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/yindia/rootcause/k8s-securitynpx skills add yindia/rootcause --skill k8s-securitygit 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-security)<a href="https://agentmods.dev/skills/yindia/rootcause/k8s-security"><img src="https://agentmods.dev/badge/skills/yindia/rootcause/k8s-security.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 | $0.00000 | $0.02253 |
| Opus 5 | $0.00000 | $0.01126 |
| Sonnet 5 | $0.00000 | $0.00451 |
| Haiku 4.5 | $0.00000 | $0.00225 |
Grade A, and why
k8s-security 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 4d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: k8s-security
Security diagnostics and audit guidance for Kubernetes workloads using RootCause MCP tools only.
Scope
- RBAC posture and dangerous grants.
- ServiceAccount and IRSA trust-chain analysis.
- Secret and ConfigMap reference validation.
- Policy compliance checks with Kyverno and Cilium context.
- Workload security best-practice review.
- Network isolation and policy-path diagnostics.
Tooling Rule
- Use RootCause tool names only.
- Use
k8s.listfor resource enumeration (including ClusterRoleBinding and RoleBinding queries). - Use
k8s.describefor object-level condition/event detail. - Do not use non-RootCause tool name variants.
Canonical Tool Set
Primary security tools
k8s.permission_debugk8s.config_debugk8s.best_practicek8s.kyverno_detectk8s.diagnose_kyvernok8s.cilium_detectk8s.diagnose_ciliumk8s.describek8s.listk8s.network_debugaws.iam.get_roleaws.iam.get_policy
Supporting event evidence
k8s.eventsk8s.events_timeline
Triggers
- rbac denied
- forbidden
- who can access
- cluster-admin usage
- wildcard verbs
- secret exfiltration risk
- pod exec abuse
- serviceaccount hardening
- irsa not working
- sts assume role error
- kyverno policy violation
- cilium deny
- network isolation drift
- compliance audit
- pod security posture
Priority Rules
| Condition | First action | Why |
|---|---|---|
| Unknown policy stack | Run k8s.kyverno_detect and k8s.cilium_detect |
Scope policy engines before deep triage |
| Permission error in app logs | Run k8s.permission_debug |
Resolves RBAC and IRSA quickly |
| IRSA suspect | Run k8s.permission_debug then aws.iam.get_role |
Validates K8s and IAM chain |
| Config/secret runtime failure | Run k8s.config_debug |
Detects missing keys and references |
| Admission denied | Run k8s.diagnose_kyverno |
Surfaces policy and report failures |
| Network deny suspicion | Run k8s.network_debug then k8s.diagnose_cilium |
Covers K8s policy + Cilium datapath |
| Broad security review | Run k8s.best_practice |
Produces security-focused workload findings |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 272 lines · 0 tokens per session scan A d3b51852f333
k8s-security is a skill published in the GitHub repository yindia/rootcause (42 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,253 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
bazel-k8s-expert
Expert knowledge for deploying Quarkus/Java applications to Kubernetes using Bazel. Covers rulesk8s, Helm, Kustomize, ConfigMaps, Secrets, and health probes.
k8s-ingress-gateway
Kubernetes Ingress 配置错误、Gateway 不通的完整诊断-修复-验证 Skill.
dependabot-batch
Use when reviewing Radar's weekly Dependabot PRs and replacing the safe, 72-hour-soaked updates with one changelog-vetted, tested PR.
test-radar
Use when building and testing Radar changes with the repository's real-instance smoke-test workflow.
visual-test
Use when visually testing Radar UI changes against a real Kubernetes cluster with Playwright screenshots.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.