prove-it-mini / rules
CLAUDE.md1 starsChanged 23 days agoMITView on GitHub
- Before you say "done", "fixed" or "works": the test suite must pass. A Stop hook (.claude/prove-it/pytest_gate.py) runs the tests when you try to finish after changing code, and sends you back if they fail. - When the gate sends you back: fix the code. Do not edit, skip, delete or loosen tests to get green. If a test is wrong, stop and say so. - Claims need evidence the user can re-run: a command and its output, a test…
In this repository4 other files it gives its agents.
- rules/AGENTS.mdAGENTS.md
- checkSkill
- setupSkill
- teardownSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 4
Before you say "done", "fixed" or "works": the test suite must pass.
- Distinctive: line 5
When the gate sends you back: fix the code.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
<!-- prove-it:begin (added by Prove-It Mini; ./install.sh --uninstall removes this block) -->Done means tests pass
- Before you say "done", "fixed" or "works": the test suite must pass. A Stop hook (
.claude/prove-it/pytest_gate.py) runs the tests when you try to finish after changing code, and sends you back if they fail. - When the gate sends you back: fix the code. Do not edit, skip, delete or loosen tests to get green. If a test is wrong, stop and say so.
- Claims need evidence the user can re-run: a command and its output, a test name, a file:line. "The code looks right" is not evidence.
- End every task with a short Not verified list: what you did not check and why.
<!-- prove-it:end -->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.