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.
git 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/commands/sagart-cactus/claude-k8s-plugin/create-operator)<a href="https://agentmods.dev/commands/sagart-cactus/claude-k8s-plugin/create-operator"><img src="https://agentmods.dev/badge/commands/sagart-cactus/claude-k8s-plugin/create-operator.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 5.1 | $0.00012 | $0.01004 |
| Opus 5 | $0.00006 | $0.00502 |
| Sonnet 5 | $0.00002 | $0.00201 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade A, and why
create-operator 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 7d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Kubernetes Operator
You are guiding the user through creating a Kubernetes CRD operator with webhooks and a fast Tilt-based dev loop. Follow these steps in order.
Step 1: Requirements Gathering
Ask these 10 questions and wait for answers before writing any code:
- CRD purpose: What does this operator manage? (1 sentence)
- Spec fields: What fields go in the spec? (name, type, required?)
- Status fields: What should be reported in status?
- Webhook type: Validating, mutating, or both?
- Defaulting rules: Any fields that should be auto-defaulted?
- Validation rules: What invariants must be enforced?
- RBAC scope: Namespace-scoped or cluster-scoped?
- Resource ownership: What child resources does the controller create/manage?
- Failure policy: For webhooks — Fail or Ignore?
- Safety gates: Any annotations/labels required to enable mutations?
Step 2: Scaffold the Project
Once requirements are confirmed:
-
Initialize a Kubebuilder project:
kubebuilder init --domain <domain> --repo <module> kubebuilder create api --group <group> --version v1 --kind <Kind> kubebuilder create webhook --group <group> --version v1 --kind <Kind> --defaulting --programmatic-validation -
Implement the CRD types in
api/v1/<kind>_types.gobased on the spec/status fields. -
Run
make generate && make manifeststo regenerate deepcopy and CRD manifests.
Step 3: Implement Controller Logic
Write the reconcile loop in internal/controller/<kind>_controller.go:
- Fetch the CR
- Check if deleted (handle finalizers)
- Create/update owned resources
- Update status
- Requeue as needed
Follow idempotency: the reconcile function should be safe to call multiple times.
Step 4: Implement Webhooks
In api/v1/<kind>_webhook.go:
- Defaulting: Set default values for optional fields
- Validation: Enforce invariants on create and update
- Keep webhook logic simple and fast
Step 5: Set Up Dev Loop
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.
- 7d ago First seen · 100 lines · 12 tokens per session scan A 10fbb5c3a3ba
create-operator is a command published in the GitHub repository Sagart-cactus/claude-k8s-plugin (34 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 1,004 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 commands, from other repositories
create-docker-mcp-tunnel
Stand up an Anthropic MCP tunnel locally with Docker Compose so Claude can call a private MCP server (manual-credentials quickstart).
cisco-isovalent-platform-setup
Install the Isovalent platform on Kubernetes (Cilium CNI, Hubble observability, Tetragon eBPF runtime security) in either OSS or Enterprise edition. Renders Helm values and install/upgrade scripts; this is the platform install prerequisite for the Splunk Observability + Splunk Platform integration done by…
build-agent
Build Docker images for Golden Armada agents.
application-crud
A command reference for creating and managing Coolify applications connected to private GitHub repositories. It covers application records, deployment settings, and common API errors.
review-helm
Run Helm chart review for structure, best practices, and K8s security/operational issues in templates.
docker-harden
Audits and hardens Dockerfiles for size and security.