SuperReview
AGENTS.md3 starsChanged 53 days agoMITView on GitHub
SuperReview is a portable skill and standard-library Python helper. Keep the skill folder self-contained. Maintain the distinction between structural validation and review accuracy. Keep personal names, addresses, handles, private URLs, credentials, and proprietary source material out of source files, documentation, and examples. Use synthetic examples. Commit metadata may use GitHub attribution with a GitHub no-reply email address. Never publish reports, post reviews, or change repository visibility without explicit intent. Verify changes with python3 -m unittest discover -s tests -v, python3…
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 repositoryOne other file it gives its agents.
- superreviewSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 1 is common, 2 are distinctive, and 1 is very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Common: line 6
Keep personal names, addresses, handles, private URLs, credentials, and proprietary source material out of source files, documentation, and …
- Distinctive: line 8
Commit metadata may use GitHub attribution with a GitHub no-reply email address.
- Distinctive: line 9
Never publish reports, post reviews, or change repository visibility without explicit intent.
- Very specific: line 11
Verify changes with python3 -m unittest discover -s tests -v, python3 examples/demo.py, and python3 scripts/check_distribution.py.
≈ “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
Project guidance
SuperReview is a portable skill and standard-library Python helper. Keep the skill folder self-contained. Maintain the distinction between structural validation and review accuracy.
Keep personal names, addresses, handles, private URLs, credentials, and proprietary source material out of source files, documentation, and examples. Use synthetic examples. Commit metadata may use GitHub attribution with a GitHub no-reply email address. Never publish reports, post reviews, or change repository visibility without explicit intent.
Verify changes with python3 -m unittest discover -s tests -v, python3 examples/demo.py,
and python3 scripts/check_distribution.py. Add behavioral coverage for safety boundaries
you change. Do not bypass hooks. Avoid introducing runtime dependencies without a concrete need.
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.