the-rookery
AGENTS.md15 starsChanged 12 days agoMITView on GitHub
This is a public open-source repository. Its working directory holds only this repository's own source, tests, docs, and configuration. Anything generated for the user rather than for the repo, along with its supporting files (builders, renders, previews, inspection files, dependency links), goes in a per-run temporary directory outside the working directory, and final artifacts go only to an explicitly approved external or private destination. The root outputs/ directory stays ignored as a privacy safeguard; it is not an approved storage…
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 31,439 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.
- checking-simplicitySkill
- coordinating-workSkill
- creating-portable-skillsSkill
- managing-issuesSkill
- managing-personal-crmSkill
- personal-chief-of-staffSkill
- reviewing-meetingsSkill
- storm-researchSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Before staging or committing, inspect all untracked paths and confirm that no personal or business artifacts are present.
- Very specific: line 20
Keep plans, brainstorms, ideation, raw dogfood notes, and point-in-time reports in the ignored working paths named in .gitignore.
- Distinctive: line 36
Before changing a skill package, read SKILLS.md for this repository's package, evaluation, and evidence requirements.
- Very specific: line 39
When implementing or debugging, search docs/solutions/ for relevant prior solutions and read matches.
- Distinctive: line 42
Read CONCEPTS.md for this project's shared vocabulary when orienting to the repo or discussing its concepts.
≈ “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
Repository Agent Guidance
Private and generated artifacts
This is a public open-source repository. Its working directory holds only this repository's own source, tests, docs, and configuration. Anything generated for the user rather than for the repo, along with its supporting files (builders, renders, previews, inspection files, dependency links), goes in a per-run temporary directory outside the working directory, and final artifacts go only to an explicitly approved external or private destination.
The root outputs/ directory stays ignored as a privacy safeguard; it is not
an approved storage location.
Before staging or committing, inspect all untracked paths and confirm that no personal or business artifacts are present.
Working artifacts
Keep plans, brainstorms, ideation, raw dogfood notes, and point-in-time reports
in the ignored working paths named in .gitignore. They may live for the life
of a worktree, but the final pull request and default branch must not contain
or depend on them. Preserve the outcome in its canonical home: code and tests
for behavior, an ADR for a lasting architectural choice, docs/solutions/ for
a reusable learning, or the current root RELEASING.md for operating and
shipping procedures.
Research is durable only when the repository will maintain it as a current source. Keep temporary audits and findings with the issue, pull request, or other reporting system. When a source issue exists, record material scope changes and follow-up work there before merge; a routine completion summary or copy of the plan is unnecessary.
Documented solutions and vocabulary
Before changing a skill package, read SKILLS.md for this repository's package, evaluation, and evidence requirements.
When implementing or debugging, search docs/solutions/ for relevant prior
solutions and read matches.
Read CONCEPTS.md for this project's shared vocabulary when orienting to the repo or discussing its concepts.
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.

