agent-packs
AGENTS.md0 starsChanged 24 days agoMITView on GitHub
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository9 other files it gives its agents.
- effective-goSkill
- git-commitSkill
- github-publishSkill
- github-releaseSkill
- github-topicsSkill
- matklad-architectureSkill
- nystrom-game-programming-patternsSkill
- ousterhout-software-designSkill
- silber-pixel-artSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use kebab-case for skill directories.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Repository Guidelines
Project Structure & Module Organization
skills/ contains reusable agent playbooks. Each skill lives in its own kebab-case directory with a SKILL.md entry point. Put detailed supporting guidance in that skill's references/ directory when needed. Root files such as README.md and LICENSE define project-level documentation and licensing. There is no dedicated test or shared assets directory.
Build, Test, and Development Commands
This repository has no build step or automated test suite. After editing a skill, review its Markdown links and manually exercise any commands or workflows affected by the change, including a representative failure path when practical.
Coding Style & Naming Conventions
Use kebab-case for skill directories. Keep guidance in skills/*/SKILL.md concise, procedural, and directly actionable. Organize longer background material into focused Markdown files under references/, and link to it from the skill entry point only where it supports the workflow.
Testing Guidelines
There is no automated coverage target. Check that every referenced file exists, every example is internally consistent, and instructions remain usable from a clean checkout. If executable tooling is added later, place tests next to the code they cover or under a new tests/ directory.
Commit & Pull Request Guidelines
Recent history favors short, imperative commits with optional Conventional Commit prefixes and scopes, such as feat(skills): add github-topics skill and docs: add skill install instructions. Follow that pattern when it improves clarity. Pull requests should explain user-visible behavior, list manual verification steps, link related issues, and include screenshots only when visual output changes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

