debug-k8s

debug-k8s is a command for coding agents from adrielp/ai-engineering-harness. It costs 0 tokens per session (1,128 once invoked), scanned A, original, Apache-2.0.

A read-only Kubernetes debugging command that examines pods, logs, events, resource details, and cluster state. Kubernetes is a system for running and managing containerized applications.

In plain words
What is it for?
Use it to investigate Kubernetes pods and workloads, inspect logs and events, and diagnose startup, application, networking, or resource problems.
Why use it?
It helps identify why an application is not starting, is producing errors, cannot connect, or lacks resources without changing the cluster.

Command

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.

agentmods
npx agentmods add commands/adrielp/ai-engineering-harness/debug-k8s
Clone the repo
git clone --depth 1 https://github.com/adrielp/ai-engineering-harness

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 debug-k8s

README.md
[![agentmods](https://agentmods.dev/badge/commands/adrielp/ai-engineering-harness/debug-k8s.svg)](https://agentmods.dev/commands/adrielp/ai-engineering-harness/debug-k8s)
Your own site
<a href="https://agentmods.dev/commands/adrielp/ai-engineering-harness/debug-k8s"><img src="https://agentmods.dev/badge/commands/adrielp/ai-engineering-harness/debug-k8s.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01128
Opus 5 $0.00000 $0.00564
Sonnet 5 $0.00000 $0.00226
Haiku 4.5 $0.00000 $0.00113

Measured 3d ago against content hash 95d8a60671e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-k8s 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 3d 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.

opencode/commands/debug-k8s.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Kubernetes

You are tasked with helping debug Kubernetes issues. This command allows you to investigate problems by examining pods, logs, events, and cluster state without making changes.

MCP Server Preference

When the Kubernetes MCP server is available, prefer using MCP tools:

  • mcp__kubernetes__list_pods - List pods in a namespace
  • mcp__kubernetes__get_pod - Get pod details
  • mcp__kubernetes__get_logs - Get pod logs
  • mcp__kubernetes__list_events - List cluster events
  • mcp__kubernetes__describe_resource - Describe any resource

When MCP is unavailable, fall back to kubectl commands via Bash.

To check if MCP is available, attempt an MCP tool first. If it fails with "tool not found", use kubectl.

Initial Response

When invoked WITH a context (namespace, pod name, or resource):

I'll help debug Kubernetes issues with [resource]. Let me check the cluster state.

What specific problem are you encountering?
- Pod not starting?
- Application errors?
- Network/connectivity issues?
- Resource constraints?

I'll investigate the pods, logs, and events to help identify the issue.

When invoked WITHOUT parameters:

I'll help debug your Kubernetes issue.

Please provide some context:
- Which namespace?
- Which pod/deployment/service?
- What's the expected vs actual behavior?

I can investigate pod status, logs, events, and resource state.

Process Steps

Step 1: Understand the Problem

  1. Get context from user (namespace, resource name, symptoms)
  2. Quick cluster check:
    • Current kubectl context
    • Target namespace

Step 2: Investigate the Issue

Spawn parallel Task agents based on the problem type:

Task 1 - Pod Status:
Check pod status and conditions
- List pods in namespace
- Get pod details (phase, conditions, container status)
Return: Pod state summary, restart counts, readiness
Task 2 - Pod Logs:
Examine recent logs for errors
- Get logs from main container
- Check previous container logs if restarted
Return: Key errors/warnings with timestamps

Read the full file on GitHub · 184 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. 3d ago First seen · 184 lines · 0 tokens per session scan A 95d8a60671e7

Subscribe to this mod's changes

debug-k8s is a command published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,128 tokens. 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.