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/codename-11/openclaw-mcp/claude-mdgit clone --depth 1 https://github.com/Codename-11/openclaw-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/codename-11/openclaw-mcp/claude-md)<a href="https://agentmods.dev/instructions/codename-11/openclaw-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/codename-11/openclaw-mcp/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 | $0.00512 | $0.00512 |
| Opus 5 | $0.00256 | $0.00256 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
openclaw-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 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 — openclaw-mcp Dev Guide
What this is
MCP (Model Context Protocol) server that bridges Claude Code ↔ OpenClaw agents. It's a stdio-based server — Claude Code spawns it as a subprocess and communicates via JSON-RPC over stdin/stdout.
Project structure
src/index.ts — All the server logic (tools, handlers)
dist/ — Compiled output (gitignored)
package.json — npm package config
tsconfig.json — TypeScript config (ES2022, Node16 modules)
Build & run
npm install
npm run build # tsc → dist/
npm run dev # tsx for fast iteration (no compile step)
Test the server manually
The server speaks JSON-RPC 2.0 over stdio. Quick smoke test:
OPENCLAW_GATEWAY_URL=http://localhost:18789 \
OPENCLAW_GATEWAY_TOKEN=your_token \
node dist/index.js
It should print to stderr: OpenClaw MCP server running (gateway: http://localhost:18789)
Then block waiting for JSON-RPC input. Ctrl+C to exit.
Adding a new tool
- Add the tool definition in the
ListToolsRequestSchemahandler - Add a case in the
CallToolRequestSchemaswitch npm run build
Key design decisions
- No axios — uses native
fetch()(Node 20+) - Stdio transport — standard MCP pattern, works with
claude mcp add - Session keys —
agent:{name}:mcpkeeps MCP convos separate from Discord - Error handling — tools return error text, never crash the server process
- 120s timeout — agents can be slow; give them room
Environment
OPENCLAW_GATEWAY_URL— defaulthttp://localhost:18789OPENCLAW_GATEWAY_TOKEN— no default, logs warning if missing
Gateway API
The server talks to the OpenClaw gateway, which is OpenAI-compatible:
POST /v1/chat/completions— send a message to an agentGET /v1/models— list available agents
Model IDs are in the format openclaw:{agent} (e.g. openclaw:daemon).
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 · 65 lines · 512 tokens per session scan A c9c926b02c7a
openclaw-mcp CLAUDE.md is an instructions file published in the GitHub repository Codename-11/openclaw-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 512 tokens to every session, about $0.0026 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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.