Borrowing it
Nothing to install: this file belongs to akutishevsky/google-tasks-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/akutishevsky/google-tasks-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/akutishevsky/google-tasks-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/akutishevsky/google-tasks-mcp/claude-md)<a href="https://agentmods.dev/instructions/akutishevsky/google-tasks-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/akutishevsky/google-tasks-mcp/claude-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/akutishevsky/google-tasks-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/akutishevsky/google-tasks-mcp/claude-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 | $0.01070 | $0.01070 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
google-tasks-mcp 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 9d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Google Tasks MCP Server — an open-source Model Context Protocol server that lets AI assistants manage Google Tasks through natural language. Built with Hono, MCP SDK, and Deno KV. Deployed on Deno Deploy.
Commands
- Build:
npm run build(runstsc) - Dev (watch):
npm run dev(runstsc --watch) - Lint:
deno lint(configured indeno.json, targetssrc/) - Run:
deno task dev(runs compiledbuild/index.js) - Generate encryption secret:
npm run generate-secret
No test framework is configured.
Architecture
Entry Point & Runtime
src/index.ts initializes Deno KV stores (tokens, OAuth sessions, rate limiter), sets OAuth config from env vars, creates the Hono app, and exports { fetch: app.fetch } for Deno Deploy.
Request Flow
Client → Hono HTTP (app.ts) → Security headers middleware → CORS middleware
├── OAuth routes (/register, /authorize, /callback, /token) → oauth.ts
├── MCP routes (/mcp GET/POST) → Bearer auth middleware → mcp-endpoints.ts
│ └── Creates McpServer + HonoSSETransport per session
│ └── Registered tools (tools/*.ts) → google/api.ts → Google Tasks API
└── Static routes (/, /health, /privacy-policy, /favicon.ico)
Key Modules
src/server/app.ts— Hono routes and security middleware. Route-specific CSP headers override the default restrictive CSP (the middleware checksc.res.headersbefore setting defaults).src/server/mcp-endpoints.ts— GET creates SSE stream + MCP session; POST either creates a new session or routes messages to existing ones. Sessions useTransformStreamfor SSE output with 15s heartbeat pings.src/transport/mcp-transport.ts— CustomHonoSSETransportimplementing MCP'sTransportinterface.SessionManagertracks sessions with 30-minute timeout and periodic cleanup.src/auth/oauth.ts— Full OAuth 2.0 with PKCE. Three-legged flow: client registers → redirects to Google → callback exchanges code → returns MCP bearer token (UUID).OAuthStoreuses Deno KV with TTLs.src/auth/token-store.ts— Encrypts Google tokens (AES-256-GCM) before storing in Deno KV. 30-day TTL.src/google/api.ts— Thin wrapper over Google Tasks REST API. All calls go throughmakeGoogleRequest()which handles auth token refresh automatically (60s expiry threshold). Functions return promises directly (not async).src/tools/tasklists.tsandsrc/tools/tasks.ts— 14 MCP tools registered viaserver.registerTool(). Each uses Zod for input schemas andaddReadableTimestamps()for response processing.src/utils/logger.ts— Logger with automatic redaction of tokens, secrets, user IDs. Set level viaLOG_LEVELenv var.src/utils/encryption.ts— AES-256-GCM with PBKDF2 key derivation (100k iterations). RequiresENCRYPTION_SECRETenv var (32+ chars).
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.
- 9d ago First seen · 74 lines · 1,070 tokens per session scan A 562aef7495aa
google-tasks-mcp CLAUDE.md is an instructions file published in the GitHub repository akutishevsky/google-tasks-mcp (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,070 tokens to every session, about $0.0053 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
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).
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.