 2)
  • Task 2.1: 単体テスト

    • 成果物: tests/unit/xxx.test.ts
    • カバレッジ目標: 80%以上
  • Task 2.2: 結合テスト

    • 成果物: tests/integration/xxx.test.ts
ドキュメントタスク(Phase 3)
  • Task 3.1: README更新(必要な場合)
    • 成果物: README.md

3. タスク依存関係

graph TD
    T11[Task 1.1<br/>型定義] --> T12[Task 1.2<br/>API実装]
    T12 --> T13[Task 1.3<br/>UI実装]
    T11 --> T21[Task 2.1<br/>単体テスト]
    T13 --> T22[Task 2.2<br/>結合テスト]
    T22 --> T31[Task 3.1<br/>README]

4. 品質チェック項目

チェック項目 コマンド 基準
ESLint npm run lint エラー0件
TypeScript npx tsc --noEmit 型エラー0件
Unit Test npm run test:unit 全テストパス
Build npm run build 成功

5. 成果物チェックリスト

コード
  • 型定義ファイル
  • APIエンドポイント
  • UIコンポーネント
テスト
  • 単体テスト
  • 結合テスト
ドキュメント
  • README更新(必要な場合)
実行契約
  • .commandmate/tasks/issue-{issue_number}.yaml(→ 「8. 実行契約の起案」)

6. Definition of Done

Issue完了条件:

  • すべてのタスクが完了
  • 単体テストカバレッジ80%以上
  • CIチェック全パス(lint, type-check, test, build)
  • コードレビュー承認
  • ドキュメント更新完了

7. 次のアクション

作業計画承認後:

  1. ブランチ作成: feature/{issue_number}-[feature-name]
  2. タスク実行: 計画に従って実装
  3. 進捗報告: /progress-reportで定期報告
  4. PR作成: /create-prで自動作成

Read the full file on GitHub · 189 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. 2d ago First seen · 189 lines · 13 tokens per session scan A 3c3c9a9872f6

Subscribe to this mod's changes

work-plan is a command published in the GitHub repository Kewton/CommandMate (39 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 2,375 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.