Borrowing it
Nothing to install: this file belongs to MarvelCollin/overleaf-claude-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/MarvelCollin/overleaf-claude-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/MarvelCollin/overleaf-claude-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/marvelcollin/overleaf-claude-mcp/agents-md)<a href="https://agentmods.dev/instructions/marvelcollin/overleaf-claude-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/marvelcollin/overleaf-claude-mcp/agents-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/marvelcollin/overleaf-claude-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/marvelcollin/overleaf-claude-mcp/agents-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 | $0.01405 | $0.01405 |
| Opus 5.5 | $0.00562 | $0.00562 |
| Sonnet 5.5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
overleaf-claude-mcp AGENTS.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 13d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting this up as an agent
You are Claude, or another coding agent, and someone asked you to set this up. Read this before running anything. The goal is to finish in one pass and interrupt the user at most once.
The only thing you cannot do
Authentication needs an Overleaf session. You must never type or ask for the user's password, and you must never handle it. Everything else in this document you can do yourself without asking.
There are three ways to get a session. Pick the first one that applies. Do not ask the user which to use.
| Situation | Method | User involvement |
|---|---|---|
| Machine has a display, browser signed in to Overleaf already | npm run login:browser -- --real-profile |
Close their browser first |
| Machine has a display, not signed in anywhere | npm run login |
They sign in, one time |
| No display, such as SSH, Docker, CI, a remote sandbox | npm run login:paste |
They paste one cookie, one time |
Detect which case you are in before choosing. On Linux, no display means DISPLAY and WAYLAND_DISPLAY are both unset.
One shot setup
Run this and nothing else. Do not narrate each step to the user.
npm run agent-setup
It installs, builds, verifies the server starts, obtains a session by whichever method fits the machine, reads one of the user's real projects to prove the connection, and registers the server with Claude Code at user scope. It is fully non interactive, so it will never hang waiting on a prompt.
Read the last two lines. They are the contract.
RESULT: READY | NEED_COOKIE | FAILED
NEXT_ACTION: <exactly what to do next>
| RESULT | Exit code | What you do |
|---|---|---|
READY |
0 | Tell the user to restart Claude. You are done. |
NEED_COOKIE |
2 | Ask the user for the cookie once, then rerun with OVERLEAF_SESSION_COOKIE set |
FAILED |
1 | Report the [fail] line to the user. Do not improvise a workaround. |
The NEED_COOKIE output contains the exact wording to use when asking. Use it verbatim, then:
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.
- 13d ago Changed · +38 tokens per session c5645bb652e6
- 2mo ago First seen · 115 lines · 1,367 tokens per session scan A 8ac43c8a8836
overleaf-claude-mcp AGENTS.md is an instructions file published in the GitHub repository MarvelCollin/overleaf-claude-mcp (5 stars, last pushed 13d ago), licensed MIT. It adds 1,405 tokens to every session, about $0.0056 per session on Opus 5.5. 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.
overleaf-claude-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| overleaf-claude-mcp AGENTS.mdMarvelCollin/overleaf-claude-mcp | Instructions file | 5 | 13d ago | MIT | A | 1,405 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |