ai-engineer / templates
AGENTS.md1 starsChanged 15 days agoMITView on GitHub
These rules apply in every session in this repository, in any coding agent. If the ready-to-merge skill is installed, run it before calling a change done. Otherwise apply engineering-bar. Replace (unknown) by running the explore-codebase skill, or fill the commands yourself from the README / CI config. Never invent a command that this repo does not actually have. Terms in Glossary come from this repo's code and docs, not from invented jargon.
- Reads credentials
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 repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- open-prSkill
- performanceSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- resolve-conflictsSkill
- revert-changeSkill
- review-changeSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- start-projectSkill
- upgrade-depsSkill
- verify-uiSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-prdSkill
- write-testsSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- could be automatic: a setting could enforce it
- Distinctive: line 5
Do not claim tests, types, lint, or builds passed unless this session ran the command and captured the output.
- Very specific: line 6
Do not commit secrets, .env files, credentials, or private keys.
- Distinctive: line 9
Do not force-push shared branches.
- Distinctive: line 10
Do not delete or skip a failing test to get a green run.
- Very specific: line 12
If the ready-to-merge skill is installed, run it before calling a change done.
≈ “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
Agent defaults
These rules apply in every session in this repository, in any coding agent.
- Do not claim tests, types, lint, or builds passed unless this session ran the command and captured the output.
- Do not commit secrets,
.envfiles, credentials, or private keys. - Match this repository's tools and style. Do not introduce a new stack or formatter.
- Smallest change that satisfies the request. Prefer reuse, the standard library, and native platform features over new code or new dependencies. No drive-by refactors.
- Do not force-push shared branches. Do not amend other people's commits.
- Do not delete or skip a failing test to get a green run.
If the ready-to-merge skill is installed, run it before calling a change done. Otherwise apply engineering-bar.
This repo
<!-- managed-by: explore-codebase -->- Root: (unknown)
- Languages: (unknown)
- Install: (unknown)
- Run: (unknown)
- Test: (unknown)
- Format: (unknown)
- Lint: (unknown)
- Typecheck: (unknown)
- Build: (unknown)
- Layout: (unknown)
- Do not edit: (unknown)
<!-- end-managed-by: explore-codebase -->Glossary
<!-- managed-by: explore-codebase-glossary -->- (none yet)
<!-- end-managed-by: explore-codebase-glossary -->Replace (unknown) by running the explore-codebase skill, or fill the commands yourself from the README / CI config. Never invent a command that this repo does not actually have. Terms in Glossary come from this repo's code and docs, not from invented jargon.
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.