What is agent-skills AGENTS.md?

Repository instructions for agents working on a collection of reusable, installable skills. They describe the project, its folders, and which files agents may change.

Use them when editing or extending the repository, especially when deciding where files belong and which files are read-only.

They give agents one clear source of guidance and prevent confusion between distributed skills, development files, and documentation.

How catalyst-cooperative/agent-skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to catalyst-cooperative/agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/catalyst-cooperative/agent-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/catalyst-cooperative/agent-skills

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/catalyst-cooperative/agent-skills/agents-md/github.svg)](https://agentmods.dev/instructions/catalyst-cooperative/agent-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/catalyst-cooperative/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/catalyst-cooperative/agent-skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/catalyst-cooperative/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/catalyst-cooperative/agent-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,625 This file is loaded in full into every session.

When invoked 3,625 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03625	$0.03625
Opus 5.5	$0.01450	$0.01450
Sonnet 5.5	$0.00725	$0.00725
Haiku 4.5	$0.00363	$0.00363

Measured 2mo ago against content hash 8ba0396eae72, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-skills 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 2mo 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 · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

A note about this file. AGENTS.md is the single source of truth for repository-level agent guidance. CLAUDE.md is just a symlink to AGENTS.md to ensure compatibility with Claude. Do not treat CLAUDE.md as a separate file or try to edit it to keep it in sync with AGENTS.md

Project Overview

This repository contains shareable agent skills — reusable, installable prompts that give agents specialized knowledge and workflows. Skills live under skills/, each providing distributed agent-facing guidance and assets. Development-only tests, generators, and other validation artifacts live under dev/skills/.

Repository Structure

Important top-level paths:

skills/ - first-party skills authored in this repository. These are the skill files you may edit.
.agents/skills/ - installed dependency/support skills used while developing the first-party skills in this repository. Treat these as read-only inputs. Never edit files under this directory as part of work on this repo.
docs/ - Zensical-backed site content for human-facing documentation.
prompts/ - Saved prompts used in development and testing, not distributed with skills.
.github/ - CI and repository automation
pyproject.toml - Pixi environment, tool dependencies, and mdformat config
.pre-commit-config.yaml - canonical lint, format, and check definitions
.markdownlint.yaml - Markdown lint rules tuned to the repo's formatting style
skills-lock.json - pinned external skill dependencies and metadata
zensical.toml - documentation site configuration

Current first-party skills live under skills/

datapackage/ - generic Frictionless Data Package exploration skill
pudl/ - PUDL data-user skill

Python utilities for use by agents in skills live under paths like skills/<skill>/scripts/. These are small CLI tools not a large application framework.

Distribution Boundary

Everything under skills/<skill_name>/ is shipped with installed skills, including SKILL.md, references/, assets/, and (when present) scripts/. Do not mention repository-internal dev paths, test suites, or example-generation scripts in distributed skill content (for example, anything under dev/skills/). If guidance needs those artifacts at runtime, move the required artifacts into the distributed skill first.

Read the full file on GitHub · 312 lines

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.

2mo ago First seen · 312 lines · 3,625 tokens per session scan A 8ba0396eae72

Subscribe to this mod's changes

agent-skills AGENTS.md is an instructions file published in the GitHub repository catalyst-cooperative/agent-skills (3 stars, last pushed 5d ago), licensed MIT. It adds 3,625 tokens to every session, about $0.0145 per session on Opus 5.5. 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.

agent-skills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-skills AGENTS.mdcatalyst-cooperative/agent-skills	Instructions file	3	5d ago	MIT	A	3,625	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-skills: Instructions file for Codex