agentleFS
Sign inStart free
ouestlabsouestlabs/audio-ui/.claude/CLAUDE.md

audio-ui

CLAUDE.md202 starsChanged 30 days agoMITView on GitHub

@../AGENTS.md Everything above applies as is; this part covers only what is specific to Claude Code.

The file

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

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Browser checks: use the Playwright MCP tools to look at a page or a component on the dev server (:4000).

    line 9

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

@../AGENTS.md

Claude Code

Everything above applies as is; this part covers only what is specific to Claude Code.

  • Skills: the workflow skills in .claude/skills/ load on their own when a task matches. The repo's canonical copy lives there; .agents/skills is a symlink to it for other agents.
  • Format hook: after every Edit/Write, .claude/hooks/format.sh formats that one file with Biome and sorts its imports. It runs the formatter only, never the linter, so an import you add before the code that uses it survives. Lint fixes (unused imports and the rest) happen when you run bun run lint:fix at the end.
  • Browser checks: use the Playwright MCP tools to look at a page or a component on the dev server (:4000).
  • TanStack Start: apps/www runs on TanStack Start (Vite, file routes in src/routes, a prerendered build served from Cloudflare). Its API moves fast: check the installed package docs before relying on memory.

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