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/samzong/agent-brains/agents-mdgit clone --depth 1 https://github.com/samzong/agent-brainsWrote 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/samzong/agent-brains/agents-md)<a href="https://agentmods.dev/instructions/samzong/agent-brains/agents-md"><img src="https://agentmods.dev/badge/instructions/samzong/agent-brains/agents-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 | $0.00547 | $0.00547 |
| Opus 5 | $0.00273 | $0.00273 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
agent-brains 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 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository stores portable agent-brain definitions and supporting loader tooling.
agents/<agent-name>/contains one agent brain. Each brain hasAGENTS.md,SOUL.md, andMEMORY.md.agents/<agent-name>/memories/stores focused long-term memory files.agents/<agent-name>/skills/<skill-name>/SKILL.mdstores brain-specific reusable methods.agents/<agent-name>/workflows/<workflow-name>/WORKFLOW.mdstores brain-specific SOPs.skills/agent-loader/contains the shared loader skill and its helper script.docs/AGENT_BRAIN_SPEC.mddefines the canonical brain format.scripts/validate_brains.pyvalidates required files, frontmatter, names, and workflow layout.
Build, Test, and Development Commands
There is no application build step. This is a Markdown and Python validation repository.
git ls-fileslists tracked project files.rg -n "<term>" . -g '!/.git/**' -g '!/.serena/**'searches brain content.uv run python scripts/validate_brains.pyruns the local validation gate.
Run validation before opening a PR or after changing any agents/, skills/, workflows/, or spec file.
Coding Style & Naming Conventions
Use Markdown for brain content and Python only for repository tooling. Keep prose direct and durable; do not turn session notes into permanent rules.
Agent, skill, and workflow names must be lowercase kebab-case, matching their directory names, for example dify-rag-pm or agent-loader. Required frontmatter:
- Brain
AGENTS.md:name,description SKILL.md:name,descriptionWORKFLOW.md:name,description
Workflow lifecycle is managed by explicit updates or removals.
Testing Guidelines
The validation script is the test suite. It checks required structure, YAML frontmatter, directory/name consistency, skill layout, and workflow layout. Add new coverage to scripts/validate_brains.py when adding new repository-level format rules.
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 · 46 lines · 547 tokens per session scan A 299c4f51e997
agent-brains AGENTS.md is an instructions file published in the GitHub repository samzong/agent-brains (6 stars, last pushed 2mo ago), licensed MIT. It adds 547 tokens to every session, about $0.0027 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
repository-harness CLAUDE.md
Instructions for hoangnb24/repository-harness, covering project rules and harness.
AGENTS.md AGENTS.md
Instructions for Anbeeld/AGENTS.md, covering global instructions, priorities, boundaries, uncertainty and evidence.
agent-context-kit AGENTS.md
AGENTS.md instructions for Cynrath/agent-context-kit, covering agents.md — agentcontextkit, controlled-release governance, canonical entry points (read in this order), ackit-first / task-first / docs-first workflow and continuous execution hard rule (explicit user mandate).
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.
agent-context-kit CLAUDE.md
Claude Code instructions for Cynrath/agent-context-kit, covering claude project context, dogfood / ackit-first, workflow, commit completeness hard rule and stack.
agent-context-kit copilot-instructions.md
Copilot instructions for Cynrath/agent-context-kit, covering copilot instructions, maintenance note, governance, workflow and commit completeness hard rule.