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/chrischall/easytable-mcp/claude-mdgit clone --depth 1 https://github.com/chrischall/easytable-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/easytable-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrischall/easytable-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/easytable-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 | $0.01107 | $0.01107 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
easytable-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.
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 — easytable-mcp
Guidance for Claude working in this repo.
TL;DR
easyTable MCP server. easyTable is a restaurant table-booking system with a
public per-restaurant widget at book.easytable.com/book/?id=<placeId> (classic
ASP + jQuery). No user login — the restaurant is identified by its id
(a.k.a. place). Every endpoint is Cloudflare-403'd server-side, so this is a
full-fetchproxy MCP ("Pattern A"): every request rides the user's own
signed-in, Cloudflare-cleared book.easytable.com tab via
@fetchproxy/server. No server-side
fetch, no bootstrap capture — the anti-bot clearance is fingerprint-bound to the
browser tab.
The reverse-engineered API is documented in docs/EASYTABLE-API.md.
Tool surface
| Tool | File | Endpoint | Kind |
|---|---|---|---|
easytable_list_types |
tools/availability.ts |
GET /book/ajax/types.asp (HTML fragment) |
read |
easytable_list_dates |
tools/availability.ts |
GET /book/ajax/calendar.asp (HTML fragment) |
read |
easytable_list_times |
tools/availability.ts |
GET /book/ajax/times.asp (HTML fragment) |
read |
easytable_find_bookings |
tools/availability.ts |
GET /book/ajax/cancel-search.asp (HTML fragment) |
read |
easytable_create_booking |
tools/booking.ts |
POST /user/ajax/json_booking.asp (JSONP) |
write (confirm) |
easytable_modify_booking |
tools/booking.ts |
POST /user/ajax/json_modify_booking.asp (JSONP) |
write (confirm) |
easytable_cancel_booking |
tools/booking.ts |
GET /user/ajax/json_cancel_booking.asp (JSONP) |
write (confirm) |
easytable_healthcheck |
(index.ts) | GET /robots.txt round-trip + bridge status |
read |
The Turnstile write-gate (the interesting bit)
create/modify need four page-derived values (all verified against a real
booking, 2026-07-09) on top of the guest details:
turnstileToken— a live Cloudflare Turnstile token (server rejects without it). Read from the widget's hiddeninput[name="cf-turnstile-response"]via the fetchproxy bridge'sread_domcapability (a 1.4.0+ verb added for this MCP): an isolated-worldquerySelectorDOM read of a selector declared inbridge-fetchproxy.ts(domSelectors), surfaced at pair time — no page-JS exec.bookingToken— a per-flow GUID the server issues in theconfirm.aspfragment (REQUIRED; empty →Status:0rejection). Parsed from a fetched fragment.cancellationtime— hidden input inconfirm.asp(empty → ASP 500s).lcid— language-dependent locale id, parsed from the page HTML.
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 · 74 lines · 1,107 tokens per session scan A 500abcddb3e0
easytable-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/easytable-mcp (0 stars, last pushed today), licensed MIT. It adds 1,107 tokens to every session, about $0.0055 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
lastminutedeals-api AGENTS.md
AGENTS.md instructions for johnanleitner1-Coder/lastminutedeals-api, covering last minute deals hq — agent api, authentication, core booking flow, flow a — redirect (human in the loop) and flow b — autonomous (agent-native, no redirect).
lastminutedeals-api CLAUDE.md
Claude Code instructions for johnanleitner1-Coder/lastminutedeals-api, covering agent instructions, the wat architecture, how to operate, the self-improvement loop and file structure.
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.
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.