agentleFS
Sign inStart free
haomingkoohaomingkoo/haomingkoo.github.io/CLAUDE.md

haomingkoo.github.io

CLAUDE.md0 starsChanged 8 days agoMITView on GitHub

  • Reads credentials

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

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    No PR CI. Workflows are monitors only: Uptime (every 15 min, uptime/endpoints.json) and Rendered pages (every 6 h, …

    line 6
  2. Very specific:

    Check SEA-LION /v1/models before changing SEALION_MODEL in wrangler.jsonc.

    line 11
  3. Very specific:

    Never commit .env, local MCP configs, raw recordings or private design exports (previews/ is gitignored).

    line 21
  4. Distinctive:

    Keep client names, internal screenshots, schemas and hostnames off the public site.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 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

CLAUDE.md — portfolio

Run and test

  • Static site, no build step. Preview: python3 -m http.server 4178.
  • npm test (worker retrieval tests), npm run check:js, npm run check:worker (wrangler dry run).
  • No PR CI. Workflows are monitors only: Uptime (every 15 min, uptime/endpoints.json) and Rendered pages (every 6 h, uptime/rendered_sites.json). Both open issues on failure. Add new app subdomains to those files.

Deploys

  • GitHub Pages (legacy build) serves main at /. A merge is a deploy.
  • The chat Cloudflare Worker (worker/, wrangler.jsonc) deploys manually with npx wrangler deploy. It bundles llms.txt at deploy time, so llms.txt edits reach the chat only after a redeploy.
  • Check SEA-LION /v1/models before changing SEALION_MODEL in wrangler.jsonc.

Content

  • python3 sync_site_content.py regenerates the blog and travel archive blocks, sitemap.xml and feed.xml from blog/posts.json and travel/posts.json. Run it after adding a post.
  • python3 sync_profile_surfaces.py writes the GitHub profile README (default ../haomingkoo/README.md) from profile.json. --check reports drift.
  • llms.txt and llms-full.txt are hand-maintained. Keep them consistent with page content.
  • New posts: ./new-post.sh (blog or travel) creates the file, updates posts.json and runs the sync. Re-run the sync after editing title or excerpt.
  • system/ CSS: load tokens.css first. See system/README.md.

Safety

  • Never commit .env, local MCP configs, raw recordings or private design exports (previews/ is gitignored).
  • Keep client names, internal screenshots, schemas and hostnames off the public site.
  • Public contact email is haomingkoo@gmail.com.

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.

Reviews can't be read right now.

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