k8s-cli

k8s-cli is a skill for Claude Code, Codex from rohitg00/kubectl-mcp-server. It costs 39 tokens per session (1,391 once invoked), scanned A, original, MIT.

A command-line interface for kubectl-mcp-server, a service that exposes Kubernetes operations as callable tools. It supports checking the service, finding available tools, and running them directly.

In plain words
What is it for?
Use it to run diagnostics, list or search tools, check server health, start the server, and call operations such as listing pods.
Why use it?
It provides one terminal workflow for discovering what Kubernetes operations are available and checking whether the required dependencies work.

Skill for Claude CodeCodex

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

Good fit Use it to run diagnostics, list or search tools, check server health…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rohitg00/kubectl-mcp-server/k8s-cli
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 rohitg00/kubectl-mcp-server --skill k8s-cli
Clone the repo
git clone --depth 1 https://github.com/rohitg00/kubectl-mcp-server

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 k8s-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/rohitg00/kubectl-mcp-server/k8s-cli.svg)](https://agentmods.dev/skills/rohitg00/kubectl-mcp-server/k8s-cli)
Your own site
<a href="https://agentmods.dev/skills/rohitg00/kubectl-mcp-server/k8s-cli"><img src="https://agentmods.dev/badge/skills/rohitg00/kubectl-mcp-server/k8s-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,391 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.
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 $0.00039 $0.01391
Opus 5 $0.00019 $0.00696
Sonnet 5 $0.00008 $0.00278
Haiku 4.5 $0.00004 $0.00139

Measured 7d ago against content hash c4b7f58391f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

k8s-cli 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 7d 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.

kubernetes-skills/claude/k8s-cli/SKILL.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kubectl-mcp-server CLI

Command-line interface for kubectl-mcp-server operations.

When to Apply

Use this skill when:

  • User mentions: "CLI", "command line", "tool discovery", "server health"
  • Operations: listing tools, calling tools directly, checking dependencies
  • Keywords: "doctor", "tools list", "call", "grep", "info"

Priority Rules

Priority Rule Impact Tools
1 Run doctor to check dependencies CRITICAL kubectl-mcp-server doctor
2 Use tools -d for descriptions HIGH kubectl-mcp-server tools -d
3 Use grep for tool discovery MEDIUM kubectl-mcp-server grep
4 Use call for direct invocation MEDIUM kubectl-mcp-server call

Quick Reference

Task Command Example
List tools tools -d kubectl-mcp-server tools -d
Search tools grep kubectl-mcp-server grep "*pod*"
Call tool call kubectl-mcp-server call get_pods '{"namespace": "default"}'
Check health doctor kubectl-mcp-server doctor

Server Commands

Start Server

# stdio transport (for Claude Desktop)
kubectl-mcp-server serve

# HTTP transport (for remote clients)
kubectl-mcp-server serve --transport streamable-http --port 8000

# With debug logging
MCP_DEBUG=true kubectl-mcp-server serve

Check Health

# Verify dependencies
kubectl-mcp-server doctor

# Shows:
# ✓ kubectl: found
# ✓ helm: found
# ✓ kubeconfig: valid
# ✓ cluster: connected

Tool Discovery

List Tools

# List all tools
kubectl-mcp-server tools

# List with descriptions
kubectl-mcp-server tools -d

# JSON output
kubectl-mcp-server tools --json

Search Tools

# Search by pattern
kubectl-mcp-server grep "*pod*"
kubectl-mcp-server grep "*helm*"
kubectl-mcp-server grep "*velero*"

# Results show matching tool names

Tool Schema

# Show tool parameters
kubectl-mcp-server tools get_pods
kubectl-mcp-server tools install_helm_chart

# Shows:
# - Description
# - Parameters (name, type, required)
# - Return type

Read the full file on GitHub · 247 lines

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. 7d ago First seen · 247 lines · 39 tokens per session scan A c4b7f58391f9

Subscribe to this mod's changes

k8s-cli is a skill published in the GitHub repository rohitg00/kubectl-mcp-server (957 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 1,391 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.