issue-split

A command that breaks a large feature into implementable project issues and maps their dependencies. It favors vertical slices, where each issue includes the user interface, server code, database work, and tests needed for a usable part.

In plain words
What is it for?
Use it to create issue titles, scopes, estimates, priorities, technical requirements, and acceptance criteria for a feature.
Why use it?
It turns a broad feature request into smaller pieces that are easier to estimate, assign, build, and verify.

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

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,688 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 $0.00012 $0.02688
Opus 5 $0.00006 $0.01344
Sonnet 5 $0.00002 $0.00538
Haiku 4.5 $0.00001 $0.00269

Measured yesterday against content hash 2958a654ea01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-split 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/issue-split.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue分割コマンド

概要

Feature全体を実装可能な単位のIssueに分割し、依存関係を整理するコマンドです。

使用方法

/issue-split [Feature概要]

:

/issue-split ダークモード機能を追加
/issue-split

実行内容

あなたはプロジェクトマネージャー兼テックリードです。Feature全体を適切なIssueに分割してください:

1. Issue分割戦略

分割の原則
  • 縦割り(Vertical Slice)優先
    • 各Issueが独立してデプロイ可能
    • UI + API + DB + テストを1つのIssueに含める
    • フェーズ(要件→設計→実装)で分割しない
Issue サイズの目安
サイズ Story Point 作業時間 推奨
XS 1 2-4時間 ✅ 小さなバグ修正
S 2 0.5-1日 ✅ 単純な機能追加
M 3-5 1-3日 ✅ 標準的な機能
L 8 3-5日 ⚠️ 分割を推奨
XL 13+ 1週間以上 ❌ 必ず分割

2. Issue一覧の作成

各Issueについて以下を定義:

## Feature: [Feature名]

### Issue #1: [タイトル]
**概要**: [1-2文で説明]
**サイズ**: S/M/L
**優先度**: High/Medium/Low
**作業見積**: [X]時間
**担当候補**: Backend/Frontend/Full-stack

**スコープ**:
- [ ] 実装内容1
- [ ] 実装内容2
- [ ] テスト作成
- [ ] ドキュメント更新

**技術スタック**:
- 言語/FW: TypeScript/Next.js 14
- データベース: SQLite
- その他: Tailwind CSS

**受入基準 (Acceptance Criteria)**:

#### 🤖 自動検証可能な基準(pm-auto-devが実施)

**機能要件**:
- [ ] APIエンドポイント `/api/v1/[リソース]` が実装される
- [ ] バリデーションエラーが適切に返される
- [ ] データベースに正常にデータが保存される

**品質基準**:
- [ ] 単体テストカバレッジ 80%以上
- [ ] 結合テストカバレッジ 50%以上
- [ ] ESLint/TypeScript エラーゼロ
- [ ] レスポンスタイム 500ms以内

**テストケース**:
- [ ] 正常系: [具体的なテストケース]
- [ ] 異常系: [具体的なテストケース]
- [ ] エッジケース: [具体的なテストケース]

#### 👤 手動検証が必要な基準(ユーザーが実施)

**UX/UI検証**:
- [ ] 画面のレイアウトが仕様通り
- [ ] エラーメッセージが分かりやすく表示される
- [ ] 操作フローが自然

**ビジネスロジック検証**:
- [ ] 実際のデータで動作確認
- [ ] 外部APIと連携確認
- [ ] セキュリティ要件確認

**運用検証**:
- [ ] ログが適切に出力される
- [ ] 管理画面で正常に表示される
- [ ] エラー時のハンドリングが機能する

#### ✅ 完了条件
- `/pm-auto-dev` 完了時点: 🤖 自動検証可能な基準 → 全て✅
- ユーザー動作確認後: 👤 手動検証が必要な基準 → 全て✅
- 上記完了後に `/create-pr` 実行可能

### Issue #2: [タイトル]
...

3. Phase毎のイシュー管理

Feature全体をPhaseに分割し、各PhaseにIssueを配置:

Phase 1: 基盤構築(並列実行可能)
Issue 概要 依存 担当 見積
#101 API設計・スキーマ定義 なし Backend 4h
#103 UI設計・コンポーネント設計 なし Frontend 4h

Phase 1 完了条件:

  • API仕様書作成完了
  • UIモックアップ承認完了

Read the full file on GitHub · 275 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 · 275 lines · 12 tokens per session scan A 2958a654ea01

Subscribe to this mod's changes

issue-split is a command published in the GitHub repository Kewton/CommandMate (39 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 2,688 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.