pm-brain AGENTS.md

Instructions for using a project-management knowledge base called pm-brain with different coding agents.

In plain words
What is it for?
Use them when an agent starts work in a pm-brain folder and needs to follow its documentation.
Why use it?
They tell each agent which project documentation to read first, reducing the chance of using the wrong entry point.

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

Made for: Codex, OpenCode.

Per session 150 This file is loaded in full into every session.
When invoked 150 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 $0.00150 $0.00150
Opus 5 $0.00075 $0.00075
Sonnet 5 $0.00030 $0.00030
Haiku 4.5 $0.00015 $0.00015

Measured 3d ago against content hash d06091ce18a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-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 3d 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 · 6 lines

What it actually says

For agents

If you are Claude (Claude Code, Claude Desktop, Claude in the API): read CLAUDE.md.

If you are a different agent (Cursor, Codex, Aider, GitHub Copilot, others): start with README.md. The brain itself is a folder of markdown files plus one CLAUDE.md in the working directory. Any agent that can read a project-root CLAUDE.md can run the brain. The canonical skill lives at .claude/skills/pm-brain/ for environments that support the SKILL.md format.

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. 3d ago First seen · 6 lines · 150 tokens per session scan A d06091ce18a1

Subscribe to this mod's changes

pm-brain AGENTS.md is an instructions file published in the GitHub repository phuryn/pm-brain (537 stars, last pushed 3mo ago), licensed MIT. It adds 150 tokens to every session, about $0.0007 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.