agentleFS
Sign inStart free
camrontaylorcamrontaylor/AI-OS-Template/CLAUDE.md

AI-OS-Template

CLAUDE.md0 starsChanged 45 days agoMITView on GitHub

Keeps Claude Code compatible with the shared AGENTS.md and adds Claude-only runtime behavior. Local override loading follows the canonical rule in AGENTS.md ("Local Agent Overrides"). Claude-only addition: also read CLAUDE.local.md before this file when present. Both files are user-owned, never updated. Follow docs/agent-startup.md from the shared AGENTS.md. The detect-first-run.js hook supplies an optional setup hint; it does not override a user task. Use /start-here only when the user chooses guided setup. Do not duplicate a daily session block already opened…

The file

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
  1. Very specific:

    Follow docs/agent-startup.md from the shared AGENTS.md.

    line 22
  2. Very specific:

    Do not duplicate a daily session block already opened during startup.

    line 25
  3. Distinctive:

    Don't greet proactively. If the user greets casually and open threads exist, mention them in one line.

    line 31
  4. Very specific:

    After a major deliverable (file saved to projects/, skill built/modified), run the post-deliverable question from AGENTS.md ("How did this …

    line 33

≈ “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

Keeps Claude Code compatible with the shared AGENTS.md and adds Claude-only runtime behavior.

@AGENTS.md

Local Overrides

Local override loading follows the canonical rule in AGENTS.md ("Local Agent Overrides"). Claude-only addition: also read CLAUDE.local.md before this file when present. Both files are user-owned, never updated.

Claude Runtime

Shared Startup

Follow docs/agent-startup.md from the shared AGENTS.md. The detect-first-run.js hook supplies an optional setup hint; it does not override a user task. Use /start-here only when the user chooses guided setup. Do not duplicate a daily session block already opened during startup. Scheduled cron runs (AI_OS_CRON_JOB_SLUG is set) follow the job prompt only. Team mode uses the injected snapshot exclusively and skips local startup.

Greeting & Checkpoint

  • Don't greet proactively. If the user greets casually and open threads exist, mention them in one line. If they state a task, begin immediately.
  • After a major deliverable (file saved to projects/, skill built/modified), run the post-deliverable question from AGENTS.md ("How did this land? Any adjustments?") and log feedback per that rule. Skip this for quick answers or small edits.

Daily Memory

Each session appends a numbered ## Session N block to context/memory/{YYYY-MM-DD}.md, tracking goal, deliverables, decisions and open threads silently as they happen (never announce). A ### Project reference means load that brief. On sign-off, run meta-wrap-up, finalising the current block. Template + tracked events: docs/daily-memory.md.

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