Borrowing it
Nothing to install: this file belongs to chrischall/tock-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/chrischall/tock-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/chrischall/tock-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/chrischall/tock-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrischall/tock-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/tock-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 | $0.02799 | $0.02799 |
| Opus 5 | $0.01399 | $0.01399 |
| Sonnet 5 | $0.00560 | $0.00560 |
| Haiku 4.5 | $0.00280 | $0.00280 |
Grade A, and why
tock-mcp CLAUDE.md scanned grade A 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Node. The same-origin `fetch(path, {credentials:'include'})` inside the user's How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tock-mcp
Read-only MCP server for Tock (exploretock.com): metro directory, per-metro
restaurant search, venue detail, a venue's bookable calendar, and the signed-in
user's reservations. Eight tock_* tools, stdio, no required env config (TOCK_WS_PORT optionally overrides the fetchproxy concentrator port — see below).
Archetype: Pattern A (every call rides the fetchproxy bridge — see
docs/fleet-conventions.md in chrischall/workflows for what A vs B means).
Pattern A is forced here, not chosen: www.exploretock.com answers every
server-side path — /, /city, /{slug} — with 403 + cf-mitigated: challenge + a "Just a moment…" interstitial. There is no login form to POST, no
consumer token exchange, and nothing to lift out of the browser and replay from
Node. The same-origin fetch(path, {credentials:'include'}) inside the user's
tab returns the full SSR HTML with no challenge. That in-tab fetch is the
transport.
src/transport-fetchproxy.ts declares domains: ['exploretock.com'] (one
domain; subdomains match the declared root) and pins subdomain: 'www' on every
request. Port 37149 is the shared fleet concentrator — TOCK_WS_PORT overrides
it for local testing only; changing the default means the extension never
connects.
Build & test
npm run build # tsc → dist/*.js + esbuild → dist/bundle.js (the bin entry)
npm test # vitest, 8 files / 61 tests, fully mocked, no bridge needed
tests/helpers.ts exports stubClient({ slices, html, graphql, errors }) — a
hand-rolled TockClient stub keyed by "path::sliceKey". Tool tests drive that;
they never touch a transport. tests/server-boot.test.ts spawns the real
dist/bundle.js with no node_modules and asserts the tools/list handshake —
it builds on demand, so a stale dist/ won't fail it silently.
vitest.config.ts adds no exclude for **/.claude/**. If you leave an agent
worktree under .claude/worktrees/, its tests get discovered too. (**/dist/**
needs no entry — vitest's default test.exclude already covers it.)
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.
- 7d ago First seen · 187 lines · 2,799 tokens per session scan A 4211d78a9c6f
tock-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/tock-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 2,799 tokens to every session, about $0.0140 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
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).
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.