agentleFS
raintree-technologyraintree-technology/hig-doctor/AGENTS.md

hig-doctor

AGENTS.md153 starsChanged 9 months agoMITView on GitHub

HIG Doctor combines open-source audit tooling with an attributed snapshot of Apple's Human Interface Guidelines. - Keep Apple-platform rules distinguishable from HIG-aligned cross-platform rules. - Preserve source URLs and attribution in every reference file. - Treat Apple's live HIG as canonical; drift detection proposes review and must not rewrite guidance automatically. - packages/core owns framework detection, the audit rule catalog, structural engines, and the audit pipeline. The CLI, MCP server, website, and demos must consume that package or generate from…

The file

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
  1. Distinctive:

    Keep Apple-platform rules distinguishable from HIG-aligned cross-platform rules.

    line 6
  2. Distinctive:

    Treat Apple's live HIG as canonical.

    line 8
  3. Very specific:

    After an audit-engine or rule-catalog change, run bun run --cwd demos/remotion-hig-doctor generate-data and inspect the generated report …

    line 14
  4. Distinctive:

    Add a focused fixture and test for every detection-rule behavior change.

    line 17
  5. Distinctive:

    Keep file scanning bounded and preserve symlink, size, and recursion safeguards.

    line 18
  6. Distinctive:

    Use Bun 1.4.3 and Node 24 through Mise.

    line 19
  7. Very specific:

    Run bun run validate while iterating and bun run validate:full for release-facing changes.

    line 20

≈ “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

HIG Doctor agent instructions

HIG Doctor combines open-source audit tooling with an attributed snapshot of Apple's Human Interface Guidelines.

  • Keep Apple-platform rules distinguishable from HIG-aligned cross-platform rules.
  • Preserve source URLs and attribution in every reference file.
  • Treat Apple's live HIG as canonical; drift detection proposes review and must not rewrite guidance automatically.
  • packages/core owns framework detection, the audit rule catalog, structural engines, and the audit pipeline. The CLI, MCP server, website, and demos must consume that package or generate from it; do not maintain copied audit engines or rule catalogs.
  • After an audit-engine or rule-catalog change, run bun run --cwd demos/remotion-hig-doctor generate-data and inspect the generated report diff before validation.
  • Add a focused fixture and test for every detection-rule behavior change.
  • Keep file scanning bounded and preserve symlink, size, and recursion safeguards.
  • Use Bun 1.4.3 and Node 24 through Mise.
  • Run bun run validate while iterating and bun run validate:full for release-facing changes.

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.