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/AndresJejen/beitlab_home_lab_clusterWrote 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/rules/andresjejen/beitlab_home_lab_cluster/homelab-operator)<a href="https://agentmods.dev/rules/andresjejen/beitlab_home_lab_cluster/homelab-operator"><img src="https://agentmods.dev/badge/rules/andresjejen/beitlab_home_lab_cluster/homelab-operator/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/rules/andresjejen/beitlab_home_lab_cluster/homelab-operator"><img src="https://agentmods.dev/badge/rules/andresjejen/beitlab_home_lab_cluster/homelab-operator.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 | $0.00256 | $0.00256 |
| Opus 5 | $0.00128 | $0.00128 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
homelab-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 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.
What it actually says
Homelab operator
This repo is a generic k3s template (Pi, other SBC, or an older Debian PC).
Placeholders are lab.example, controller, worker1. Do not check in real
inventory.
- Prefer
uv run homelab/uv run ansible-playbook(seedocs/cli.md). - Single-node users:
docs/getting-started-single-node.md. - Read
AGENTS.mdanddocs/ai/README.mdbefore changing cluster state. - Never commit
inventory.ini,*.kubeconfig, or Vault init JSON. - New workloads:
homelab.local/node-pool: pi, Longhorn if they need a disk, register inapplications.json, add to shutdown/resume playbooks if PVC. - Do not delete PVCs or Longhorn volumes unless the user asks to destroy data.
- Do not run shutdown or node-remove playbooks without an explicit confirm in the current user message.
- If you are unsure, diagnose with
kubectl get/ansible pingand ask.
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 · 22 lines · 256 tokens per session scan A 80f14fdec28d
homelab-operator is a cursor rule published in the GitHub repository AndresJejen/beitlab_home_lab_cluster (5 stars, last pushed 11d ago), licensed MIT. It adds 256 tokens to every session, about $0.0013 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 2026-08-31.
Other cursor rules, from other repositories
python-containerization-cursorrules-prompt-file
Cursor rules for Python development with containerization integration.
aws-ecs
Definitive guidelines for building, deploying, and operating applications on AWS ECS, emphasizing immutable containers, secure secrets management, and robust operational patterns.
hack
Hack is local-first. This project uses hack for local runtime orchestration (compose + DNS/TLS + logs + sessions). Prefer hack when shell access is available. Use MCP only when shell access is unavailable.
colima-docker-runtime
This workspace uses Colima for Docker; use compose-backed tests when Colima is running.
local-compose-db-lifecycle-for-web-tests
Keep local compose DB lifecycle ready for web tests.
runwhen-infrastructure
Infrastructure conventions for scripts targeting Kubernetes and databases via RunWhen runners.