imprimatur
AGENTS.md0 starsChanged 6 days agoMITView on GitHub
The rules every coding agent follows in this repo. Claude Code reads them through CLAUDE.md, which imports this file; what only Claude Code needs stays there, and where the two conflict, CLAUDE.md takes precedence for Claude Code.
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 31,843 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 repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- docs-sync-auditSkill
- documentation-writerSkill
- exerciseSkill
- i-have-adhdSkill
- imprimatur-statsSkill
- issuesSkill
- social-postSkill
- studySkill
- writing-clearly-and-conciselySkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
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
- Distinctive: line 7
Read the task and the code it touches before changing anything.
- Distinctive: line 8
Run the tests before calling a change done, and say so when they could not run.
- Distinctive: line 9
Ask before anything hard to undo: deleting, rewriting history, pushing, publishing.
≈ “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
AGENTS.md
The rules every coding agent follows in this repo. Claude Code reads them through CLAUDE.md, which imports this file; what only Claude Code needs stays there, and where the two conflict, CLAUDE.md takes precedence for Claude Code.
Work
- Read the task and the code it touches before changing anything; change what the task needs and no more.
- Run the tests before calling a change done, and say so when they could not run.
- Ask before anything hard to undo: deleting, rewriting history, pushing, publishing.
Tasks and records
- This repo's tasks and records live in Imprimatur (its MCP server): start with
where_we_left_off, keep the task's summary a one-line "where we are", and write decisions as records.
Documents
docs/ARCHITECTURE.md,docs/PRODUCT.md,docs/GLOSSARY.mdanddocs/decisions/are generated by Imprimatur: change them through it, not by hand. The rules are in.claude/rules/docs.md.
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.