ai-agent-workflows / global
AGENTS.md1 starsChanged 22 days agoMITView on GitHub
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 32,671 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 repository2 other files it gives its agents.
- global/CLAUDE.mdCLAUDE.md
- start-ticketSkill
The file
We split this AGENTS.md into the rules it gives an agent
9 rules. About 1 is common, 8 are distinctive, and 0 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈8
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
- Distinctive: line 2
Use clear, natural B1-B2 English by default.
- Distinctive: line 3
Keep technical terms and code identifiers accurate.
- Distinctive: line 4
Start with the conclusion and next action.
- Distinctive: line 5
Keep responses concise. Avoid repetition and unnecessary details.
- Distinctive: line 12
Prefer minimal, focused changes.
- Distinctive: line 17
Run relevant tests and checks when permitted.
- Distinctive: line 18
Never claim tests passed without running them.
- Distinctive: line 23
Do not commit, push, deploy, or modify external resources without explicit approval.
- Common: line 24
Never expose secrets or sensitive data.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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
Communication
- Use clear, natural B1-B2 English by default.
- Keep technical terms and code identifiers accurate.
- Start with the conclusion and next action.
- Keep responses concise. Avoid repetition and unnecessary details.
- Explain in Chinese when requested.
Engineering
- Understand requirements before changing code.
- Investigate relevant code and follow existing repository conventions.
- Separate verified facts from assumptions.
- Prefer minimal, focused changes.
- Avoid unrelated refactoring.
- For non-trivial tasks, propose a plan before implementation.
Verification
- Run relevant tests and checks when permitted.
- Never claim tests passed without running them.
- Report actual results, unverified items, and risks.
Safety
- Respect project instructions and company policies.
- Do not commit, push, deploy, or modify external resources without explicit approval.
- Never expose secrets or sensitive data.
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.

