verify_unused

Use this skill to safety-check whether a GKE or Kubernetes cluster is active or unused before executing any cluster deletion commands (DeleteCluster, gcloud container clusters delete, or kubectl delete). This prevents accidental data loss, service interruption, and destruction of active environments.

Critical Rule

[!IMPORTANT] NEVER delete a GKE or Kubernetes cluster without running this verification skill first or verifying that deletion_policy: VERIFY_UNUSED is enforced. If this check returns [ACTIVE] (exit code 1) or fails due to network/server timeout ([FAIL-CLOSE], exit code 2), you must block the deletion and prompt the user for explicit confirmation or intervention.

Safety Criteria

The safety verification evaluates three core heuristics. If any condition is met, deletion is blocked:

1. External Exposure

• Failure Condition: Presence of $\ge 1$ Service of type LoadBalancer, OR any Ingress, Gateway (Gateway API), or MultiClusterIngress resource in any namespace.
• Rationale: These resources indicate the cluster is actively serving (or configured to serve) ingress traffic. Deleting the cluster would cause an immediate service disruption for users or connected systems.

2. Persistent Data