Borrowing it
Nothing to install: this file belongs to tieubao/capacities-mcp-worker. 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/tieubao/capacities-mcp-worker/master/CLAUDE.mdgit clone --depth 1 https://github.com/tieubao/capacities-mcp-workerWrote 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/tieubao/capacities-mcp-worker/claude-md)<a href="https://agentmods.dev/instructions/tieubao/capacities-mcp-worker/claude-md"><img src="https://agentmods.dev/badge/instructions/tieubao/capacities-mcp-worker/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/tieubao/capacities-mcp-worker/claude-md"><img src="https://agentmods.dev/badge/instructions/tieubao/capacities-mcp-worker/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 | $0.00492 | $0.00492 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
capacities-mcp-worker 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 8d 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
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
A Cloudflare Worker that exposes the Capacities API (api.capacities.io) as a remote MCP server. It bridges Claude clients (web, iOS, Desktop, Code) to a user's Capacities knowledge base over HTTPS.
Commands
npm install # Install dependencies
npm run dev # Local dev server (wrangler dev)
npm run deploy # Deploy to Cloudflare Workers
npx wrangler secret put CAPACITIES_API_KEY # Set API key secret
No test framework is configured yet.
Architecture
Two source files:
-
src/index.ts— Worker entry point and MCP tool definitions. TheCapacitiesMCPclass extendsMcpAgent(from theagentspackage) and registers six MCP tools in itsinit()method. The default export is the CF Worker fetch handler that routes/health,/sse(legacy SSE transport), and/mcp(Streamable HTTP transport) to the appropriate handlers. -
src/capacities.ts— Thin HTTP client for the Capacities REST API.createClient(apiKey)returns{get, post}methods that hithttps://api.capacities.io.
The Worker uses a Durable Object (CapacitiesMCP) for MCP session state, declared in wrangler.toml.
Key Dependencies
agents— Cloudflare's agent framework; providesMcpAgentbase class withserveSSE()andserve()static methods@modelcontextprotocol/sdk— MCP protocol SDK; providesMcpServerand tool registrationzod— Schema validation for tool inputs (bundled via MCP SDK)
Environment / Secrets
CAPACITIES_API_KEY— Required. Stored as a Cloudflare Worker secret, accessed viathis.env.CAPACITIES_API_KEY.CAPACITIES_MCP— Durable Object namespace binding (configured in wrangler.toml).
Capacities API Constraints
- Rate limit: 120 requests per 60s per endpoint
- Search returns IDs/titles only, not full object content
- API is beta and subject to change
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.
- 8d ago First seen · 46 lines · 492 tokens per session scan A 4feb9a307106
capacities-mcp-worker CLAUDE.md is an instructions file published in the GitHub repository tieubao/capacities-mcp-worker (0 stars, last pushed 5mo ago), licensed MIT. It adds 492 tokens to every session, about $0.0025 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.