BagelSkills
AGENTS.md2 starsChanged 4 months 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 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 repository10 other files it gives its agents.
- agent-proof-workSkill
- anti-slop-frontendSkill
- blast-radiusSkill
- decision-tribunalSkill
- failure-museumSkill
- grill-me-until-its-clearSkill
- launch-forensicsSkill
- repo-archaeologistSkill
- scope-sniperSkill
- ux-friction-hunterSkill
The file
We split this AGENTS.md into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 3
Follow the current Agent Skills specification at https://agentskills.io/specification.
- Distinctive: line 4
Keep skills portable across clients.
- Distinctive: line 5
Every behavior-changing rule needs a reason, completion criterion, or evaluation.
- Very specific: line 6
Put always-needed procedure in SKILL.md and branch-specific detail in references/.
- Distinctive: line 7
Add both should-trigger and should-not-trigger cases for description changes.
- Very specific: line 8
Run python scripts/validate.py before committing.
- Distinctive: line 9
Never weaken validation to make a broken skill pass.
≈ “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 instructions
- Follow the current Agent Skills specification at https://agentskills.io/specification.
- Keep skills portable across clients; do not require one vendor unless the skill's purpose demands it.
- Every behavior-changing rule needs a reason, completion criterion, or evaluation.
- Put always-needed procedure in SKILL.md and branch-specific detail in references/.
- Add both should-trigger and should-not-trigger cases for description changes.
- Run
python scripts/validate.pybefore committing. - Never weaken validation to make a broken skill pass.
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.

