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 tahirraufkeeyu/software-development-agent-stack--sdas --skill cluster-healthgit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/cluster-health)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/cluster-health"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/cluster-health/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/tahirraufkeeyu/software-development-agent-stack--sdas/cluster-health"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/cluster-health.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 | $0.00075 | $0.03182 |
| Opus 5 | $0.00037 | $0.01591 |
| Sonnet 5 | $0.00015 | $0.00636 |
| Haiku 4.5 | $0.00007 | $0.00318 |
Grade A, and why
cluster-health 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 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.
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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
- User inherits a cluster and wants a baseline report.
- Alerts are firing but the root cause is unclear — need a structured triage before drilling into a single service.
- Before running any changes (Helm upgrade, CNI swap, node pool recycle), confirm the cluster is green.
- Post-incident: validate that the cluster is back to baseline.
- Recurring "some pods are weird" complaints that need systematic triage.
Do not use this skill for application-level debugging (use the owning service's logs), for cloud-provider outages (check provider status page), or for cost reviews (separate skill).
Inputs
- Kubeconfig context (single cluster per run; run again per context for multi-cluster estates).
- Optional: list of critical namespaces to give extra weight (e.g.
payments,ingress,kube-system). - Optional: an incident time window to focus event triage on.
Outputs
A report with these sections:
- Cluster summary: version, node count, region, CNI, ingress controller.
- Node table:
node | role | version | conditions | CPU util | mem util | disk util | PID util | age. - Control-plane check: API server reachability, scheduler, controller-manager, etcd (or managed control plane indicators), admission webhooks.
- Critical DaemonSets: CNI, CSI, kube-proxy, node-exporter, log shipper, cert-manager, ingress.
ready / desiredper DaemonSet. - Pod lifecycle: counts of
Running,Pending,CrashLoopBackOff,ImagePullBackOff,Error,Terminating. - Event triage: last 1 h of
Warning-level events grouped by reason. - Findings ladder:
blocker/high/medium/low/info, each with a concrete command or manifest fix.
Tool dependencies
kubectl(≥ 1.27),jq,yq.kubectl top(requires metrics-server).kubectl-neat,sternoptional for prettier output.- Kubernetes MCP for batched list/describe.
- Optional:
kubeval,kube-score,popeyefor deeper static checks.
Procedure
- Detect the stack. Before running any diagnostic commands, confirm the target is a Kubernetes cluster this skill can read:
kubectl config current-context— must return a context. Empty output → stop; this skill requireskubernetes.kubectl auth can-i get nodes— must returnyes. Ifno, the current kubeconfig lacks the permissions required for a cluster-wide health check; stop and ask the user for a kubeconfig with at least read access across the cluster.kubectl version --short 2>&1 | head -3— record client and server versions; warn on deprecated (<1.27) server versions.
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 · 219 lines · 75 tokens per session scan A e1b8c58c4ea2
cluster-health is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 3,182 once invoked, about $0.0004 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
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.