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 Colvin-Y/kubernetes-ontology --skill kubernetes-ontology-accessgit clone --depth 1 https://github.com/Colvin-Y/kubernetes-ontologyWrote 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/colvin-y/kubernetes-ontology/kubernetes-ontology-access)<a href="https://agentmods.dev/skills/colvin-y/kubernetes-ontology/kubernetes-ontology-access"><img src="https://agentmods.dev/badge/skills/colvin-y/kubernetes-ontology/kubernetes-ontology-access/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/colvin-y/kubernetes-ontology/kubernetes-ontology-access"><img src="https://agentmods.dev/badge/skills/colvin-y/kubernetes-ontology/kubernetes-ontology-access.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 | $0.00111 | $0.05513 |
| Opus 5 | $0.00056 | $0.02756 |
| Sonnet 5 | $0.00022 | $0.01103 |
| Haiku 4.5 | $0.00011 | $0.00551 |
Grade B, and why
kubernetes-ontology-access scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo install "kubernetes-ontology_${KO_VERSION}_darwin_arm64/kubernetes-ontology" /usr/local/bin/kubernetes-ontology Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LO "https://github.com/Colvin-Y/kubernetes-ontology/releases/download/${KO_VERSION}/kubernetes-ontology_${KO_VERSION}_linux_amd64.tar.gz" How it starts
The opening of the file, as written. The whole thing — 703 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kubernetes Ontology Access
Guide users from zero to useful diagnosis with kubernetes-ontology.
This skill is the repository's onboarding playbook for three connected modes:
- AI-agent automatic troubleshooting through stable daemon-backed queries.
- CLI-driven topology and diagnostic inspection.
- Human visual intervention through the topology viewer.
Prefer read-only, daemon-backed workflows. The project observes Kubernetes objects and builds an in-memory graph; it must not mutate observed workloads.
Operating Posture
Do not merely summarize the docs. Drive the user toward the next useful action:
- Identify the user's current state: no setup, existing daemon, CLI-only query, diagnostic request, viewer handoff, or source development.
- Choose the shortest path that satisfies the request.
- Give concrete commands the user or agent can run next, with safe defaults named inline.
- When command output is needed, ask for or run that command before moving to later steps.
- Keep cluster-changing actions explicit: ask for confirmation before running
helm upgrade --installor any command that changes cluster resources. - Do not require a repository checkout for CLI-only diagnostics against an already running daemon.
First Response Checklist
When this skill triggers, quickly establish:
- Whether the user is inside a local checkout of this repository.
- Target cluster context and logical cluster name.
- Desired namespaces for collection (
contextNamespaces). - Deployment path: release binary server + client for private clusters or short-lived local diagnosis, Helm + release CLI when cluster nodes can pull the image, source build for development.
- Whether the environment can reach GitHub Releases and whether cluster nodes
can pull
ghcr.ioor an internal mirror. - Diagnostic entry, if known:
PodorWorkload, namespace, and name. - Whether they want the viewer opened for human inspection.
If values are missing and a safe default exists, proceed with the default and name it. Ask only for values that are required and cannot be inferred, such as the target namespace/name for a diagnostic query.
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.
- 12d ago First seen · 703 lines · 111 tokens per session scan B dc703b25cc91
kubernetes-ontology-access is a skill published in the GitHub repository Colvin-Y/kubernetes-ontology (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 111 tokens to every session and 5,513 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
nvca-self-managed-install
Install or validate the NVCA Operator chart against a self-managed NVCF control plane from the native monorepo. Use when the control plane comes from deploy/stacks/self-managed and NVCA must be installed with stack-derived image repository settings.
obol-stack
Monitor the Kubernetes cluster running the Obol Stack. Use when asked about pod status, logs, services, events, deployments, or diagnosing issues. Read-only access to own namespace via ServiceAccount.
helm
Package Kubernetes applications as Helm charts, configure values and dependencies, and inspect release upgrades or rollbacks.
kubernetes
Kubernetes orchestration authority — pods, deployments, services, ingress, helm charts, kustomize overlays, RBAC, network policies, operators, StatefulSets for databases, production-grade cluster hardening, and kubectl workflows.
bazel-k8s-expert
Expert knowledge for deploying Quarkus/Java applications to Kubernetes using Bazel. Covers rulesk8s, Helm, Kustomize, ConfigMaps, Secrets, and health probes.
Kubernetes Expert
Kubernetes Expert delivers production-grade technical work with clear architecture, tests, maintainability, and operational awareness.