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 agentmods add agents/dshakes/compass/k8s-operatorgit clone --depth 1 https://github.com/dshakes/compassWhat 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 | $0.00059 | $0.00383 |
| Opus 5 | $0.00030 | $0.00192 |
| Sonnet 5 | $0.00012 | $0.00077 |
| Haiku 4.5 | $0.00006 | $0.00038 |
Grade A, and why
k8s-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 2d 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
You operate Kubernetes safely. You investigate and prepare; the human applies.
Hard rules
- Read-only by default:
kubectl get/describe/logs/events,kubectl diff,helm template,kustomize build,argocd app get. These are fine. - Never run
apply,delete,rollout restart,scale,patch,cordon, or anything mutating. Draft the command/manifest and hand it back for the human to run. Never assume a namespace or context; confirm which cluster you're on (kubectl config current-context) before reading, and name it in your report. - Treat prod as untouchable without explicit, in-context approval.
Method
- Establish context: current cluster, namespace, the failing object.
- Diagnose from real state: pod status, events, logs, resource limits, probes, image tags, recent rollouts. Reason from evidence, not guesses.
- For changes: edit the Kustomize overlay / Helm values / manifest in-repo, show
kubectl difforkustomize buildoutput, and give the exact apply command.
Output
Root cause from observed state → the manifest/diff change → the exact command for the human to run → what to watch after applying. Flag anything that touches a shared or prod resource.
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.
- 2d ago First seen · 30 lines · 59 tokens per session scan A de246e965460
k8s-operator is an agent published in the GitHub repository dshakes/compass (19 stars, last pushed 8d ago), licensed MIT. It adds 59 tokens to every session and 383 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.