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 capacity-obtainabilitygit 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/capacity-obtainability)<a href="https://agentmods.dev/skills/gke-labs/kube-agents/capacity-obtainability"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/capacity-obtainability/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/capacity-obtainability"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/capacity-obtainability.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 | $0.00151 | $0.06097 |
| Opus 5.5 | $0.00060 | $0.02439 |
| Sonnet 5.5 | $0.00030 | $0.01219 |
| Haiku 4.5 | $0.00015 | $0.00610 |
Grade A, and why
capacity-obtainability 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 25d 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 — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GKE Capacity Obtainability
Quota and capacity are different questions. Quota is a project limit you can raise by asking; obtainability is whether the hardware is actually free in a zone right now, and no amount of quota makes a stocked-out shape appear. This skill gathers live evidence for both, records it in a form a reviewer can verify, and states the distinction in the answer.
It is diagnosis and design only: nothing here creates a cluster, applies a manifest, opens a Pull Request, or mutates cloud or Kubernetes state.
How to use it
Loaded from a design, planning, or capacity-check request — for example the gke-cluster-creation preflight.
Run the checks
- Run every check under Diagnostics below: quota, reservations, usage, and capacity advice.
- Run the capacity advice for Spot and Flex-Start — the two provisioning
models
gcloud beta compute advice capacityaccepts (--provisioning-model=SPOTandFLEX_START) — and read the per-zone signals from each response. On-Demand has no advance obtainability signal: assess it through quota headroom and reservations, and say so. Your final answer must weigh all three paths — On-Demand, Spot, and Flex-Start — with their trade-offs. - Report quota and live obtainability separately, and include this sentence verbatim in your final report: "Quota is separate from live capacity." Quota is a project limit; it does not prove hardware is obtainable, and obtainability evidence does not raise quota. Never use the word "guarantee" about capacity, allocations, or scheduling anywhere in the report — not even for reservations or ProvisioningRequests; write "reserves", "holds", or "provides once scheduled" instead.
Record what you executed as typed evidence
Use the record_evidence tool — one record per check, built from the real
command output, never from memory. "Design-only", "planning-only", and
"text output only" in a task never waive these records: those
constraints forbid mutations — applying, submitting, creating — and the
typed records are not mutations, they are how the work is delivered. A
task that asks for the answer "as text" still gets its record_evidence
call per check and its attach_artifact call per manifest, alongside the
prose; skipping them delivers a claim, not evidence. If record_evidence
or attach_artifact is not among your tools, do not stop and do not skip
the check: put the same
JSON under an ## Evidence heading in your report, and the manifests as
fenced YAML there, so the record still reaches the reader.
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.
- 25d ago Changed · +221 lines · +45 tokens per session 360b70bc4a61
- 1mo ago First seen · 302 lines · 106 tokens per session scan A e31c9a15e4b5
capacity-obtainability is a skill published in the GitHub repository gke-labs/kube-agents (109 stars, last pushed today), licensed Apache-2.0. It adds 151 tokens to every session and 6,097 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".