agentleFS
jackson2wjackson2w/claude-code-skills/claude-code-remote-control-host/SKILL.md

claude-code-remote-control-host

Skill1 starsChanged 9 days agoNo licenceView on GitHub

This skill should be used when building, debugging, or extending a persistent Claude Code Remote Control server host — a Linux box (LXC/VM/VPS) that runs `claude remote-control` under systemd as a dedicated service user so sessions can be driven from the Claude mobile app or claude.ai/code and survive the laptop closing — including the login/auth model, per-project systemd template units, the liveness watchdog, and fleet SSH access for the service user. Built once for the homelab (`claude-code`, VMID 112, 2026-09-09). Trigger phrases include "claude remote-control", "remote control server systemd", "claude-rc@", "Remote Control requires a full-scope login token", "You must be logged in to use Remote Control", "setup-token remote control", "CLAUDE_CODE_OAUTH_TOKEN remote control", "refreshTokenExpiresAt", ".credentials.json expiresAt", "remote control journal spam", "claude remote-control --help hangs", "list-unit-files template instance", "systemctl show --value order", "git ls-remote -h HEAD", "Enable Remote Control? (y/n)", "hasTrustDialogAccepted", "workspace trust headless", "claude-rc-watchdog", "claude-code-install.yml", "claude_code_pubkey", "herdr", "agent-aware multiplexer", "terminal client for remote control", "ssh into the claude code host", "claude: command not found in a tmux pane", "RemoteCommand not found", "~/.local/bin not on PATH over ssh", "claude --continue resumed the wrong session", "same session open on phone and terminal", "herdr integration install claude".

  • Pipes a download into a shell
  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 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.

  • 4

    Very specific

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

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “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.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.