card-skill
AGENTS.md0 starsChanged 31 days agoMITView on GitHub
Build card-skill. Read docs/STATUS.md first: what works, what is unverified, what is next. Then docs/DECISIONS.md before you change behavior; supersede an entry, do not rewrite it. UI work reads DESIGN.md and TASTE.md. The skill is skill/; its policy is skill/SKILL.md; the format is skill/reference/format.md (boards are Org: board.org). The agent never edits skill/runtime/ to style one board: meaning decides looks. Test: npm test. A change to the format updates format.md, a template, and a test together. An explanation for a…
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 31,439 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 repositoryOne other file it gives its agents.
- card-skillSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Read docs/STATUS.md first: what works, what is unverified, what is next.
- Very specific: line 12
Test: npm test. A change to the format updates format.md, a template, and a test together.
- Distinctive: line 18
Use a diagram when the structure is the claim.
≈ “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
Super goal
Build card-skill.
Resume here
Read docs/STATUS.md first: what works, what is unverified, what is next.
Then docs/DECISIONS.md before you change behavior; supersede an entry, do not rewrite it.
UI work reads DESIGN.md and TASTE.md.
The skill is skill/; its policy is skill/SKILL.md; the format is skill/reference/format.md (boards are Org: board.org).
The agent never edits skill/runtime/ to style one board: meaning decides looks.
Test: npm test. A change to the format updates format.md, a template, and a test together.
Output
An explanation for a person is a discardable HTML page the eye can check. Sentences stay near ASD-STE100: one fact each, plain verbs. Use a diagram when the structure is the claim. Use video only when someone will watch it. A polished page at the wrong altitude is a failed page.
Loop
Code we keep: one change, approaches before code, a test, a commit. Code we throw away: label it throwaway. The human reads and decides. The agent files, compiles, and shows the work.
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.