What is AGENTS.md? How to write one your coding agents follow
AGENTS.md is a Markdown file that tells AI coding agents how to work on your repo. What it is, which tools read it, and how to write one that works.
Starter skills pack: 5 tested SKILL.md agent skills
Five validated agent skills (code review, pre-deploy check, Supabase RLS audit, PR description, SEO brief) plus a directory of official skill repos.
Our own skills, checked with the Agent Skills validator. They work in Claude Code, Codex and Cursor.
Preview: README.md
| Skill | Use it when you say… |
| --- | --- |
| `ai-code-review` | "Review this branch before I merge" |
| `pre-deploy-check` | "Is this ready to ship?" |
| `supabase-rls-audit` | "Check my Supabase tables are locked down" |
| `pr-description-writer` | "Write the PR description" |
| `seo-article-brief` | "Write an SEO brief for this topic" |
## Install
Copy the folders from `skills/` to:
What's inside
- 5 skill folders, each with a
SKILL.md SKILLS-DIRECTORY.md: official skill repos, with stars and licences
How to use it
- Unzip.
- Copy the skill folders you want to
.agents/skills/(Cursor, Codex) or.claude/skills/(Claude Code). - Ask for the task in plain words, for example "is this ready to ship?". The agent loads the matching skill.
Who it's for
Anyone who wants useful skills now, without writing them from scratch.
Related
Keep reading
Keep reading
How to run coding agents safely: permissions, sandboxes and secrets
How to run coding agents safely with Claude Code permission modes, Codex sandbox and approval settings, deny rules, and habits that keep secrets out of reach.
MCP security best practices: how to use MCP servers without leaking data
MCP security best practices for vibe coders: prompt injection risks, what the MCP spec requires, and a checklist to use MCP servers without leaking data.
Newsletter
The Codema publication. Consent is required. You are not subscribed until you confirm from the email, and nothing is stored if email delivery is not connected.