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/noboru-i/web-development-toolbox/claude-mdgit clone --depth 1 https://github.com/noboru-i/web-development-toolboxWrote 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/noboru-i/web-development-toolbox/claude-md)<a href="https://agentmods.dev/instructions/noboru-i/web-development-toolbox/claude-md"><img src="https://agentmods.dev/badge/instructions/noboru-i/web-development-toolbox/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 | $0.00884 | $0.00884 |
| Opus 5 | $0.00442 | $0.00442 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
web-development-toolbox 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 4d 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.
What it actually says
CLAUDE.md
このファイルは、このリポジトリでコードを扱う際にClaude Code (claude.ai/code) に対してガイダンスを提供します。
プロジェクトアーキテクチャ
これはWeb開発ユーティリティ用のMCP(Model Context Protocol)サーバー実装を含むTypeScriptモノレポです。アーキテクチャは2つのメインパッケージを持つワークスペースベースの構造に従っています:
- web-development-toolbox-mcp: エンコーディング、色変換、日時操作、QRコード、画像生成のユーティリティツールを提供するメインMCPサーバー
- web-development-toolbox-mcp-remote: OAuth統合を備えたCloudflare Workersベースのリモート版
開発コマンド
ビルド・開発
# 全パッケージをビルド
npm run build
# 全パッケージのウォッチモード
npm run watch
# 特定パッケージをビルド
npm run build --workspace=packages/web-development-toolbox-mcp
# デバッグ用MCPインスペクターを実行
cd packages/web-development-toolbox-mcp && npm run inspector
パッケージ固有のコマンド
# MCPパッケージ
cd packages/web-development-toolbox-mcp
npm run build
npm run inspector
# リモートパッケージ (Cloudflare Workers)
cd packages/web-development-toolbox-mcp-remote
npm run build
npm run start # wrangler dev
npm run deploy # wrangler deploy
npm run inspector # 同時実行: inspector + dev server
コード構造
Operationsパターン
両パッケージとも、各ユーティリティ カテゴリが独自のモジュールに分離されたモジュラー操作パターンを使用しています:
operations/base64.ts- Base64エンコーディング/デコーディングoperations/color.ts- 色フォーマット変換(hex、RGB、HSV)operations/datetime.ts- Unix/ISOタイムスタンプ変換operations/image.ts- プレースホルダー画像生成operations/jwt.ts- JWTトークンデコーディングoperations/qr.ts- QRコード生成operations/uuid.ts- UUID v4/v7生成
MCPサーバーアーキテクチャ
メインサーバー(index.ts)はModel Context Protocol SDKを使用し、以下の機能があります:
server-handlers.tsのgetAvailableTools()によるツール登録- ツール実行のための
handleToolCall()によるリクエスト処理 - 入力検証とJSONスキーマ生成のためのZodスキーマ
コーディング規準
- コメント: 常に英語でコメントを記述する(.github/copilot-instructions.md に基づく)
- TypeScript: 明示的な型を使用し、
anyを避け、単一責任の原則に従う - JSDoc: エクスポート関数には英語でJSDocコメントを含める
- 関数: 複雑なロジックは独立した関数に分離する
- エクスポート: エクスポート関数と内部関数を明確に区別する
TypeScript設定
プロジェクトはTypeScriptコンポジット設定を使用しています:
- ターゲット: ES2022
- モジュール: Node16
- 厳密モード有効
- ワークスペースパッケージ用のプロジェクト参照
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.
- 4d ago First seen · 76 lines · 884 tokens per session scan A a1e22e678cb3
web-development-toolbox CLAUDE.md is an instructions file published in the GitHub repository noboru-i/web-development-toolbox (5 stars, last pushed 1y ago), licensed MIT. It adds 884 tokens to every session, about $0.0044 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
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.