agentleFS
Sign inStart free
romanveselovskiromanveselovski/agents-frontend-rules/AGENTS.md

agents-frontend-rules

AGENTS.md0 starsChanged 58 days agoMITView on GitHub

Rules: .cursor/rules/ or web-ai-rules/rules/. The user's request outranks any file. Chat language — same language as the user's task. Code and site copy — product language. Code — karpathy-guidelines.mdc. React/Next already in the repo — you may use skills/frontend-developer/SKILL.md. Do not invent a stack. UI build — empty repo: 01-greenfield.mdc. Visual: 14-design.mdc + frontend-design. Behavior: 16-ux.mdc (Google/Material interaction, not necessarily their look). Motion: antigravity-design-expert unless a flat mock exists. Components beat decoration. prefers-reduced-motion kills scenes. Copy — 52-copy.mdc + avoid-ai-writing.mdc…

  • 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 repository7 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 1 is common, 0 are distinctive, and 1 is very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

    No raw HTML from outside. No secrets in the client.

    line 25
  2. Very specific:

    Before handoff: focus visible.

    line 27

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Agent: frontend of this site

Rules: .cursor/rules/ or web-ai-rules/rules/. The user's request outranks any file.

Chat language — same language as the user's task. Code and site copy — product language.

Code — karpathy-guidelines.mdc. React/Next already in the repo — you may use skills/frontend-developer/SKILL.md. Do not invent a stack.

UI build — empty repo: 01-greenfield.mdc. Visual: 14-design.mdc + frontend-design. Behavior: 16-ux.mdc (Google/Material interaction, not necessarily their look). Motion: antigravity-design-expert unless a flat mock exists. Components beat decoration. prefers-reduced-motion kills scenes.

Copy — 52-copy.mdc + avoid-ai-writing.mdc (including tsx/html).

Articles — 53-content.mdc, skills/blog-author/SKILL.md, facts from project-facts.md. Schema — skills/seo-aeo-schema-generator/SKILL.md. GEO — skills/seo-geo/SKILL.md.

Measurement — CWV on production. CI gate — skills/frontend-lighthouse/SKILL.md only if CI was requested.

UI

  1. Reuse existing components and the shared header/footer first.
  2. One toast, tooltip, form, modal, button per project.
  3. Home logo is not a link. Clickable: hover + pointer + pressed. On mobile, a press state is required, not hover alone. Logo: pointer only.
  4. Forms: label, error summary, do not clear values. No toast for form errors.
  5. Data views: loading / empty / error / success.
  6. WCAG 2.2 AA. Keyboard equals mouse. Light and dark themes from the first scaffold.
  7. Custom 404 + HTTP 404 from the first scaffold.
  8. No raw HTML from outside. No secrets in the client.

Before handoff: focus visible; no logo self-link; no blank screen; LCP not lazy; noopener; Esc closes overlays; scrollbar does not shift the page; text selection does not close the modal; a dead URL serves the custom 404; both themes; no AI-boilerplate copy.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free