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/signalcompose/claude-tools/claude-mdgit clone --depth 1 https://github.com/signalcompose/claude-toolsWrote 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/signalcompose/claude-tools/claude-md)<a href="https://agentmods.dev/instructions/signalcompose/claude-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/signalcompose/claude-tools/claude-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 | $0.02599 | $0.02599 |
| Opus 5 | $0.01300 | $0.01300 |
| Sonnet 5 | $0.00520 | $0.00520 |
| Haiku 4.5 | $0.00260 | $0.00260 |
Grade A, and why
claude-tools 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 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-tools - Project Configuration
プロジェクト概要
SignalComposeが提供するClaude Codeプラグインのマーケットプレイス
| 項目 | 内容 |
|---|---|
| リポジトリ | signalcompose/claude-tools |
| 種別 | マーケットプレイス（プラグイン配布） |
| ライセンス | MIT |
技術スタック
- Git Subtrees（プラグイン管理）
- JSON（marketplace.json）
- Markdown（ドキュメント）
セッション開始時の手順
-
ドキュメント確認
docs/INDEX.mdを読む- 必要に応じて各ドキュメントを参照
-
作業ブランチ作成
git checkout main git pull git checkout -b feature/<作業内容>
開発原則
DDD（Documentation Driven Development）
- ドキュメントが真実の唯一の源
- 仕様変更はドキュメントから
コミット規約
タイトル: 英語（Conventional Commits） 本文: 日本語
<type>(<scope>): <subject>
<日本語の説明>
Co-Authored-By: Claude Opus 4.5 <[email protected]>
Type一覧:
feat: 新機能（プラグイン追加等）fix: 修正docs: ドキュメントchore: 設定変更等
Git Workflow（軽量版）
ブランチ戦略
main: 本番ブランチfeature/*: 作業ブランチ
作業フロー
mainからfeature/*ブランチを作成- 変更を実装・コミット
- PR作成 → マージ
禁止事項
- ❌
mainへの直接コミット（推奨レベル） - ❌ Force Push
- ❌ Squashマージ
バージョン管理ルール
Hash-based Versioning:
- プラグインはGit commit hashで自動管理（Anthropic公式と同様）
plugin.jsonにversionフィールドは不要- Claude Codeがインストール時にcommit SHAを記録
利点:
- 手動バージョン更新のオーバーヘッド削減
- 頻繁な修正に対応しやすい
- 正確なコード追跡が可能
PRマージ後:
- Subtree管理プラグインは各リポジトリに変更を反映
# CVI
git subtree push --prefix=plugins/cvi https://github.com/signalcompose/cvi.git main
# YPM
git subtree push --prefix=plugins/ypm https://github.com/signalcompose/ypm.git main
Subtree管理プラグイン一覧:
| Plugin | Repository |
|---|---|
| cvi | signalcompose/cvi |
| ypm | signalcompose/ypm |
よくある操作
プラグイン追加（Subtree）
# 1. Subtree追加
git subtree add --prefix=plugins/<plugin> https://github.com/signalcompose/<plugin>.git main --squash
# 2. .claude-plugin/marketplace.json更新
# plugins配列に新しいプラグイン情報を追加
# 3. README.md更新
# Available Pluginsテーブルに追加
# 4. コミット
git add .
git commit -m "feat(plugins): add <plugin>"
プラグイン更新（Subtree）
git subtree pull --prefix=plugins/<plugin> https://github.com/signalcompose/<plugin>.git main --squash
git commit -m "chore(plugins): update <plugin> from upstream"
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 · 287 lines · 2,599 tokens per session scan A ee1e8ac1c9b1
claude-tools CLAUDE.md is an instructions file published in the GitHub repository signalcompose/claude-tools (4 stars, last pushed 8d ago), licensed MIT. It adds 2,599 tokens to every session, about $0.0130 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.