Menu
Pause a RunPod pod: stop GPU billing; keep /workspace only (container disk is wiped on resume).
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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).
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.
| name | zombuul:pause-runpod |
| description | Pause a RunPod pod: stop GPU billing; keep /workspace only (container disk is wiped on resume). |
| user-invocable | true |
| allowed-tools | Bash, AskUserQuestion |
Pause a running RunPod pod without terminating it. Only the /workspace MooseFS volume is preserved across pause — container disk (/, /opt/, /root/) is wiped on resume.
List pods: Run ${CLAUDE_PLUGIN_ROOT}/scripts/runpod_ctl.py list.
If there are multiple pods, ask the user which one to pause using AskUserQuestion.
Remind the user about data loss risk. Before pausing, note in the chat that pausing wipes container disk (/, /opt/, /root/) and only /workspace/ survives. Suggest they rsync important experiment outputs off-pod or to /workspace/ first. This is a reminder, not a hard block — continue to the pause command.
Pause: Run ${CLAUDE_PLUGIN_ROOT}/scripts/runpod_ctl.py pause <pod_id>.
If no pods are running, tell the user.
