syokan / coding
AGENTS.md0 starsChanged 18 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 31,700 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 repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/brand-assets/AGENTS.mdAGENTS.md
- .agents/skills/brand-assets/CLAUDE.mdCLAUDE.md
- .agents/skills/coding/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- brand-assetsSkill
- codingSkill
- syokanSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 3
Read SKILL.md, then only the routed reference needed for the work.
- Very specific: line 4
Keep references/*.md as one-line bullets with observable facts, commands, paths, and rationale.
- Distinctive: line 6
Treat automated session-retro changes as review packets: a human decides whether to merge, revise, or reject them.
- Distinctive: line 8
Prefer checks that exercise public behavior over tests that only prove an internal helper's shape.
≈ “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
Coding Skill Governance
- Read
SKILL.md, then only the routed reference needed for the work. - Keep
references/*.mdas one-line bullets with observable facts, commands, paths, and rationale; do not record one-off task history. - Validate a changed rule against current source and focused tests before updating it; browser-only renderer behavior requires a real dev-browser reproduction.
- Treat automated session-retro changes as review packets: a human decides whether to merge, revise, or reject them.
- For snapshot envelope or store behavior changes, add or update regression tests around old on-disk data and dedup responses.
- Prefer checks that exercise public behavior over tests that only prove an internal helper's shape.
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.