agentleFS
marcogallucciomarcogalluccio/company-brain-os/daily-log/CLAUDE.md

company-brain-os / daily-log

CLAUDE.md7 starsChanged 47 days agoMITView on GitHub

Per-operator, per-day session record. - One file per operator per day: YYYY-MM-DD-<slug>.md. ISO date, then the operator's registry slug. - The slug always comes from operators/, resolved via the rule in operators/CLAUDE.md. Never derive it from git config user.name directly: a name is free text, a slug is a value a registry file claims. If the operator can't be resolved, fix that first (see operators/ONBOARDING.md Troubleshooting) rather than guessing a filename. - Sections, in order: - ## What happened: what…

The file

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

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    If the operator can't be resolved, fix that first (see operators/ONBOARDING.md Troubleshooting) rather than guessing a filename.

    line 12
  2. Distinctive:

    If something in a log entry needs to be findable later or acted on across sessions, it belongs in a memory file too, the log is where it …

    line 24
  3. Distinctive:

    Never edit another operator's log file.

    line 30
  4. Distinctive:

    Don't backfill or edit a past day's log to reflect information learned later.

    line 32

≈ “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

daily-log/

Per-operator, per-day session record.

Convention

  • One file per operator per day: YYYY-MM-DD-<slug>.md. ISO date, then the operator's registry slug.
  • The slug always comes from operators/, resolved via the rule in operators/CLAUDE.md. Never derive it from git config user.name directly: a name is free text, a slug is a value a registry file claims. If the operator can't be resolved, fix that first (see operators/ONBOARDING.md Troubleshooting) rather than guessing a filename.
  • Sections, in order:
    • ## What happened: what was worked on, in plain terms.
    • ## Decisions: anything decided during the session, and why.
    • ## Open threads: unfinished business to pick up next session.

What this is not

A daily log is a session record, not a project tracker. Status, next actions, deadlines, and ownership live in memory/ (see memory/CLAUDE.md). If something in a log entry needs to be findable later or acted on across sessions, it belongs in a memory file too, the log is where it happened, memory is where it stands.

Rules

  • Never edit another operator's log file. If a session touches someone else's work, note it in your own log and let them pick it up in theirs.
  • Don't backfill or edit a past day's log to reflect information learned later. Add a new entry on today's date instead.

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.