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 skills add yindia/rootcause --skill k8s-coregit clone --depth 1 https://github.com/yindia/rootcauseWrote 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/yindia/rootcause/k8s-core)<a href="https://agentmods.dev/skills/yindia/rootcause/k8s-core"><img src="https://agentmods.dev/badge/skills/yindia/rootcause/k8s-core/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.
<a href="https://agentmods.dev/skills/yindia/rootcause/k8s-core"><img src="https://agentmods.dev/badge/skills/yindia/rootcause/k8s-core.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.02528 |
| Opus 5.5 | $0.00000 | $0.01011 |
| Sonnet 5.5 | $0.00000 | $0.00506 |
| Haiku 4.5 | $0.00000 | $0.00253 |
Grade A, and why
k8s-core 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 1mo 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 — 550 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: k8s-core
Comprehensive read-first Kubernetes reference using RootCause MCP tool names.
Use this skill when the task is to inspect, query, explain, and trace core resources.
Mission
Deliver high-signal cluster state with minimal noise.
Default flow:
- verify context and connectivity
- scope namespace and selectors
- list/get/describe resources
- correlate logs and events
- summarize facts and open questions
Core Resources Covered
- Pods
- Deployments
- Services
- ConfigMaps
- Secrets
- Namespaces
- Nodes
Core Tool Set
Read and discovery tools:
k8s.pingk8s.overviewk8s.getk8s.listk8s.describek8s.logsk8s.eventsk8s.events_timelinek8s.contextk8s.api_resourcesk8s.crdsk8s.explain_resourcek8s.execk8s.port_forward
Priority Rules
| Priority | Rule | Reason |
|---|---|---|
| P0 | Run k8s.context then k8s.ping before data collection |
prevent wrong-cluster conclusions |
| P1 | Start broad with k8s.overview for unknown scope |
quick health baseline |
| P2 | Prefer k8s.list with selectors before k8s.get loops |
less API chatter, cleaner outputs |
| P3 | Use k8s.describe for state transitions and owner chains |
richer operational context |
| P4 | Use k8s.events_timeline for chronology, k8s.events for raw detail |
time ordering matters |
Parameter Examples By Tool
k8s.context list contexts:
{
"action": "list"
}
k8s.context current context:
{
"action": "current"
}
k8s.ping:
{}
k8s.overview cluster scope:
{}
k8s.overview namespace scope:
{
"namespace": "payments"
}
k8s.get by kind:
{
"kind": "Pod",
"name": "api-6fd5d4f7fb-9w2rc",
"namespace": "payments"
}
k8s.get by resource + apiVersion:
{
"apiVersion": "apps/v1",
"resource": "deployments",
"name": "api",
"namespace": "payments"
}
k8s.list pods with label selector:
{
"namespace": "payments",
"labelSelector": "app=api,tier=backend",
"resources": [
{ "kind": "Pod" }
]
}
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.
- 1mo ago First seen · 550 lines · 0 tokens per session scan A 22c0d77b0aaf
k8s-core is a skill published in the GitHub repository yindia/rootcause (41 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,528 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.
Other skills, from other repositories
k8s-ingress-gateway
A troubleshooting guide for Kubernetes Ingress and Gateway configurations. Kubernetes is a system for running containers, and Ingress and Gateway components route web traffic to those containers.
helm
A guide to Helm, a package manager for Kubernetes applications. Helm uses reusable packages called Charts to install, configure, upgrade, inspect, and remove groups of Kubernetes resources.
k8s-deployer
Kubernetes deployment management - generate manifests, Helm charts, manage rollouts, check cluster status, and apply security best practices.
bazel-k8s-expert
Expert knowledge for deploying Quarkus/Java applications to Kubernetes using Bazel. Covers rulesk8s, Helm, Kustomize, ConfigMaps, Secrets, and health probes.
kubernetes-operator
Deploy and manage applications on Kubernetes. Covers deployments, services, ingress, HPA, secrets, and production-grade cluster configuration.
nvca-values-customization
Customize NVCA Operator Helm chart values in the native monorepo. Use when modifying vendored defaults, changing stack-derived install values, adding deployment-time overrides, or updating scripts under deploy/helm/nvca-operator.