agentleFS
Sign inStart free
mkmlabs-aimkmlabs-ai/linkedin-agent/CLAUDE.md

linkedin-agent

CLAUDE.md4 starsChanged 15 days agoMITView on GitHub

Agent that runs the owner's LinkedIn account 3x a day in Ego Lite. See README.md. - If data/config.json does not exist or bin/li doctor reports voice.md/topics.md as templates, offer to run the setup skill (the first-run wizard) and run it on "yes". - "zatrzymaj agenta" / "stop the agent" = bin/li stop; "wznów" / "resume" = bin/li resume. - "przełącz na live" / "go live" = set "mode": "live" in data/config.json after one confirmation; "tryb próbny" / "dry run" =…

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:

    If data/config.json does not exist or bin/li doctor reports voice.md/topics.md as templates, offer to run the setup skill (the first-run …

    line 7
  2. Very specific:

    Never commit anything from data/ and never copy personal facts into tracked files.

    line 22
  3. Distinctive:

    No MCP servers, no external posting APIs.

    line 24
  4. Very specific:

    Before committing: uv run --no-project --with pytest python -m pytest and uvx ruff check ..

    line 25

≈ “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

linkedin-agent

Agent that runs the owner's LinkedIn account 3x a day in Ego Lite. See README.md.

When a person opens Claude Code in this folder

  • If data/config.json does not exist or bin/li doctor reports voice.md/topics.md as templates, offer to run the setup skill (the first-run wizard) and run it on "yes".
  • "zatrzymaj agenta" / "stop the agent" = bin/li stop; "wznów" / "resume" = bin/li resume.
  • "przełącz na live" / "go live" = set "mode": "live" in data/config.json after one confirmation; "tryb próbny" / "dry run" = "mode": "dry_run".
  • "co dziś zrobił agent?" / "what did the agent do?" = bin/li status plus the latest file in data/reports/, summarised in plain words.

Project rules

  • Skills live only in .claude/skills/ of this project: linkedin-session (operator playbook), setup (first-run wizard), li-post, li-comment, li-reply, li-plan, li-human.
  • Scheduled agent: .claude/agents/linkedin-operator.md.
  • CLI: bin/li (state, limits, log, runner, schedule). Code in src/linkedin_agent/, tests in tests/.
  • Private state is data/ (git-ignored): config, voice, topics, plan, log, drafts, reports. Never commit anything from data/ and never copy personal facts into tracked files.
  • Mode: data/config.json mode = dry_run or live. Emergency stop: touch data/STOP.
  • No MCP servers, no external posting APIs. Browser = Ego Lite only.
  • Before committing: uv run --no-project --with pytest python -m pytest and uvx ruff check ..

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