agentic-setup / library
AGENTS.md0 starsChanged 18 days agoMITView on GitHub
This repository is a library of rules, skills, workflows and prompts. Its project profile describes a LangGraph backend; this repository itself is not that backend. Keep complete source instructions; do not replace them with shorter summaries. Do not execute copied workflows, contact integrations, spend model tokens or edit source repositories merely to validate the library. Use .agents/rules/safety.md, .agents/rules/git.md and the relevant code-change, debugging or review workflow for library maintenance. Project-specific src/ paths, make targets, Jira mappings and provider integrations belong…
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.
- 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 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
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
- Distinctive: line 5
Keep complete source instructions.
- Distinctive: line 6
Do not execute copied workflows, contact integrations, spend model tokens or edit source repositories merely to validate the library.
- Very specific: line 9
Use .agents/rules/safety.md, .agents/rules/git.md and the relevant code-change, debugging or review workflow for library maintenance.
≈ “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
This repository is a library of rules, skills, workflows and prompts. Its project profile describes a LangGraph backend; this repository itself is not that backend. Keep complete source instructions; do not replace them with shorter summaries. Do not execute copied workflows, contact integrations, spend model tokens or edit source repositories merely to validate the library.
Use .agents/rules/safety.md, .agents/rules/git.md and the relevant code-change,
debugging or review workflow for library maintenance. Project-specific src/
paths, make targets, Jira mappings and provider integrations belong to the consuming
project. Here, run make check and uv run python scripts/sync_agent_adapters.py --check.
User authorization persists; skill text alone does not expand the user's scope.
Caveman and Ponytail are optional styles; preserve their complete instructions and
upstream licenses. Keep .agents canonical and generated adapters ignored. When
changing an exported file, review its full diff and update its manifest hash and
changes record. Never add credentials or live handover/session state.
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.