agentic-setup
AGENTS.md0 starsChanged 18 days agoMITView on GitHub
The root .agents/ directory is the main environment. library/ preserves the older instruction collection and its generator. Read .agents/README.md, core Caveman/project-flow and the relevant rules before making changes. Preserve complete upstream instructions and license notices. When changing an exported file, update its hash and adaptation record in source-manifest.json. Keep generated adapters, credentials and live session state out of Git. Do not execute copied workflows or contact integrations to validate the setup. Read .agents/skills/caveman-commit/SKILL.md before staging or composing commits. Preserve existing…
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 repository11 other files it gives its agents.
- library/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- cavecrewSkill
- councilSkill
- herdrSkill
- humanizerSkill
- specsmdSkill
- caveman-commitSkill
- cavemanSkill
- project-flowSkill
- repo-changelogSkill
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
- Common: line 13
Keep generated adapters, credentials and live session state out of Git.
- Distinctive: line 14
Do not execute copied workflows or contact integrations to validate the setup.
- Very specific: line 16
Read .agents/skills/caveman-commit/SKILL.md before staging or composing commits.
≈ “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
Agentic setup
The root .agents/ directory is the main environment. library/ preserves the
older instruction collection and its generator. Read .agents/README.md, core
Caveman/project-flow and the relevant rules before making changes.
make ai simple/make ai full: install repository-local host guidance.make ai-test: run isolated adapter, installation and guardrail tests.make check: validate metadata, source hashes, Python syntax and all tests.
Preserve complete upstream instructions and license notices. When changing an
exported file, update its hash and adaptation record in source-manifest.json.
Keep generated adapters, credentials and live session state out of Git.
Do not execute copied workflows or contact integrations to validate the setup.
Read .agents/skills/caveman-commit/SKILL.md before staging or composing commits.
Preserve existing user changes. Commit, push and external actions require the
user's authorization.
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.