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 agentmods add skills/vladkesler/initrunner/kubernetesnpx skills add vladkesler/initrunner --skill kubernetesgit clone --depth 1 https://github.com/vladkesler/initrunnerWrote 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/vladkesler/initrunner/kubernetes)<a href="https://agentmods.dev/skills/vladkesler/initrunner/kubernetes"><img src="https://agentmods.dev/badge/skills/vladkesler/initrunner/kubernetes.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00031 | $0.01084 |
| Opus 5 | $0.00015 | $0.00542 |
| Sonnet 5 | $0.00006 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
kubernetes 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You have Kubernetes diagnostic capabilities via kubectl and helm.
When to activate
Use these tools when the user asks about:
- Pod failures (CrashLoopBackOff, ImagePullBackOff, Pending, OOMKilled)
- Service connectivity or DNS resolution issues
- Node pressure, resource exhaustion, or scheduling failures
- Storage issues (PVC pending, mount failures)
- Deployment rollouts stuck or failing
- Cluster health checks or capacity planning
Diagnostic methodology
Follow this six-step process for every issue:
1. Preflight
Confirm cluster access and context before running any commands:
kubectl config current-context
kubectl cluster-info
If the user has not specified a namespace, ask or default to the namespace from context. Always confirm the target cluster before making changes.
2. Categorize
Classify the issue into one of these layers:
| Layer | Symptoms |
|---|---|
| Pod | CrashLoopBackOff, ImagePullBackOff, OOMKilled, exit codes |
| Service/Network | Connection refused, DNS failures, endpoint mismatches |
| Node/Scheduling | Pending pods, taints, resource pressure |
| Storage | PVC pending, mount errors, capacity |
| Config | ConfigMap/Secret not found, env var issues |
| Rollout | Stuck deployments, replica mismatches |
3. Gather
Collect evidence using kubectl. Start broad, then narrow:
- Broad:
kubectl get pods -n <ns>,kubectl get events -n <ns> --sort-by=.lastTimestamp - Narrow:
kubectl describe pod <name> -n <ns>,kubectl logs <name> -n <ns> --tail=100 - Deep:
kubectl get pod <name> -n <ns> -o yaml, container-level logs with-c
Use the think tool to reason through the evidence before concluding.
4. Reference
Consult reference materials before proposing fixes. If the agent has filesystem access to reference docs, read them for symptom-to-fix lookups and decision tree guidance.
5. Fix
Propose a fix with:
- The exact kubectl command(s) to run
- An explanation of what each command does and why
- The blast radius (what else could be affected)
- A rollback plan if the fix does not work
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.
- 6d ago First seen · 145 lines · 31 tokens per session scan A b372dec21b7f
kubernetes is a skill published in the GitHub repository vladkesler/initrunner (41 stars, last pushed 5d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,084 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
kubernetes
Kubernetes operations expert for kubectl, pods, deployments, and debugging.
Vizra ADK Tool Creation
Build custom tools for Vizra ADK agents - includes patterns for database, API, file, and email tools.
Vizra ADK Evaluation Framework
Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
Vizra ADK Agent Creation
Create AI agents with Vizra ADK - includes patterns for customer service, data analysis, and content generation agents.
Vizra ADK Workflows
Orchestrate complex multi-agent workflows - sequential, parallel, conditional, and loop patterns.