agentleFS
siddathsiddath/lifeOS/CLAUDE.md

lifeOS

CLAUDE.md7 starsChanged 23 days agoMITView on GitHub

This project uses the rules in AGENTS.md. Read it first for the file map, data contracts, privacy boundaries, optional focus method and mission-swap lifecycle. The owner chooses their priorities and pace; do not infer an emotional state from their planning. Identity and per-instance settings (owner name, timezone, area codes, enabled modules) live in dashboard/lifeos.config.json — copy dashboard/lifeos.config.example.json there and make it yours in a private instance, or run the setup skill to generate it. Nothing hardcodes a person; everything reads…

The file

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

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

  • ≈0

    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. Very specific:

    Start any session by reading AGENTS.md, then 00_START_HERE.md, then 06_Trackers/.

    line 7

≈ “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

CLAUDE.md

This project uses the rules in AGENTS.md. Read it first for the file map, data contracts, privacy boundaries, optional focus method and mission-swap lifecycle. The owner chooses their priorities and pace; do not infer an emotional state from their planning.

Identity and per-instance settings (owner name, timezone, area codes, enabled modules) live in dashboard/lifeos.config.json — copy dashboard/lifeos.config.example.json there and make it yours in a private instance, or run the setup skill to generate it. Nothing hardcodes a person; everything reads from that config.

Start any session by reading AGENTS.md, then 00_START_HERE.md, then 06_Trackers/.

Build-level work for this repo is queued in TODOS.md; agent traces and the friction log live in worksheets/.

Verification

What command proves a change works: npm test. It chains the three checks (package.json), and CI runs exactly this on every push and PR (.github/workflows/ci.yml):

CommandProves
npm run validateEvery dashboard/*.json matches its schema in schemas/, and every task/KB area is a real area code from the config.
npm run check-linksEvery relative Markdown link in the repo resolves. Run this after touching any doc.
npm run test:unitNotion mapping/auth, backup validation and shipped dialog handlers, seed/pull races, sync acknowledgement, check history and local dates (tests/).
bash scripts/pii-scan.sh .No secrets or personal data are about to be committed. Not part of npm test — it runs as its own CI job (.github/workflows/pii-scan.yml). Run it before pushing; this is a public repo.

The dashboard has no build step — for a UI change, open dashboard/index.html directly (or python3 -m http.server) and look at it. There is nothing to compile and no dev server.

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.