agentleFS
Sign inStart free
T0mSIlverT0mSIlver/skills/claude-remote-control-server/SKILL.md

claude-remote-control-server

Skill1 starsChanged 33 days agoMITView on GitHub

Install, change, or troubleshoot per-repo `claude remote-control` (RC) servers under user systemd, which let claude.ai/code start sessions on this machine.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the installer from the repo.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
SKILL.md

Claude Remote Control server

Each repo gets one user systemd service running claude remote-control --spawn worktree, so claude.ai/code and the Claude app can start sessions in it, each in its own git worktree.

Install or change a server

Run the installer from the repo. To change a server, run it again with the new values.

CAPACITY=8 install-claude-rc-server-service.sh
VariableDefault
REPO_DIRthe current git checkout
SERVICE_NAMEclaude-rc-<repo>
SESSION_NAME<repo>@<host>
SESSION_PREFIX<host>-<repo>
CAPACITY8
PERMISSION_MODEthe CLI's default

DRY_RUN=1 prints the unit instead of installing it. To preview a change, pass the values the service was installed with plus the new one, and diff:

DRY_RUN=1 SERVICE_NAME=claude-rc-myapp CAPACITY=12 install-claude-rc-server-service.sh \
  | diff - <(systemctl --user cat claude-rc-myapp.service | tail -n +2)

The installer also enables claude-rc-refresh.timer. A CLI auto-update can delete the binary a server starts sessions from, so the timer restarts servers left on an old CLI once no session is mid-turn. Sessions pick up again on their next message. See reference/cli-updates.md.

Sessions started from claude.ai/code ignore PERMISSION_MODE, because the web sends its own mode. To stop approval prompts, add permissions.allow rules to the repo's .claude/settings.json. See reference/web-spawn-permission-mode.md.

Check a server

systemctl --user status claude-rc-myapp.service
loginctl show-user "$USER" -p Linger

Expect active and Linger=yes. active only means the process is up. When sessions fail to start, plain journalctl hides the errors as [171B blob data]; reference/cli-updates.md shows how to read them.

Change a server by re-running the installer, not by editing its unit. The installer strips ANTHROPIC_API_KEY and similar variables so the server uses the claude.ai login, and the next install overwrites hand edits.

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