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/shutootaki/gwm/agents-mdgit clone --depth 1 https://github.com/shutootaki/gwmWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/shutootaki/gwm/agents-md)<a href="https://agentmods.dev/instructions/shutootaki/gwm/agents-md"><img src="https://agentmods.dev/badge/instructions/shutootaki/gwm/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01155 | $0.01155 |
| Opus 5 | $0.00577 | $0.00577 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
gwm AGENTS.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 5d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
AI coding agents向けのプロジェクトガイドライン。
プロジェクト概要
gwm (Git Worktree Manager) - Git worktreeをインタラクティブTUIで管理するCLIツール。
| 実装 | ディレクトリ | フレームワーク | 状態 |
|---|---|---|---|
| Rust | ルート | ratatui | メイン |
| TypeScript | gwm-ts/ |
React + Ink | deprecated |
開発コマンド
cargo build # ビルド
cargo test # テスト
cargo clippy # リント
cargo fmt # フォーマット
make check # CI相当のチェック
ローカル検証
cargo build
./target/debug/gwm {command}
ディレクトリ構成
src/
├── main.rs # エントリポイント
├── cli/ # CLIコマンド定義
├── config/ # 設定管理
├── git/ # Git操作
├── ui/ # TUIコンポーネント
├── hooks/ # フック実行
└── trust/ # 信頼検証
gwm-ts/ # TypeScript版（deprecated）
CLIコマンド
| コマンド | エイリアス | 説明 |
|---|---|---|
list |
ls |
ワークツリー一覧 |
add |
- | 新規作成 |
remove |
rm |
削除 |
go |
- | 移動（パス出力） |
clean |
- | マージ済み整理 |
sync |
pull-main |
main更新 |
開発ルール
DO（必須）
- テストを書く: 新機能・バグ修正には必ずテストを追加
- 動作確認: コード変更後はローカルで動作確認
- UX優先: ユーザー体験を最優先に設計
- エラーメッセージ: 具体的で対処法がわかるメッセージ
- 既存パターン踏襲: プロジェクト内の既存コードスタイルに従う
DON'T（禁止）
- 未読のコード変更禁止: 読んでいないファイルを変更しない
- 過剰な抽象化禁止: 必要最小限の実装に留める
- 機密情報禁止:
.envや認証情報をコミットしない - 破壊的変更禁止: 既存のCLIインターフェースを壊さない
コーディング規約
cargo clippyの警告をすべて解消cargo fmtでフォーマットunwrap()は避け、適切なエラーハンドリングunsafeは使用禁止thiserror/anyhowでエラーハンドリング
テスト
cargo test # 全テスト
cargo test git:: # 特定モジュール
cargo test -- --nocapture # 出力表示
コミットメッセージ
Conventional Commits形式:
feat: 新機能追加
fix: バグ修正
refactor: リファクタリング
test: テスト追加・修正
docs: ドキュメント
chore: その他
スコープ例: feat(gwm): add clean command
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.
- 5d ago First seen · 164 lines · 1,155 tokens per session scan A 493406b7c213
gwm AGENTS.md is an instructions file published in the GitHub repository shutootaki/gwm (18 stars, last pushed 7mo ago), licensed MIT. It adds 1,155 tokens to every session, about $0.0058 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
sessionview AGENTS.md
AGENTS.md instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.
formax AGENTS.md
Instructions for yusifeng/formax, covering repository guidelines, agents scope, project structure & module organization, build, test, and development commands and coding style & naming conventions.
gemini-cli-desktop AGENTS.md
Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
codmate AGENTS.md
Instructions for loocor/codmate, a project described as: CodMate is a macOS SwiftUI app for managing CLI AI sessions: browse, search, organize, resume, and review work produced by Codex, Claude Code, and Gemini CLI. It focuses on speed, a compact three-column UI, and “ship it” workflows like Project Review (Git…
cordon AGENTS.md
AGENTS.md instructions for ilyautov/cordon, covering working in this repository, the three invariants, the map, commands and tests.
everything-gemini-code GEMINI.md
Gemini CLI instructions for Jamkris/everything-gemini-code, covering project instructions, prompt defense baseline and guidelines.