ai-tools / rules
AGENTS.md0 starsChanged 18 days agoMITView on GitHub
A repo's own AGENTS.md is its rulebook and wins over this file. Before writing app code in a repo that has none, load the standards skill. For anything I read (replies, docs, PR bodies, UI copy): plain words, active voice, one idea per sentence. Periods and commas only, never em dashes. No puffery, no chatbot phrases. Say what a thing does, not how it feels. Build every app's UI from its own component library: styles live only in src/components/ui/, screens…
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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- convexSkill
- design-planSkill
- frontend-designSkill
- new-projectSkill
- prdSkill
- prSkill
- retroSkill
- setup-hostingSkill
- standardsSkill
- unslopSkill
- writing-for-agentsSkill
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 17
Update CHANGELOG.md for meaningful changes.
≈ “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
Global rules
A repo's own AGENTS.md is its rulebook and wins over this file. Before writing app code in a repo that has none, load the standards skill.
Writing
For anything I read (replies, docs, PR bodies, UI copy): plain words, active voice, one idea per sentence. Periods and commas only, never em dashes. No puffery, no chatbot phrases. Say what a thing does, not how it feels.
UI
Build every app's UI from its own component library: styles live only in src/components/ui/, screens compose those components with no className or style, and /dev/ui shows every one. The standards skill has the full setup.
Git
- Conventional Commits:
feat:,fix:,chore:,refactor:. - Branch as
feature/{name}unless the repo says otherwise. Squash before merging. - Update
CHANGELOG.mdfor meaningful 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.