write-agents-md
Skill0 starsChanged 14 days agoMITView on GitHub
Draft a short, accurate AGENTS.md (and a CLAUDE.md bridge) for a repository from evidence in the repo. Use when a project has no agent instructions, or when asked to create or rewrite AGENTS.md.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- Aarf101/budgetlooptheir own version, first seen Oct 20, 2026
- joshua-zyy/write-agents-mdtheir own version, first seen Oct 3, 2026
- AsakuraMizu/skillstheir own version, first seen Sep 18, 2026
- dzianisv/skillstheir own version, first seen Aug 18, 2026
- narumiruna/skillstheir own version, first seen Jul 15, 2026
- brandhaug/skillstheir own version, first seen Jul 3, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- narumiruna/skills★ 17same name
- dzianisv/skills★ 4same name
- AsakuraMizu/skills★ 2same name
- Aarf101/budgetloop★ 0same name
- brandhaug/skills★ 0same name
- josecabralf/skills★ 0same name
- joshua-zyy/write-agents-md★ 0same name
- justinchoo93/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- agents-md-auditSkill
- brag-doc-from-gitSkill
- dependency-upgradeSkill
- explain-codebaseSkill
- pr-descriptionSkill
- prove-it-ranSkill
- repro-first-debuggingSkill
- review-my-diffSkill
- safe-refactorSkill
- security-quick-reviewSkill
- session-handoffSkill
- write-subagentSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Use references/template.md as the skeleton.
- Distinctive: line 41
Run each command you documented (skip destructive ones, say so).
- Distinctive: line 42
Check every path exists.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Write an AGENTS.md from evidence
Goal: a file under about 100 lines that tells a coding agent how to run, test and change this repo, using only facts you verified. Unknown beats invented.
Gather evidence first (read, do not guess)
README*,CONTRIBUTING*, anydocs/index.- Manifests and task runners:
package.jsonscripts,Makefile,justfile,pyproject.toml,Cargo.toml,go.mod,*.csproj,project.godot. - CI config (
.github/workflows/*,.gitlab-ci.yml): the commands CI runs are the commands that must pass. - Lint, format and type-check config (
.eslintrc*,ruff.toml,.editorconfig,tsconfig.json). - Directory layout, two levels deep, ignoring
node_modules,.git, build output. - Existing instruction files (
CLAUDE.md,.cursor/rules,.github/copilot-instructions.md). Merge, do not duplicate.
Write the file
Use references/template.md as the skeleton. Rules:
- Commands first. Exact commands to install, run, test one file, run the full suite, lint, build. Copy them from the manifests; run the safe ones to confirm.
- Only what the agent cannot infer. Skip "this is a Next.js app" if
package.jsonsays so. Keep: unusual conventions, forbidden areas, generated files, required env setup. - Make each rule testable. "Run
npm run lintbefore finishing" not "keep code clean". - Boundaries section. Files and directories never to edit by hand (generated code, lockfiles, vendored code), and actions that need approval (migrations, deploys, deleting data, force-push).
- Unknowns. Where evidence is missing, write
TODO(owner): <question>instead of guessing, and list the TODOs in your final message. - No secrets, no personal paths, no links you did not open.
Bridge for other tools
- Claude Code reads
CLAUDE.md, notAGENTS.md. If noCLAUDE.mdexists, create one containing only@AGENTS.mdso both stay in sync (Claude Code supports@pathimports). If one exists, add that import line at the top and remove duplicated content. - Cursor, GitHub Copilot, Codex and others read
AGENTS.mddirectly or via their own files; do not copy the content into several places.
Verify before finishing
- Run each command you documented (skip destructive ones, say so).
- Check every path exists.
- Count lines. If over about 100, move scoped rules to nested
AGENTS.mdfiles or tool-specific rule files. - Show the user the file and the TODO list. Do not commit unless asked.
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.