github-brain AGENTS.md

Project instructions for an experimental GitHub service that uses a local database and generates Go code from Markdown.

In plain words
What is it for?
They guide changes to main.md, compilation through the project's prompt file, the matching main.go output, and use of README.md for behavior.
Why use it?
They establish where changes should be made and which project files and documentation to check before editing the generated code.

Instructions file for CodexOpenCode

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/wham/github-brain/agents-md
Clone the repo
git clone --depth 1 https://github.com/wham/github-brain

Made for: Codex, OpenCode.

Per session 103 This file is loaded in full into every session.
When invoked 103 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 $0.00103 $0.00103
Opus 5 $0.00051 $0.00051
Sonnet 5 $0.00021 $0.00021
Haiku 4.5 $0.00010 $0.00010

Measured 2d ago against content hash c87424be7be2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 4 lines

What it actually says

  • The app is coded in Markdown file main.md and compiled to Go code using the instructions in .github/prompts/compile.prompt.md.
  • IMPORTANT: When prompted to make any changes, start by updating main.md and letting me to review the changes before touching the Go code.
  • Everything must fit into a single main.md / main.go file pair. Avoid creating new files.
  • README.md contains usage instructions. Read it to understand how the app should work.
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. 2d ago First seen · 4 lines · 103 tokens per session scan A c87424be7be2

Subscribe to this mod's changes

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.