Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add causaai/causa-backend --skill kubernetes-diagnosticsgit clone --depth 1 https://github.com/causaai/causa-backendWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/causaai/causa-backend/kubernetes-diagnostics)<a href="https://agentmods.dev/skills/causaai/causa-backend/kubernetes-diagnostics"><img src="https://agentmods.dev/badge/skills/causaai/causa-backend/kubernetes-diagnostics/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/causaai/causa-backend/kubernetes-diagnostics"><img src="https://agentmods.dev/badge/skills/causaai/causa-backend/kubernetes-diagnostics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.01235 |
| Opus 5 | $0.00016 | $0.00617 |
| Sonnet 5 | $0.00006 | $0.00247 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
kubernetes-diagnostics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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, orTerminatedStarted At— timestamp the container last startedRestart Count— number of times the container has restartedResource Limits— CPU and Memory hard limits set on the containerResource Requests— CPU and Memory requests set on the container
POD EVENTS format
Each event is formatted as: [Type] timestamp: Reason - Message
TypeisNormalorWarningReasonis the short event keyword (e.g.OOMKilling,BackOff,Unhealthy)Messageis the human-readable detail — the exit code is embedded in theMessagetext (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.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 109 lines · 32 tokens per session scan A e6836a9e6652
kubernetes-diagnostics is a skill published in the GitHub repository causaai/causa-backend (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,235 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hermes-s6-container-supervision
Modify or debug s6 services in the Hermes Docker image.
smoke-test
Health smoke tests + auto-fix for gbrain installs (and OpenClaw services when present). Run after machine/container restarts or whenever something seems broken. Tests critical services, auto-fixes bounded local issues, and reports worker topology without starting daemons. Extensible via user-defined test scripts in…
competition-container-runtime
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for live container runtime analysis, mounted secrets, sidecars, namespaces, init containers, entrypoint drift, and route-to-container resolution. Use when the user asks why a live container differs from manifests, where a mounted secret is…
meta-home-it-rescue
Use this meta-skill instead of answering directly when the user needs help with home, small-team, laptop, browser, printer, Docker, Git, network, UI, or deployment troubleshooting that benefits from multi-skill orchestration across symptom intake, environment capture, web lookup, and repair planning.
debugging-local-replay
Debugs why session recordings aren't appearing in the local dev environment. Use when a developer reports that local replay ingestion isn't working, recordings aren't showing up despite /s calls, or the replay pipeline seems broken after hogli start. Covers the full local pipeline: SDK capture, Caddy proxy…
docker-debug
Debug Kurtosis running on local Docker. Inspect engine, API container, and service logs. Diagnose container crashes, port conflicts, and networking issues. Use when kurtosis commands fail or services aren't reachable on Docker.