Analyze Kubernetes cluster issues through MCP with K8sGPT

Analyze Kubernetes cluster issues through MCP with K8sGPT is a skill for Claude Code, Codex from agentskillexchange/skills. It costs 43 tokens per session (500 once invoked), scanned A, original, MIT.

A Kubernetes troubleshooting setup that connects K8sGPT to an MCP-compatible AI client. Kubernetes is software for running containerized applications across a cluster of machines.

In plain words
What is it for?
Use it to inspect a reachable Kubernetes cluster, understand failing resources, and investigate possible remedies.
Why use it?
It helps turn unhealthy Kubernetes resources into plain-language explanations and prioritized clues about what to fix.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect a reachable Kubernetes cluster, understand failing resources, and investigate possible remedies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentskillexchange/skills/analyze-kubernetes-cluster-issues-through-mcp-with-k8sgpt
Install

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.

Any agent
npx skills add agentskillexchange/skills --skill analyze-kubernetes-cluster-issues-through-mcp-with-k8sgpt
Clone the repo
git clone --depth 1 https://github.com/agentskillexchange/skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Analyze Kubernetes cluster issues through MCP with K8sGPT

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentskillexchange/skills/analyze-kubernetes-cluster-issues-through-mcp-with-k8sgpt/github.svg)](https://agentmods.dev/skills/agentskillexchange/skills/analyze-kubernetes-cluster-issues-through-mcp-with-k8sgpt)
Your own site
<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.

agentmods 80×15 button for Analyze Kubernetes cluster issues through MCP with K8sGPT

Your own site · 80×15
<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>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 13d ago against content hash 2b857388407c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

skills/analyze-kubernetes-cluster-issues-through-mcp-with-k8sgpt/SKILL.md · 52 lines

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:

Documentation

Source

Changes

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.

  1. 13d ago First seen · 52 lines · 43 tokens per session scan A 2b857388407c

Subscribe to this mod's changes

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.

Related

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.

seed-forge/harness-ai-kit · 50 tokens

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.

seed-forge/harness-ai-kit · 56 tokens

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.

seed-forge/harness-ai-kit · 63 tokens

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.

sawrus/agent-guides · 62 tokens

kubestellar-console

Multi-cluster Kubernetes dashboard with AI-powered operations via MCP server and 10+ built-in agent skills.

aboalrejal-ai/skills · 25 tokens

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…

QoderAI/better-harness · 87 tokens