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/forgesworn/rendezvous-mcp/claude-mdgit clone --depth 1 https://github.com/forgesworn/rendezvous-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/forgesworn/rendezvous-mcp/claude-md)<a href="https://agentmods.dev/instructions/forgesworn/rendezvous-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/forgesworn/rendezvous-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 5.1 | $0.00538 | $0.00538 |
| Opus 5 | $0.00269 | $0.00269 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
rendezvous-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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — rendezvous-mcp
MCP server for AI-driven fair meeting point discovery. Thin wrapper over rendezvous-kit exposing 5 tools via the Model Context Protocol.
Conventions
- British English everywhere — favour, colour, behaviour, licence, initialise, metre
- Never use
console.log()— stdio transport reserves stdout for JSON-RPC. Useconsole.error()for all debug output. - Git: commit messages use
type: descriptionformat. Do NOT includeCo-Authored-Bylines. - ESM-only with
.jsextensions in imports - TypeScript strict mode — no
any, no implicit returns
Project structure
src/
index.ts — server entry point, dual transport (stdio/HTTP)
routing.ts — RoutingClient wrapping ValhallaEngine with L402 handling
l402.ts — L402State credential storage + types
tools/
score-venues.ts — score candidate venues by travel time fairness
search-venues.ts — search Overpass for venues near a location
isochrone.ts — compute reachability polygon
directions.ts — turn-by-turn routing
store-credentials.ts — store L402 macaroon + preimage after payment
Build & test
npm run build # tsc → build/
npm test # vitest run
npm run typecheck # tsc --noEmit
npm start # stdio mode (default)
npm run start:http # HTTP mode on port 3002
Handler extraction pattern
Each tool file exports two things:
handle*()— extracted handler function (testable without MCP framework)register*Tool()— one-liner that registers the handler with the MCP server
This pattern keeps tool logic testable and registration minimal.
Environment variables
| Variable | Default | Description |
|---|---|---|
TRANSPORT |
stdio |
Transport mode: stdio or http |
PORT |
3002 |
HTTP server port (HTTP mode only) |
HOST |
0.0.0.0 |
HTTP bind address (HTTP mode only) |
VALHALLA_URL |
https://routing.trotters.cc |
Routing engine URL |
OVERPASS_URL |
Public endpoints | Venue search API |
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.
- 5d ago First seen · 55 lines · 538 tokens per session scan A 89e5f0cea69d
rendezvous-mcp CLAUDE.md is an instructions file published in the GitHub repository forgesworn/rendezvous-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 538 tokens to every session, about $0.0027 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
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).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
geolens CLAUDE.md
Claude Code instructions for geolens-io/geolens: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.