agent-smitt
AGENTS.md4 starsChanged 15 days agoMITView on GitHub
This repository is the source of truth for the skills under skills/. When creating or editing agent instructions, apply writing-for-agents, including its rules for conditional context pointers. - Keep each skill and all of its relative references in one complete directory tree. - Give every skill a unique name in its SKILL.md front matter. - Put stable engineering skills under skills/engineering and stable personal workflow skills under skills/productivity. Keep experiments and private maintenance tools outside the public catalog. - Run…
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 31,700 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 repository31 other files it gives its agents.
- ask-smittSkill
- change-walkthroughSkill
- closeoutSkill
- codebase-designSkill
- code-reviewSkill
- deliver-specSkill
- deliver-ticketSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- grill-with-docsSkill
- implementSkill
- improve-codebase-architectureSkill
- prototypeSkill
- prSkill
- researchSkill
- resolving-merge-conflictsSkill
- review-feedbackSkill
- setup-federated-workflowSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wayfinderSkill
- wizardSkill
- grillingSkill
- grill-meSkill
- handoffSkill
- teachSkill
- to-questionnaireSkill
- wait-whatSkill
- writing-for-agentsSkill
The file
We split this AGENTS.md into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 5
When creating or editing agent instructions, apply writing-for-agents, including its rules for conditional context pointers.
- Distinctive: line 9
Keep each skill and all of its relative references in one complete directory tree.
- Very specific: line 12
Put stable engineering skills under skills/engineering and stable personal workflow skills under skills/productivity.
- Distinctive: line 15
Run the installer tests after changing skill layout or installation behavior.
- Distinctive: line 16
Do not add generated Codex symlinks to this repository.
- Very specific: line 17
Keep linked reference sources in their owning directories.
- Very specific: line 20
Keep the public catalog in docs/skills.md and workflow guide in docs/workflow.md consistent with the retained skills.
≈ “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
This repository is the source of truth for the skills under skills/.
When creating or editing agent instructions, apply writing-for-agents, including its rules for conditional context pointers.
- Keep each skill and all of its relative references in one complete directory tree.
- Give every skill a unique
namein itsSKILL.mdfront matter. - Put stable engineering skills under
skills/engineeringand stable personal workflow skills underskills/productivity. Keep experiments and private maintenance tools outside the public catalog. - Run the installer tests after changing skill layout or installation behavior.
- Do not add generated Codex symlinks to this repository.
- Keep linked reference sources in their owning directories. Regenerate
references/bundled/withpython3 bin/sync-skill-references; do not edit generated copies directly. Run its--checkmode before delivery. - Keep the public catalog in
docs/skills.mdand workflow guide indocs/workflow.mdconsistent with the retained skills.
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.

