k8s-image-auditor

k8s-image-auditor is an agent for Claude Code from TheLobbi/claude. It costs 41 tokens per session (321 once invoked), scanned A, original, MIT.

A Kubernetes deployment checker that reviews container images, image-pulling settings, and storage resources. Kubernetes runs containerized applications, while Helm manages their deployment settings.

In plain words
What is it for?
Use it before or after Helm deployments to check running pod images, compare them with Docker build logs, review image settings, and inspect persistent volume health. It provides kubectl or Helm commands for each reported issue.
Why use it?
It helps find deployments that run outdated or missing images, reuse changeable tags unsafely, or leave storage resources unused. It also reports whether a deployment is broken, risky, or merely needs a best-practice improvement.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the claude-orchestration plugin — 6 skills, 133 commands, 9 agents, 8 hooks, 6 plugins shipped together

Good fit Use it before or after Helm deployments to check running pod images, compare them with Docker build logs, review image settings, and inspect persistent volume health. It provides kubectl or Helm commands for each reported issue.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thelobbi/claude/k8s-image-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Or install claude-orchestration, the plugin that ships this one along with the rest of its 6 skills, 133 commands, 9 agents, 8 hooks, 6 plugins.

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-image-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/thelobbi/claude/k8s-image-auditor/github.svg)](https://agentmods.dev/agents/thelobbi/claude/k8s-image-auditor)
Your own site
<a href="https://agentmods.dev/agents/thelobbi/claude/k8s-image-auditor"><img src="https://agentmods.dev/badge/agents/thelobbi/claude/k8s-image-auditor/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 k8s-image-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/thelobbi/claude/k8s-image-auditor"><img src="https://agentmods.dev/badge/agents/thelobbi/claude/k8s-image-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 321 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 $0.00041 $0.00321
Opus 5 $0.00020 $0.00161
Sonnet 5 $0.00008 $0.00064
Haiku 4.5 $0.00004 $0.00032

Measured 8d ago against content hash 50c7a014c1a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

k8s-image-auditor 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.

.claude/agents/k8s-image-auditor.md · 31 lines

What it actually says

You are a Kubernetes deployment auditor specializing in image lifecycle and caching issues.

Your primary job is to detect and prevent these common problems:

  1. Stale images: Pods running old images because K8s cached them locally
  2. Wrong pull policy: IfNotPresent on mutable tags like :latest
  3. Tag reuse: Same tag pointing to different image digests over time
  4. Missing images: Deploying images that don't exist in the registry
  5. Orphaned volumes: PVCs not mounted by any pod

Audit process:

  1. Check all running pod images and their pull policies
  2. Cross-reference with the build log at .claude/logs/docker-builds.jsonl
  3. Identify pods using :latest or mutable tags with IfNotPresent
  4. Check Helm release values for image configuration
  5. Verify PV/PVC health and detect orphans
  6. Report findings with specific remediation commands

Output format:

  • Critical (deploy is broken or using wrong image)
  • Warnings (caching risk, may break on next deploy)
  • Info (best practice recommendations)

For each issue, provide the exact kubectl/helm command to fix it.

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. 8d ago First seen · 31 lines · 41 tokens per session scan A 50c7a014c1a2

Subscribe to this mod's changes

k8s-image-auditor is an agent published in the GitHub repository TheLobbi/claude (21 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 321 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.

Related

Other agents, from other repositories

devops-engineer

Deployment and infrastructure expert for .NET — Docker multi-stage builds, GitHub Actions and Azure DevOps pipelines, and .NET Aspire orchestration. Use when containerizing an application, setting up or fixing CI/CD, configuring Aspire AppHost and service defaults, or preparing an app for production deployment.

codewithmukesh/dotnet-claude-kit · 64 tokens

devops-engineer

Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.

faizkhairi/claude-code-blueprint · 29 tokens

incident-commander

Conduz investigação de incidente end-to-end — triagem, preservação de evidência, hipótese, validação e proposta de mitigação. Despachado por /pwdev-devops:incidente. Modelo forte porque correlacionar sintomas sob pressão é onde o raciocínio mais importa. Propõe; nunca executa sozinho.

pwdev-solucoes/pwdev-claude-marketplace · 74 tokens

helm-agent

Executing agent. Writes and maintains Helm charts: Chart.yaml, templates/, values.yaml, helpers. Scope: davinci/kubernetes/apps/helm/, /Chart.yaml, /values.yaml.

alexeyshishin/as-skill · 44 tokens

deployment-verifier

Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.

asysta-act/agent-flow · 24 tokens

devops-automator

Use this agent when setting up CI/CD pipelines, configuring cloud infrastructure, implementing monitoring systems, or automating deployment processes. This agent specializes in making deployment and operations seamless for rapid development cycles.

PMDevSolutions/Aurelius · 44 tokens