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/probelabs/big-brain/claude-mdgit clone --depth 1 https://github.com/probelabs/big-brainWrote 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/probelabs/big-brain/claude-md)<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>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 | $0.00864 | $0.00864 |
| Opus 5 | $0.00432 | $0.00432 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00086 | $0.00086 |
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.
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
- ChatGPT Desktop app must be installed (https://chatgpt.com/desktop)
- macOS accessibility permissions must be granted to Terminal
Running Tests
- 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)
- Test Manual Mode (Default)
node scripts/tests/test_mcp_direct.js
- 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
- Build the project:
npm run build - Copy UI reader to build:
cp scripts/chatgpt/chatgpt_ui_reader_ultrafast.js build/ - 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}`;
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 · 107 lines · 864 tokens per session scan A 8af04b8f32dc
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.
Other instructions, from other repositories
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.