Borrowing it
Nothing to install: this file belongs to knishioka/cost-management-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/knishioka/cost-management-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/knishioka/cost-management-mcpWrote 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/knishioka/cost-management-mcp/agents-md)<a href="https://agentmods.dev/instructions/knishioka/cost-management-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/knishioka/cost-management-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/knishioka/cost-management-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/knishioka/cost-management-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.05286 | $0.05286 |
| Opus 5 | $0.02643 | $0.02643 |
| Sonnet 5 | $0.01057 | $0.01057 |
| Haiku 4.5 | $0.00529 | $0.00529 |
Grade C, and why
cost-management-mcp AGENTS.md scanned grade C with 1 finding 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 11d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **原因**: `npm run clean` が `rm -rf` を使用。 How it starts
The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS | cost-management-mcp
適用範囲 / Scope
- このファイルはリポジトリ直下 (
/) に配置され、リポジトリ全体へ適用されます。- 将来的にパッケージ配下へ
AGENTS.mdが追加された場合は、"近接優先" ルールに従い、より深い階層の指示を優先してください (Closest file wins)。- 現在このリポジトリは単一パッケージ構成であり、追加のローカル
AGENTS.mdは存在しません。
1. Overview | 概要
1.1 Mission Statement | 目的
- このリポジトリは Model Context Protocol (MCP) サーバーを実装し、AWS / OpenAI / Anthropic など複数クラウド・API のコストを統合的に分析・可視化します。
- TypeScript (Node.js) ベースで、MCP クライアント (例: Claude Desktop) からの自然言語クエリに応答するツール群を提供します。
- 既存のCI/CD (GitHub Actions) と連携し、品質 (Lint/Typecheck/Test) とセキュリティ (Audit/Secret scan) を自動化しています。
1.2 Architecture Snapshot | アーキテクチャ概観
- ランタイム: Node.js >= 18 (CIでは 18.x / 20.x をサポート)。
- 言語: TypeScript 5.x。CommonJS 出力 (
type: "commonjs")。 - フレームワーク: MCP SDK (
@modelcontextprotocol/sdk) を用いたツール定義。 - テスト: Jest (ts-jest) によるユニット/統合テスト。カバレッジ収集は Codecov へ送信。
- Lint/Format: ESLint + Prettier (lint-staged と Husky でプリコミット適用)。
- キャッシュ層:
node-cache(in-memory)、オプションで Redis (REDIS_URL) を使用可能。 - Secrets 管理:
.envor MCP config (例:.mcp.json) を通じて環境変数で渡す。リポジトリには秘匿情報を含めない。
1.3 Directory Map | 主要ディレクトリ
/src: ソースコード (MCP ツール、サービス、キャッシュ実装)。/tests: Jest テストケース。__snapshots__等がある場合はここに格納。/node_modules: インストール済み依存。原則編集禁止。/dist:npm run buildで生成される出力。Git管理外。/configsディレクトリは存在しませんが、tsconfig.json/jest.config.js/eslint.config.js/.prettierrcがリポジトリ直下にあります。/.github/workflows: GitHub Actions 定義 (ci.yml,release.yml,security.yml等)。.env.example: 必須環境変数のサンプル。実値は追加しないでください。mcp-config-example.json,.mcp.json.example: MCP クライアント用設定例。
1.4 Key Entry Points | 重要エントリポイント
src/index.ts: MCP サーバーの起動ポイント。npm run dev/npm run startで参照。src/tools/*: 個別ツール定義 (cost_get,provider_list, etc.)。src/services/*: 各クラウド/ベンダーとの通信ロジック。src/utils/*: 共通ユーティリティ (キャッシュ、フォーマッタなど)。tests/**/*.test.ts: Jest テスト。
1.5 Documentation Cross-Links | 追加資料
README.md: 機能概要、利用例、バッジ。CONTRIBUTING.md: 貢献ガイドライン (コミット規約はConventional Commits推奨)。openai-analysis-report.md,billing-apis-research.md: ドメイン調査メモ。TEST_RESULTS.md: 過去テスト実行レポート (参考程度)。
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.
- 11d ago First seen · 332 lines · 5,286 tokens per session scan C bd8361a982da
cost-management-mcp AGENTS.md is an instructions file published in the GitHub repository knishioka/cost-management-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 5,286 tokens to every session, about $0.0264 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other instructions, from other repositories
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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 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).
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.
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).