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 Sagart-cactus/claude-k8s-plugin --skill k8s-operator-workflowgit clone --depth 1 https://github.com/Sagart-cactus/claude-k8s-pluginWrote 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/sagart-cactus/claude-k8s-plugin/k8s-operator-workflow)<a href="https://agentmods.dev/skills/sagart-cactus/claude-k8s-plugin/k8s-operator-workflow"><img src="https://agentmods.dev/badge/skills/sagart-cactus/claude-k8s-plugin/k8s-operator-workflow/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/sagart-cactus/claude-k8s-plugin/k8s-operator-workflow"><img src="https://agentmods.dev/badge/skills/sagart-cactus/claude-k8s-plugin/k8s-operator-workflow.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 | $0.00018 | $0.00859 |
| Opus 5 | $0.00009 | $0.00430 |
| Sonnet 5 | $0.00004 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
k8s-workflow 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 11d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kubernetes Operator Workflow
Operating Mode
- Dev-only: Target kind clusters only. Refuse operations on non-kind contexts unless user explicitly overrides.
- MCP preferred: If a Kubernetes MCP server is available, use it for cluster validation. Otherwise, fall back to
kubectlcommands. - Safety first: Allow only
kind-*contexts. Avoid destructive operations by default.
Agent Responsibilities
- Ask questions to clarify CRD purpose, fields, validation rules, webhook type, and safety constraints.
- Generate CRD schema and example custom resources.
- Scaffold controller and webhook code using Go + Kubebuilder patterns.
- Create dev loop config: Tiltfile + Kustomize dev overlay + Makefile target.
- Create a kind cluster and install CRDs/webhooks.
- Validate behavior using MCP or
kubectland logs. - Iterate until requirements are satisfied.
Required Q&A (ask before writing code)
Always ask these 10 questions and wait for answers:
- CRD purpose (1 sentence)
- Spec fields (name + type + required?)
- Status fields (what should be reported?)
- Webhook type (validating, mutating, or both)
- Defaulting rules (if any)
- Validation rules (invariants)
- RBAC scope (namespace or cluster)
- Resource ownership (what objects are created/managed)
- Failure policy (for webhooks)
- Safety gates (annotations/labels to enable mutations)
Dev Fast Loop Workflow
Default to Tilt (tilt up or make dev) for all build and deploy cycles. Do not manually run docker build, kind load, or kustomize build | kubectl apply unless Tilt live-update cannot handle the change.
Overview
- One command:
make dev(wrapstilt up) - Tilt builds the Docker image, loads it into kind, and applies Kustomize manifests
- Local
go buildproduces the manager binary - Tilt live-update syncs the binary into the running manager pod
- Tilt kills the process to restart with new code
Iteration Cycle
- Edit Go files (types, controller, webhook)
- Tilt recompiles locally
- Binary syncs into the running pod
- Process restarts
- Check logs/events for feedback
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.
- 11d ago First seen · 96 lines · 18 tokens per session scan A b8ca6813e269
k8s-workflow is a skill published in the GitHub repository Sagart-cactus/claude-k8s-plugin (34 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 859 once invoked, about $0.0001 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.