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 automateyournetwork/netclaw --skill k8s-workload-inventorygit clone --depth 1 https://github.com/automateyournetwork/netclawWrote 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/automateyournetwork/netclaw/k8s-workload-inventory)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/k8s-workload-inventory"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/k8s-workload-inventory/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/automateyournetwork/netclaw/k8s-workload-inventory"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/k8s-workload-inventory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 9 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00051 | $0.00813 |
| Opus 5 | $0.00026 | $0.00407 |
| Sonnet 5 | $0.00010 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
k8s-workload-inventory 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kubernetes Workload Inventory
Server
k8s-mcp — vendored third-party, read-only, 7 tools: pods_list, pods_list_in_namespace, pods_get,
namespaces_list, events_list, resources_list, resources_get. See
k8s-network-policy for the shared preflight.
Always say which scope you covered
pods_list is cluster-wide; pods_list_in_namespace is not. State which you used. Leaving it ambiguous
is how "12 pods" gets read as the whole cluster when it was one namespace.
And say which cluster answered — an operator with several must never have to guess.
Report failures, never omit them
A pod that is not Running is the interesting one. Give its phase and reason:
| Phase / reason | Means |
|---|---|
Pending + Unschedulable |
no node satisfies its requests or affinity |
Pending + ContainerCreating |
image pull or volume mount in progress |
ImagePullBackOff / ErrImagePull |
wrong image, wrong tag, or missing pull secret |
CrashLoopBackOff |
starts and dies repeatedly — check events_list |
Running but not Ready |
readiness probe failing. It is not serving traffic |
Evicted |
node pressure |
Running is not Ready. A pod can be Running and serving nothing. Report both, and never summarise a
set of pods as "healthy" on phase alone.
Events give the why
events_list explains what a pod status only names. Events are time-limited (typically one hour) — an
empty event list for an old problem means the events aged out, not that nothing happened. That is
another empty-result trap: say "no events in the retention window", not "no events".
Empty results
The six-cause table in k8s-network-policy applies. Most relevant here: a non-existent namespace and an
empty namespace both return zero pods. Check namespaces_list before concluding.
Boundaries
| Want to… | Use |
|---|---|
| Pod CPU/memory over time | prometheus, grafana — this is the object model, not metrics |
| Actual traffic | kubeshark-traffic |
| Whether traffic is permitted | k8s-network-policy |
| Why a service has no endpoints | k8s-service-path |
| Build a lab | containerlab, gns3, cml |
| Change anything | nothing here. Read-only; Secrets are denied |
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 · 73 lines · 51 tokens per session scan A 92edb26231cd
k8s-workload-inventory is a skill published in the GitHub repository automateyournetwork/netclaw (651 stars, last pushed 3d ago), licensed Apache-2.0. It adds 51 tokens to every session and 813 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
kubernetes
Kubernetes operations playbook for deploying services: core objects, probes, resource sizing, safe rollouts, and fast kubectl debugging.
troubleshooting
A troubleshooting guide for Kubernetes, a system for running containerized applications across computers. It lists commands for checking clusters, nodes, components, pods, events, resources, and storage.
k8s-dns-failure
A guide for diagnosing and fixing DNS problems in Kubernetes, a system for running containerised applications. It focuses on CoreDNS, the component that helps services find one another and reach external services.
kubernetes-operator
Deploy and manage applications on Kubernetes. Covers deployments, services, ingress, HPA, secrets, and production-grade cluster configuration.
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.
network-rca
Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…