codex-evolution
AGENTS.md2 starsChanged 57 days agoMITView on GitHub
Build a small, real local application, not a mock UI. Read README.md and the relevant module before editing. Use python3 -m unittest discover -s tests -v for core regression checks. Browser tests are optional development tooling; explain what was and was not tested. Keep runtime dependencies at zero unless the requested feature provides a concrete reason to change that decision. Preserve aggregate-only report exports, explicit model consent, source references, and original-file read-only behavior. Use synthetic fixtures. Never commit real histories,…
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 repository4 other files it gives its agents.
- anti-bloat-reviewSkill
- collaboration-retrospectiveSkill
- instruction-auditSkill
- workflow-distillerSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 1 is common, 1 is distinctive, and 1 is very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- could be automatic: a setting could enforce it
- Very specific: line 5
Use python3 -m unittest discover -s tests -v for core regression checks.
- Distinctive: line 7
Keep runtime dependencies at zero unless the requested feature provides a concrete reason to change that decision.
- Common: line 9
Use synthetic fixtures. Never commit real histories, credentials, private instruction files or application databases.
≈ “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
Working on Codex Evolution
Build a small, real local application, not a mock UI. Read README.md and the relevant module before editing.
Use python3 -m unittest discover -s tests -v for core regression checks. Browser tests are optional development tooling; explain what was and was not tested.
Keep runtime dependencies at zero unless the requested feature provides a concrete reason to change that decision. Preserve aggregate-only report exports, explicit model consent, source references, and original-file read-only behavior.
Use synthetic fixtures. Never commit real histories, credentials, private instruction files or application databases. Do not weaken explicit user approvals to make an audit appear cleaner.
Proceed with requested, scoped implementation work; ask only when missing information materially blocks correctness or authorization. Finish with the actual change, validation results and remaining limitations. Do not claim a feature, test, deployment or API call succeeded without evidence.
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.