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 agentskillexchange/skills --skill analyze-kubernetes-cluster-issues-through-mcp-with-k8sgptgit clone --depth 1 https://github.com/agentskillexchange/skillsWrote 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/agentskillexchange/skills/analyze-kubernetes-cluster-issues-through-mcp-with-k8sgpt)<a href="https://agentmods.dev/skills/agentskillexchange/skills/analyze-kubernetes-cluster-issues-through-mcp-with-k8sgpt"><img src="https://agentmods.dev/badge/skills/agentskillexchange/skills/analyze-kubernetes-cluster-issues-through-mcp-with-k8sgpt/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/agentskillexchange/skills/analyze-kubernetes-cluster-issues-through-mcp-with-k8sgpt"><img src="https://agentmods.dev/badge/skills/agentskillexchange/skills/analyze-kubernetes-cluster-issues-through-mcp-with-k8sgpt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.00500 |
| Opus 5 | $0.00022 | $0.00250 |
| Sonnet 5 | $0.00009 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
Analyze Kubernetes cluster issues through MCP with K8sGPT 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 13d 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.
What it actually says
Analyze Kubernetes cluster issues through MCP with K8sGPT
Run K8sGPT as an MCP server so an agent can scan a Kubernetes cluster, explain unhealthy resources, and return prioritized remediation clues in natural language.
Prerequisites
A reachable Kubernetes cluster, K8sGPT, and an MCP-compatible client
Installation
Use the upstream install or setup path that matches your environment:
- brew install k8sgpt
- brew tap k8sgpt-ai/k8sgpt
- built from the source. k8sgpt Install Clang or run brew install gcc.
Requirements and caveats from upstream:
- K8sGPT can be integrated with Claude Desktop to provide AI-powered Kubernetes cluster analysis. This integration requires K8sGPT v0.4.14 or later.
- Analyzer Node took 160.109833ms
- Node
Basic usage or getting-started notes:
-
If you install gcc as suggested, the problem will persist. Therefore, you need to install the build-essential package.
-
Currently, the default AI provider is OpenAI, you will need to generate an API key from OpenAI
-
Extracted from upstream docs: https://raw.githubusercontent.com/k8sgpt-ai/k8sgpt/HEAD/README.md
Documentation
Source
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.
- 13d ago First seen · 52 lines · 43 tokens per session scan A 2b857388407c
Analyze Kubernetes cluster issues through MCP with K8sGPT is a skill published in the GitHub repository agentskillexchange/skills (38 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 500 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 2026-08-30.
Other skills, from other repositories
diag-container-oom
A diagnostic runbook for containers stopped by an out-of-memory condition. A container is an isolated process environment, and OOM means the operating system or container limit stopped it because it used too much memory.
diag-k8s-node-pressure
A diagnostic runbook for Kubernetes node resource pressure. Kubernetes is a system that runs containers; a node is one machine in that system, and pressure means it is short on CPU, memory, disk space, or process IDs.
diag-k8s-pod-crashloop
A diagnostic runbook for Kubernetes Pods stuck in CrashLoopBackOff. A Pod is a Kubernetes unit that runs one or more containers; CrashLoopBackOff means a container keeps failing and Kubernetes waits longer between restart attempts.
pod-troubleshooting
Systematic diagnosis of Kubernetes pod failures — CrashLoopBackOff, OOMKilled, Pending, ImagePullBackOff, and service connectivity issues. Use when the user encounters pods not starting, container restart loops, scheduling failures, or service unreachability in a K8s cluster.
kubestellar-console
Multi-cluster Kubernetes dashboard with AI-powered operations via MCP server and 10+ built-in agent skills.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…