agentleFS
Sign inStart free
niki914niki914/zafiro/.agents/skills/host-command-bridge/SKILL.md

host-command-bridge

Skill371 starsChanged todayMITView on GitHub

Delegate heavy compilation/testing or opening visual artifacts on the host Mac from the Linux VM. Keep all other tasks inside the VM.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All routine tasks (git, file inspection, search, normal CLI commands) MUST run locally in this Lima VM.

    line 16
  2. Distinctive:

    Check if the daemon is reachable:

    line 21
  3. Very specific:

    Run commands from within any project directory under ~/shared:

    line 27
  4. Distinctive:

    If setting up for the first time on Mac:

    line 45

≈ “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

Host Command Bridge

Delegates heavy compilation tasks or visual presentation from the Linux VM to the Mac Host.

Boundaries (MUST FOLLOW)

  • Allowed:
    • Heavy compilation or test tasks (e.g. mac-run ./gradlew assembleDebug, mac-run ./gradlew testDebugUnitTest).
    • Presenting visual files/artifacts to the user on Mac (e.g. mac-run open path/to/report.html).
  • Forbidden:
    • All routine tasks (git, file inspection, search, normal CLI commands) MUST run locally in this Lima VM. Minimize mac-run usage.
    • Strictly forbidden from reading or writing host data outside ~/.vm/.monet (~/shared).

Usage

Check if the daemon is reachable:

curl -s http://host.lima.internal:9876/health

Run commands from within any project directory under ~/shared:

mac-run ./gradlew assembleDebug
mac-run open doc/report.html

Daemon Troubleshooting

The Mac host runs the HTTP daemon server; the Linux VM is only a client (mac-run). If health check fails or connection is refused:

Do NOT attempt to start the server inside the Linux VM. Prompt the user to start the daemon on their Mac host:

# On Mac Host (run by user):
python3 ~/.vm/mac_command_daemon.py

If setting up for the first time on Mac:

# On Mac Host (run by user):
mkdir -p ~/.vm
cp ~/.vm/.monet/repo/zafiro/.agents/skills/host-command-bridge/scripts/mac_command_daemon.py ~/.vm/mac_command_daemon.py
python3 ~/.vm/mac_command_daemon.py

To ensure mac-run is available in the Linux VM:

# In Linux VM:
mkdir -p ~/.local/bin
cp ~/shared/repo/zafiro/.agents/skills/host-command-bridge/scripts/mac-run ~/.local/bin/mac-run
chmod +x ~/.local/bin/mac-run

References

  • references/daily-usage.md: Whitelist CLI management and detailed usage.
  • references/environment-setup.md: Complete setup guide, persistent launchd service, and security sandbox architecture.

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