zombuul

Interactive onboarding for zombuul. Walks through prerequisites, API keys, .env creation, and verifies everything works. Run this after installing the plugin.

End-to-end smoke test of zombuul. Pre-flight, then 3 parallel agents (API, pod list, full pod lifecycle), then a serial e2e step that runs /zombuul:run-experiment on a tiny canned spec to exercise the orchestration + PR flow. Use before publishing a release. Takes ~10–15 minutes and costs roughly $0.10 in RunPod GPU time.

Run an experiment from a spec or description. If given a path to an existing spec, runs it directly. If given a natural language description, synthesizes a spec first, then runs it. Argument $ARGUMENTS — `<spec_path_or_description> [--remote] [--no-pr]`. Pass `--remote` to execute autonomously on a GPU pod (survives local disconnects); otherwise runs local-first. Pass `--no-pr` to skip the draft-PR-on-the-experiment-branch flow.

Finalize an experiment after the main work is done — sync pod results back, run analysis, spawn report review, commit and push. Argument $ARGUMENTS — `<spec_path> [--pod <pod_name>]`. Invoked automatically by `/zombuul:babysit --on-complete` when a long-running job finishes, or directly by you when an experiment doesn't use a babysitter (no pod, no cron).

Spin up a RunPod GPU pod. Argument $ARGUMENTS — optional pod name, optionally followed by `--remote` to install Claude Code + zombuul plugin on the pod (needed when the pod itself will run an agent, not just receive SSH commands).

Pause a RunPod pod: stop GPU billing; keep /workspace only (container disk is wiped on resume).

Provision a RunPod pod: wait for setup, configure SSH, sync .env and data. Argument $ARGUMENTS — JSON with keys: pod_id, pod_name, ip, port, and optionally spec_path and data_dirs.

Resume a paused RunPod pod.

Review an experiment spec for completeness before running it. Argument $ARGUMENTS — path to the experiment spec.

Monitor a long-running job on a RunPod GPU pod. Checks every 5 min, restarts on crash, and either pauses the pod or fires a follow-up prompt when done. Argument $ARGUMENTS — `<pod_name> <description> [--on-complete "<prompt>"]`. Use when a GPU job is expected to take >10 min and may crash (I/O errors, OOM, SSH timeouts). The description should say what's running and how to tell when it's done. Pass `--on-complete` to chain the next step (e.g. `/zombuul:finalize-experiment <spec> --pod <name>`) so the workflow resumes automatically when the job finishes.

Review and rewrite a research report for clarity. Argument $ARGUMENTS — path to the report markdown file.