big-brain CLAUDE.md

big-brain CLAUDE.md is an instructions file for coding agents from probelabs/big-brain. It costs 864 tokens per session, scanned A, original, MIT.

Project instructions for BigBrain, including how to test its ChatGPT Desktop mode and direct MCP mode. MCP is a way for an AI assistant to call a program's tools.

In plain words
What is it for?
It helps run automated ChatGPT Desktop tests, direct MCP tests, and the MCP Inspector, with options for terminals, loops, sounds, and notifications.
Why use it?
It gives developers the required setup, commands, and options for checking that BigBrain works.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/probelabs/big-brain/claude-md
Clone the repo
git clone --depth 1 https://github.com/probelabs/big-brain

Wrote 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.

agentmods badge for big-brain CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/probelabs/big-brain/claude-md.svg)](https://agentmods.dev/instructions/probelabs/big-brain/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/probelabs/big-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/probelabs/big-brain/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 864 This file is loaded in full into every session.
When invoked 864 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00864 $0.00864
Opus 5 $0.00432 $0.00432
Sonnet 5 $0.00173 $0.00173
Haiku 4.5 $0.00086 $0.00086

Measured 4d ago against content hash 8af04b8f32dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

big-brain 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.

CLAUDE.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BigBrain Project Documentation

Testing BigBrain

Testing ChatGPT Mode

The ChatGPT mode allows BigBrain to automatically query ChatGPT Desktop and return responses without manual intervention.

Prerequisites
Running Tests
  1. Test ChatGPT Mode Directly
node scripts/tests/test_chatgpt_mode.js

This will:

  • Start BigBrain with --chatgpt flag
  • Send a test question via MCP protocol
  • Automatically query ChatGPT Desktop
  • Return the response (takes 30-60 seconds)
  1. Test Manual Mode (Default)
node scripts/tests/test_mcp_direct.js
  1. Test with MCP Inspector
npm run inspector -- --chatgpt

Then use the web UI to call the ask_big_brain tool.

Available Command-Line Flags

  • --chatgpt - Enable automatic ChatGPT Desktop integration
  • --terminal <app> - Specify terminal app for ChatGPT mode (Terminal, iTerm, Warp, Alacritty)
  • --loop <prompt> - Enable loop mode for multi-agent systems
  • --disable-sound - Disable sound notifications
  • --disable-notification - Disable dialog notifications
  • --max-tokens <number> - Set custom token limit (default: 40000)

Testing Workflow

  1. Build the project: npm run build
  2. Copy UI reader to build: cp scripts/chatgpt/chatgpt_ui_reader_ultrafast.js build/
  3. Run test: node scripts/tests/test_chatgpt_mode.js

Deployment

Cloudflare Pages Deployment

To deploy the website to Cloudflare Pages and make it available at https://probelabs.com/big-brain/:

1. Deploy the Site
npx wrangler pages deploy site/ --project-name big-brain
2. Get the Latest Deployment URL
npx wrangler pages deployment list --project-name big-brain

Copy the latest deployment URL (e.g., https://ea82634b.big-brain-cyt.pages.dev)

3. Update Worker with Latest URL

Edit worker.js line 10 to use the latest deployment URL:

const pagesUrl = `https://[latest-hash].big-brain-cyt.pages.dev${newPath}${url.search}`;

Read the full file on GitHub · 107 lines

Changes

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.

  1. 4d ago First seen · 107 lines · 864 tokens per session scan A 8af04b8f32dc

Subscribe to this mod's changes

big-brain CLAUDE.md is an instructions file published in the GitHub repository probelabs/big-brain (4 stars, last pushed 12mo ago), licensed MIT. It adds 864 tokens to every session, about $0.0043 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.

Related

Other instructions, from other repositories