kubernetes-diagnostics

Kubernetes Diagnostics Skill

Interprets the Kubernetes context already collected by Causa. The context contains three sections from the MCP server — POD STATUS, POD EVENTS, and POD LOGS.

What the Context Contains

POD STATUS fields

• State — container state: Running, Waiting, or Terminated
• Started At — timestamp the container last started
• Restart Count — number of times the container has restarted
• Resource Limits — CPU and Memory hard limits set on the container
• Resource Requests — CPU and Memory requests set on the container

POD EVENTS format

Each event is formatted as: [Type] timestamp: Reason - Message

• Type is Normal or Warning
• Reason is the short event keyword (e.g. OOMKilling, BackOff, Unhealthy)
• Message is the human-readable detail — the exit code is embedded in the Message text (e.g. "exit code 137"), not as a standalone field

Exit codes in event Message text

Exit Code	Meaning
137	Container killed by the kernel (SIGKILL) — process memory exceeded Resource Limits Memory
143	Container received SIGTERM — graceful shutdown by Kubernetes (rolling restart, scale down)
1	Process exited with a general error — check POD LOGS for a stack trace or startup error
2	Process argument or flag error — check POD LOGS for initialisation errors

POD LOGS

Last 25 lines of container stdout. May be empty or truncated if the container was killed mid-write.

---

Interpreting POD STATUS

State: Terminated + Restart Count > 0 The container exited and Kubernetes restarted it. Read POD EVENTS for the exit reason and POD LOGS for the last output before the crash.

State: Waiting The container has not started. Check POD EVENTS for BackOff (crash loop) or image pull failures.

State: Running + Restart Count > 0 The pod is currently running but has crashed before. Correlate with POD EVENTS and POD LOGS from previous restarts.