hyper-taste
AGENTS.md1 starsChanged 4 days agoMITView on GitHub
A collection of agent skills. Each skill lives in skills/<name>/ and is installed into users' projects as is, so put nothing there that isn't for the agent using the skill. - Skills describe outcomes and how to judge them. No check scripts, templates or examples to copy: agents use their own tools. A rule a script would enforce is written as a rule. - One owner per job. Before adding a rule, find the skill that owns the topic and…
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 32,671 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 repository20 other files it gives its agents.
- agents-mdSkill
- app-iconSkill
- buildSkill
- cloneSkill
- debugSkill
- design-systemSkill
- docker-optimizeSkill
- improve-loopSkill
- mac-appSkill
- mac-designSkill
- product-briefSkill
- quality-barSkill
- refactorSkill
- researchSkill
- reviewSkill
- start-hereSkill
- stop-overthinkingSkill
- ui-directorSkill
- user-storiesSkill
- ux-designSkill
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 13
After any change to skills or manifests, run node scripts/validate.mjs and claude plugin validate ..
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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
Hyper Taste
A collection of agent skills. Each skill lives in skills/<name>/ and is installed into users'
projects as is, so put nothing there that isn't for the agent using the skill.
- Skills describe outcomes and how to judge them. No check scripts, templates or examples to copy: agents use their own tools. A rule a script would enforce is written as a rule.
- One owner per job. Before adding a rule, find the skill that owns the topic and put it there; other skills point to it by name. Never repeat content between skills.
- Credit work we build on with one line in the README's Credits, nowhere else: no notices or source lines in skills.
- Adding a skill or cutting a release: follow
CONTRIBUTING.md. - After any change to skills or manifests, run
node scripts/validate.mjsandclaude plugin validate .. - Human docs go in
docs/<name>/, slash commands incommands/<name>/, evals inevals/<name>/. The ui-director before and after pairs indocs/ui-director/pairs/are eval fixtures and the live gallery; keep each pair'sbefore.htmlandafter.html.
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.

