chatjs
AGENTS.md1.2k starsChanged 21 days agoApache-2.0View on GitHub
We split this AGENTS.md into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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
- Distinctive: line 5
Use Bun for packages and scripts.
- Very specific: line 7
Run bun lint, bun test:types, and the relevant tests before handing off code changes.
- Distinctive: line 13
Prefer concrete code and evidence over high-level advice.
- Distinctive: line 14
Remove unused code rather than preserving compatibility aliases or dead exports.
- Distinctive: line 18
Use the strategic-testing skill when deciding whether to add or change tests.
- Distinctive: line 19
Before changing any component, page, or styles, read the making-ui-changes skill and follow it - reuse before you create, add/update the …
- Very specific: line 24
When changing apps/chat routes or page states, update the corresponding capture in packages/chat-visual-tests/pages.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 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
ChatJS Agent Instructions
Repository
- Use Bun for packages and scripts.
- The monorepo contains applications in
apps/and shared packages inpackages/. - Run
bun lint,bun test:types, and the relevant tests before handing off code changes. Do not run a production build merely to type-check.
Agent guidance
- Repository rules follow agents.md and live in
AGENTS.mdfiles. The nearest file in the directory tree adds to or overrides this file for its subtree. - On-demand workflows live in
.agents/skills/<name>/SKILL.mdand follow the Agent Skills specification. - Prefer concrete code and evidence over high-level advice. Keep communication concise.
- Remove unused code rather than preserving compatibility aliases or dead exports.
Testing
- Use the strategic-testing skill when deciding whether to add or change tests.
- Before changing any component, page, or styles, read the making-ui-changes skill and follow it - reuse before you create, add/update the story or capture in the same change, check the blast radius on shared components, and prove the change with a visual test.
- When a registry tool in
packages/registry/src/tools/<id>declares arendererExportin its manifest, it must ship arenderer.tsxexporting it and a co-locatedrenderer.visual.tsxbrowser test that renders it in every state in one snapshot. Theregistry-coverageunit test enforces this; runbun run checkinpackages/registryto verify types, unit, and visual tests.
Reference app visual coverage
- When changing
apps/chatroutes or page states, update the corresponding capture inpackages/chat-visual-tests/pages. Follow the suite instructions; this maintainer suite stays outside scaffolded apps.
Trending
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Other versions1 project uses a version of this.
Word for word · 1
- FranciscoMoretti/sparka★ 1.2k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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.
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 28,693 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 repository17 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- check-visual-changesSkill
- create-vercel-ai-issueSkill
- dev-auth-bypassSkill
- economical-visual-testsSkill
- generate-code-snippetSkill
- lazy-prefetch-patternSkill
- making-ui-changesSkill
- next-cache-components-adoptionSkill
- next-dev-loopSkill
- next-partial-prefetching-adoptionSkill
- review-docsSkill
- strategic-testingSkill
- triage-visual-changesSkill
- trpc-patternsSkill
- vitest-visual-testingSkill
- worktree-portsSkill
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.

