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.
npx agentmods add instructions/kewton/commandmate/claude-mdgit clone --depth 1 https://github.com/Kewton/CommandMateWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.05589 | $0.05589 |
| Opus 5 | $0.02795 | $0.02795 |
| Sonnet 5 | $0.01118 | $0.01118 |
| Haiku 4.5 | $0.00559 | $0.00559 |
Grade A, and why
CommandMate CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
このドキュメントはClaude Code向けのプロジェクトガイドラインです。
⚠️ 重要: モジュール詳細を CLAUDE.md に書かないこと
- モジュールの実装詳細・関数シグネチャ・Issue 履歴は 必ず docs/module-reference.md に記載する（CLAUDE.md には書かない）
- CLAUDE.md は brief overview のみ。各 module 説明は 1 行 100 文字以内 を厳守
Issue #N で…追加のような履歴 narrative を CLAUDE.md に append しない。履歴は git log / CHANGELOG / PR description で辿る- docs/module-reference.md も append-only で肥大化させない（既存行の更新を優先する）
- 違反すると CI でブロックされる（
## 品質担保の CLAUDE.md size check 参照）
プロジェクト概要
基本情報
- プロジェクト名: CommandMate
- 説明: Git worktree管理とClaude CLI/tmuxセッション統合ツール
- リポジトリ: https://github.com/Kewton/CommandMate
技術スタック
| カテゴリ | 技術 |
|---|---|
| フレームワーク | Next.js 14 |
| 言語 | TypeScript |
| スタイル | Tailwind CSS |
| データベース | SQLite (better-sqlite3) |
| テスト | Vitest (unit/integration), Playwright (e2e) |
ブランチ構成
ブランチ戦略
main (本番) ← PRマージのみ
│
develop (受け入れ・動作確認)
│
feature/*, fix/*, hotfix/* (作業ブランチ)
命名規則
| ブランチ種類 | パターン | 例 |
|---|---|---|
| 機能追加 | feature/<issue-number>-<description> |
feature/123-add-dark-mode |
| バグ修正 | fix/<issue-number>-<description> |
fix/456-fix-login-error |
| 緊急修正 | hotfix/<description> |
hotfix/critical-security-fix |
| ドキュメント | docs/<description> |
docs/update-readme |
標準マージフロー
通常フロー
feature/* ──PR──> develop ──PR──> main
fix/* ──PR──> develop ──PR──> main
hotfix/* ──PR──> main (緊急時のみ)
PRルール
- PRタイトル:
<type>: <description>形式- 例:
feat: add dark mode toggle - 例:
fix: resolve login error
- 例:
- PRラベル: 種類に応じたラベルを付与
feature,bug,documentation,refactor
- レビュー: 1名以上の承認必須（main向けPR）
- CI/CD: 全チェックパス必須
コミットメッセージ規約
<type>(<scope>): <subject>
<body>
<footer>
| type | 説明 |
|---|---|
feat |
新機能 |
fix |
バグ修正 |
docs |
ドキュメント |
style |
フォーマット（機能変更なし） |
refactor |
リファクタリング |
test |
テスト追加・修正 |
chore |
ビルド・設定変更 |
ci |
CI/CD設定 |
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.
- 2d ago First seen · 422 lines · 5,589 tokens per session scan A 1522dae1a44f
CommandMate CLAUDE.md is an instructions file published in the GitHub repository Kewton/CommandMate (39 stars, last pushed 2d ago), licensed MIT. It adds 5,589 tokens to every session, about $0.0279 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.
Other instructions, from other repositories
agent-of-empires AGENTS.md
AGENTS.md instructions for agent-of-empires/agent-of-empires, covering repository guidelines, where to look, commands, code rules and tests.
psmux AGENTS.md
AGENTS.md instructions for psmux/psmux, covering agent instructions and test isolation.
vscode-ext-tmux-worktree AGENTS.md
Instructions for kargnas/vscode-ext-tmux-worktree, covering ai agent guidelines, instruction, tested vs code, 1. codebase understanding and project structure.
remobi AGENTS.md
Instructions for connorads/remobi, covering remobi, architecture, stack, key commands and local development.
tws AGENTS.md
Instructions for ytaskiran/tws, covering agents.md, build & test, ci, workflow and ...edit, commit, push, gh pr create.
Multiplex AGENTS.md
Instructions for multiplex-term/Multiplex, covering build & test, build, unit tests — fast, no device i/o, architecture and reference docs — read before touching an area.