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/wham/github-brain/agents-mdgit clone --depth 1 https://github.com/wham/github-brainWhat 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 | $0.00103 | $0.00103 |
| Opus 5 | $0.00051 | $0.00051 |
| Sonnet 5 | $0.00021 | $0.00021 |
| Haiku 4.5 | $0.00010 | $0.00010 |
Grade A, and why
github-brain 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 2d 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.
What it actually says
- The app is coded in Markdown file
main.mdand compiled to Go code using the instructions in.github/prompts/compile.prompt.md. - IMPORTANT: When prompted to make any changes, start by updating
main.mdand letting me to review the changes before touching the Go code. - Everything must fit into a single
main.md/main.gofile pair. Avoid creating new files. README.mdcontains usage instructions. Read it to understand how the app should work.
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.
- 2d ago First seen · 4 lines · 103 tokens per session scan A c87424be7be2
github-brain AGENTS.md is an instructions file published in the GitHub repository wham/github-brain (78 stars, last pushed 6mo ago), licensed MIT. It adds 103 tokens to every session, about $0.0005 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 2026-08-30.
Other instructions, from other repositories
pentagi CLAUDE.md
Instructions for vxcontrol/pentagi, covering claude.md, core interaction rules, project overview, build & development commands and backend (run from backend/).
mockd CLAUDE.md
Instructions for getmockd/mockd, covering mockd — ai agent instructions, what is mockd?, mcp server, ports and cli quick reference.
mockd copilot-instructions.md
Instructions for getmockd/mockd, covering mockd instructions for github copilot, mockd mock server, mcp server, ports and cli commands.
pyck-oss AGENTS.md
AGENTS.md instructions for pyck-ai/pyck-oss, covering pyck, for ai agents, documentation, architecture overview and code review.
pyck-oss CLAUDE.md
Claude Code instructions for pyck-ai/pyck-oss, a project described as: An Open-Source warehousing framework, engineered for the AI era.
ollama CLAUDE.md
Instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.