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 gke-labs/kube-agents --skill gke-compute-classesgit clone --depth 1 https://github.com/gke-labs/kube-agentsWrote 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/gke-labs/kube-agents/gke-compute-classes)<a href="https://agentmods.dev/skills/gke-labs/kube-agents/gke-compute-classes"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/gke-compute-classes/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/gke-labs/kube-agents/gke-compute-classes"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/gke-compute-classes.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 | $0.00083 | $0.07341 |
| Opus 5.5 | $0.00033 | $0.02936 |
| Sonnet 5.5 | $0.00017 | $0.01468 |
| Haiku 4.5 | $0.00008 | $0.00734 |
Grade A, and why
gke-compute-classes 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 8d 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.
This is a copy
91% identical to gke-compute-classes — 21 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GKE ComputeClasses
Guidance on configuring, optimizing, and troubleshooting GKE ComputeClasses.
A change goes out as a pull request to the GitOps repository, never as a write from here: Kubernetes objects as YAML through
gke-manifest-generation, cluster settings and other Google Cloud resources as Config Connector YAML throughgcp-config-connector, opened withsubmit-suggestion. Each profile's config offers only thegkeMCP server's read tools, and the broker refuseskubectlandgcloudwrites.
When to Use
- Cost optimization: Spot VMs with on-demand fallback.
- GPU/TPU workloads: Target specific accelerators (e.g., L4, H100, v5p).
- Performance tuning: Select specific machine families (c3, c4, n4).
- Zone targeting: Colocate workloads with zonal resources.
CRITICAL RULES
- CODE-FIRST VERIFICATION (OPEN-SOURCE CODEBASE): GKE Cluster Autoscaler and ComputeClasses are open-sourced at
https://github.com/GoogleCloudPlatform/cluster-autoscaler. When user questions challenge or explore undocumented/subtle behaviors, or when guidance is not explicitly established in this skill, READ THE CODE WITH THEinspect-repositorySKILL: this install's terminal has nogitand cannot clone or fetch from GitHub itself, butinspect-repositoryclones broker-side and lets yougrepandfetchfiles at the clonedsha. Start from the package or symbol in the code index and cite the commit you read. It returns files without history, sogit log -Sandgit blameare the user's to run: name the symbol for them, and do not state a version or date range you have not read. Seereferences/compute-class-code-index.mdfor exact package and symbol mappings.
Engagement Rules: Generalized First, Refine Later
ComputeClasses depend on zone availability, CUDs, and workload constraints. Do not block the user's initial request. If asked for YAML/recommendations:
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/balanced-reserved-zonal-compute-class.yaml 3.6 KB
- assets/capacity-quota-spillover.yaml 775 B
- assets/computeclass-rbac-editor.yaml 1.4 KB
- assets/dynamic-rwo-storageclass.yaml 1.4 KB
- assets/equal-priority-tiebreak-compute-class.yaml 2.0 KB
- assets/genai-inference-g4-compute-class.yaml 1.9 KB
- assets/kafka-broker-compute-class.yaml 2.0 KB
- assets/log-autoscaler-events.sh 11 KB runs code
- assets/manual-pool-tiebreak-compute-class.yaml 1.5 KB
- assets/postgres-primary-compute-class.yaml 2.4 KB
- assets/redis-compute-class.yaml 1.7 KB
- assets/restrict-computeclass-usage-vap.yaml 4.1 KB
- assets/shared-l4-inference-compute-class.yaml 1.2 KB
- assets/spark-proximal-compute-class.yaml 2.4 KB
- assets/spot-cost-tiebreak-compute-class.yaml 2.4 KB
- assets/system-pool-compute-class.yaml 1.9 KB
- assets/tpu-v5e-training-compute-class.yaml 1.5 KB
- references/compute-class-autopilot-mode.md 3.8 KB
- references/compute-class-code-index.md 6.2 KB
- references/compute-class-cost-optimization.md 4.5 KB
- references/compute-class-crd-fields.md 6.5 KB
- references/compute-class-debug.md 7.3 KB
- references/compute-class-gotchas-and-cuds.md 4.2 KB
- references/compute-class-governance.md 5.1 KB
- references/compute-class-karpenter-migration.md 3.6 KB
- references/compute-class-lifecycle.md 7.2 KB
- references/compute-class-prioritization.md 8.8 KB
- references/compute-class-provisioning-methods.md 7.5 KB
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.
- 8d ago Changed · +2 lines 6a86cb3809a5
- 11d ago Changed · +53 lines e2882bf21cb9
- 1mo ago First seen · 334 lines · 83 tokens per session scan A 229307c017b3
gke-compute-classes is a skill published in the GitHub repository gke-labs/kube-agents (116 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 7,341 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to gke-compute-classes, differing in 21 lines, and is treated as a copy.
Other skills, from other repositories
openshell-cli
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, profile management, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger…
azd-deployment
Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.
cdf-orchestration-setup
Use when the user asks to deploy, install, reinstall, redeploy, upgrade, or connect to the CDF Orchestration Airflow controller. Owns the end-to-end deploy sequence and runs the cdf-orchestration-preflight audit first. Covers make setup, controller image builds, Helm installation, controller connection…
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…
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.