Borrowing it
Nothing to install: this file belongs to san-rat/latex-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/san-rat/latex-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/san-rat/latex-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/san-rat/latex-mcp/claude-md)<a href="https://agentmods.dev/instructions/san-rat/latex-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/san-rat/latex-mcp/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/san-rat/latex-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/san-rat/latex-mcp/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 | $0.01684 | $0.01684 |
| Opus 5 | $0.00842 | $0.00842 |
| Sonnet 5 | $0.00337 | $0.00337 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
latex-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 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
An MCP server + web UI that lets LLMs (and humans) run a write → compile → check → revise loop on LaTeX documents. Compilation is done by a self-hosted instance of Overleaf's open-source CLSI (Common LaTeX Service Interface) running in Docker. See README.md for the high-level pitch.
Running the system
Three things must be up. The first two are started manually and must be running before MCP tools or the UI will work; the third is spawned by the LLM client, never run by hand.
# 1. CLSI (LaTeX compiler) — Docker container on :3013
docker compose up -d
# 2. Backend service — Node process on :4000 (HTTP + WebSocket)
node packages/backend/dist/index.js # or: npm run dev:backend (tsx watch)
# 3. MCP server — spawned over stdio by the LLM client per .mcp.json; do NOT run manually
# Web UI (optional) — Vite dev server on :5173
npm run dev --workspace=@latex-mcp/web-ui
The MCP server connection is defined in .mcp.json (absolute path + BACKEND_URL). After rebuilding the MCP server, the LLM client must reconnect (restart the session) to pick up tool changes — you cannot hot-reload a connected MCP server mid-session.
Build
npm run build # builds shared + backend + mcp-server via tsc -b project references
npm run build --workspace=@latex-mcp/web-ui # builds web-ui SEPARATELY (tsc --noEmit + vite build)
The root tsc -b does NOT build web-ui. web-ui is deliberately excluded from the project-reference graph in tsconfig.json because it uses a different module/JSX/bundler-resolution config (Vite owns its build). Always build it with its own workspace command.
Tests
There is no automated test suite. Verification in this project is done manually:
- MCP tools: drive a real handshake over stdio (a throwaway Node client that spawns
packages/mcp-server/dist/index.jsand sendsinitialize→notifications/initialized→tools/call), or connect via a real client and call the tools. - Web UI: run it and check in a real browser (CLSI + backend must be up).
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 · 76 lines · 1,684 tokens per session scan A e625f8ee05f7
latex-mcp CLAUDE.md is an instructions file published in the GitHub repository san-rat/latex-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,684 tokens to every session, about $0.0084 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.