agentsclimarketplace

Preflight

Skill Walliiee/agent-harness/plugin/skills/preflight

Run the agent-harness clone-level preflight doctor (deps, repo structure, an adapt.py dry-run) and summarize what is present vs missing, split into required / scheduler / optional. Invoke when the user wants to check whether a machine is ready to run agent-harness.From its SKILL.md

Install
npx -y skills add Walliiee/agent-harness --skill preflight

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.3 KB, 263 tokens by cl100k_base, as published. Nobody here has run it

Preflight — is this machine ready for agent-harness?

Run the bundled clone-level doctor and summarize the result for the user. The plugin's files are under ${CLAUDE_PLUGIN_ROOT}.

bash "${CLAUDE_PLUGIN_ROOT}/scripts/preflight.sh"

Then report concisely:

  • Required (template path / adapt.py): is it satisfied? If anything is missing here, the harness can't be adapted yet — call it out first.
  • Scheduler + DR tooling: PyYAML, OS, gh — needed only to install/verify the macOS LaunchAgents and DR scripts.
  • Optional (live memory stack: Postgres / Bun / QMD / Gbrain / Ollama / OpenClaw): note any that are missing or below their tested baseline (the script prints a warn-only line for those — surface it, but it is not a failure).

The script exits 0 when the required template path is ready and 1 if a required dependency or repo file is missing — relay which case it is. To actually wire the harness in, point the user at the adapt skill (/agent-harness:adapt).

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.