agent-kit / templates
AGENTS.md0 starsChanged 3 months agoMITView on GitHub
Instructions for AI coding agents working in this repository. Read SOURCE.md first — in every chat, before inferring from code or conversation. SOURCE.md is the persistent project record; chat history is not project memory. When you learn or change durable project facts (stack, architecture, decisions, deferrals, focus), update SOURCE.md. Append to Decisions and Deferred; rewrite Current focus when it shifts. Do not duplicate project facts in chat or in this file. Prefer SOURCE.md over this file or codebase inference when…
- Commits and pushes
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 repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/source/templates/CLAUDE.mdCLAUDE.md
- sourceSkill
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
23 rules. About 0 are common, 17 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈17
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Read SOURCE.md first — in every chat, before inferring from code or conversation.
- Distinctive: line 9
When you learn or change durable project facts (stack, architecture, decisions, deferrals, focus), update SOURCE.md.
- Distinctive: line 11
Prefer SOURCE.md over this file or codebase inference when they conflict.
- Distinctive: line 15
Always read Current focus and Overview first.
- Distinctive: line 16
Read other sections only when the task needs them (e.g.
- Distinctive: line 17
Never infer project facts from chat when the relevant SOURCE section exists.
- Distinctive: line 23
Run relevant tests or lint after substantive changes when applicable.
- Distinctive: line 29
Add comments only for non-obvious logic.
- Distinctive: line 37
Always use read-only git commands when you need repository state — e.g.
- Distinctive: line 38
Always update SOURCE.md when durable project facts change.
- Distinctive: line 39
Always ask the user to run builds manually when a build is needed.
- Very specific: line 40
Always use gh only for read-only PR review when needed — e.g.
- Distinctive: line 41
Always stop and report when an approach fails.
- Very specific: line 45
Never run write git commands unless the user explicitly asks — includes commit, push, tag, reset, rebase, and other operations that mutate …
- Distinctive: line 46
Never open pull requests unless the user explicitly asks.
- Very specific: line 47
Never use gh for write, push, edit, or change actions — includes gh pr create, gh pr merge, gh issue create, and similar mutating commands.
- Very specific: line 48
Never run build commands yourself — e.g.
- Very specific: line 49
Never run Docker build commands yourself — e.g.
- Very specific: line 50
Never run database migrations yourself — e.g.
- Distinctive: line 51
Never retry, loop, or switch to an alternative approach after a failure without the user's approval.
- Distinctive: line 52
Never rely on conversation history for project facts — read and update SOURCE.md instead.
- Distinctive: line 53
Never remove or overwrite SOURCE.md entries without reason.
- Distinctive: line 61
Before finishing, ensure changed behavior is covered by existing tests or manual steps documented in SOURCE.md.
≈ “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
Agents
Instructions for AI coding agents working in this repository.
Project context
Read SOURCE.md first — in every chat, before inferring from code or conversation. SOURCE.md is the persistent project record; chat history is not project memory.
When you learn or change durable project facts (stack, architecture, decisions, deferrals, focus), update SOURCE.md. Append to Decisions and Deferred; rewrite Current focus when it shifts. Do not duplicate project facts in chat or in this file.
Prefer SOURCE.md over this file or codebase inference when they conflict.
Reading SOURCE.md
- Always read Current focus and Overview first.
- Read other sections only when the task needs them (e.g. Commands before run/test work, Architecture before large refactors).
- Never infer project facts from chat when the relevant SOURCE section exists.
Workflow
- Confirm scope before large refactors or new dependencies.
- Match existing patterns in the codebase; read surrounding code before editing.
- Run relevant tests or lint after substantive changes when applicable.
Code changes
- Minimize diff scope; avoid unrelated edits.
- Preserve existing naming, types, and abstractions unless change is required.
- Add comments only for non-obvious logic.
Boundaries
<!-- source: boundaries-default -->Do:
- Always use read-only git commands when you need repository state — e.g.
git status,git diff,git log,git show. - Always update SOURCE.md when durable project facts change.
- Always ask the user to run builds manually when a build is needed.
- Always use
ghonly for read-only PR review when needed — e.g.gh pr view,gh pr diff,gh pr checks. - Always stop and report when an approach fails; wait for the user's explicit approval before retrying or trying another approach.
Do not:
- Never run write git commands unless the user explicitly asks — includes
commit,push,tag,reset,rebase, and other operations that mutate repository state. - Never open pull requests unless the user explicitly asks.
- Never use
ghfor write, push, edit, or change actions — includesgh pr create,gh pr merge,gh issue create, and similar mutating commands; always ask the user to run them and hand over the exact command. - Never run build commands yourself — e.g.
npm run build,flutter build,make,cargo build, or equivalent; the user runs builds manually. - Never run Docker build commands yourself — e.g.
docker build,docker compose build; the user runs Docker builds manually. - Never run database migrations yourself — e.g.
php artisan migrate,prisma migrate,pnpm db migrate,rails db:migrate, or equivalent; always ask the user to run migrations, including on local environments. - Never retry, loop, or switch to an alternative approach after a failure without the user's approval.
- Never rely on conversation history for project facts — read and update SOURCE.md instead.
- Never remove or overwrite SOURCE.md entries without reason.
<!-- /source: boundaries-default --><!-- Project-specific additions below -->Verification
Before finishing, ensure changed behavior is covered by existing tests or manual steps documented in SOURCE.md.
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.

