agent-toolkit
AGENTS.md85 starsChanged 21 days agoMITView on GitHub
A collection of reusable skills and rules for AI agents (Claude Code and similar). Everything must be self-contained and generic — reusable in any project — so avoid project-specific logic or assumptions. Rules are opt-in: a skill must work correctly with no rules installed, so never fix or extend a skill by adding a rule it depends on. Test harnesses, for a skill or an install script, live in test/<name>/ — repo-internal, never installed; their runs/ output dirs are gitignored.…
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 repository31 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agentify-projectSkill
- attach-to-ticketSkill
- check-ticket-implementationSkill
- compact-docs-writerSkill
- compact-skill-creatorSkill
- context-checkupSkill
- create-implementation-planSkill
- create-manual-test-instructionsSkill
- execute-plan-tasksSkill
- explain-in-simple-languageSkill
- extract-pr-review-rulesSkill
- fetch-pr-reviewSkill
- fetch-ticketSkill
- fresh-eyes-reviewSkill
- grill-meSkill
- handoverSkill
- harden-artifactSkill
- maintainer-reviewSkill
- memory-doctorSkill
- prepare-promptSkill
- refine-pr-reviewSkill
- refine-ticketSkill
- review-code-assistantSkill
- review-ticketSkill
- run-nx-checksSkill
- self-improveSkill
- self-reviewSkill
- split-plan-tasksSkill
- use-conversational-languageSkill
- verify-understandingSkill
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 8
Test harnesses, for a skill or an install script, live in test/<name>/ — repo-internal, never installed.
≈ “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
Agent Toolkit Guide
A collection of reusable skills and rules for AI agents (Claude Code and similar). Everything must be self-contained and generic — reusable in any project — so avoid project-specific logic or assumptions. Rules are opt-in: a skill must work correctly with no rules installed, so never fix or extend a skill by adding a rule it depends on.
Test harnesses, for a skill or an install script, live in test/<name>/ — repo-internal, never
installed; their runs/ output dirs are gitignored. Planning documents go in .agents/plans/
(gitignored).
Docs
- docs/authoring-conventions.md — read before editing any skill, rule, doc, manifest or install script.
- docs/core-philosophy.md — the five pillars and their litmus test; read before creating or redesigning a skill, or when brainstorming toolkit direction.
- docs/contributor-setup.md — how this repo is wired for agents; read when hooking a new agent up to it.
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.