haechi
AGENTS.md17 starsChanged 14 days agoMITView on GitHub
This repository uses no sensitive data. Do not add real personal, patient, or payment data. Write plugin-owned instructions, configuration/setup text, generated guidance and maintained documentation in English. Preserve user-provided content, intentional multilingual examples and parser/test literals, and immutable historical evidence in their original language. Chat responses may follow the user's language. Use Node.js 24 for the Cloud development environment. Run npm run check to verify generated files. Run relevant tests individually with node --test test/<file>.test.mjs; do not run npm test…
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 31,843 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 repository32 other files it gives its agents.
- aboutSkill
- answerSkill
- attack-testsSkill
- audit-experimentSkill
- bugSkill
- ci-watchSkill
- commitSkill
- contextSkill
- delegateSkill
- documentSkill
- evalSkill
- featureSkill
- impact-mapSkill
- implement-workSkill
- mrSkill
- mutation-checkSkill
- perfSkill
- previewSkill
- refactorSkill
- requestSkill
- review-diffSkill
- reviewSkill
- run-experimentSkill
- screen-designSkill
- screen-paritySkill
- setupSkill
- sibling-path-mapSkill
- specSkill
- sweepSkill
- test-hardeningSkill
- verify-workSkill
- work-graphSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 7
Write plugin-owned instructions, configuration/setup text, generated guidance and maintained documentation in English.
- Very specific: line 11
Use Node.js 24 for the Cloud development environment.
- Very specific: line 13
When continuing the Cloud migration, start with docs/cloud-handoff-2026-10-30.md.
- Very specific: line 17
Use jisuzzzz <meked@naver.com> as the human Git author for this repository.
≈ “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 data
This repository uses no sensitive data. Do not add real personal, patient, or payment data.
Language
Write plugin-owned instructions, configuration/setup text, generated guidance and maintained documentation in English. Preserve user-provided content, intentional multilingual examples and parser/test literals, and immutable historical evidence in their original language. Chat responses may follow the user's language.
Development and handoff
Use Node.js 24 for the Cloud development environment. Run npm run check to verify generated files. Run relevant tests individually with node --test test/<file>.test.mjs; do not run npm test or npm run test.
When continuing the Cloud migration, start with docs/cloud-handoff-2026-10-30.md. It summarizes decisions, current status, verification and remaining work, with links to the design and historical carryover. Current repository rules take precedence over historical notes.
Commit attribution
Use jisuzzzz <meked@naver.com> as the human Git author for this repository. Set repository-local user.name and user.email accordingly in each environment before creating commits. Do not add alternate identities for the same person as Co-authored-by trailers.
Include Co-authored-by: Codex <codex@openai.com> in commits created with Codex assistance, including the final squash merge commit.
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.