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 vinnie357/claude-skills --skill kata-on-gkegit clone --depth 1 https://github.com/vinnie357/claude-skillsWrote 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/vinnie357/claude-skills/kata-on-gke)<a href="https://agentmods.dev/skills/vinnie357/claude-skills/kata-on-gke"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/kata-on-gke/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/vinnie357/claude-skills/kata-on-gke"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/kata-on-gke.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 72 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00088 | $0.01655 |
| Opus 5 | $0.00044 | $0.00827 |
| Sonnet 5 | $0.00018 | $0.00331 |
| Haiku 4.5 | $0.00009 | $0.00166 |
Grade A, and why
kata-on-gke scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kata-on-gke
GKE ships a managed "Agent Sandbox" add-on, but it pins runtimeClassName: gvisor. There is no managed Kata path. For microVM isolation on GKE, follow the upstream examples/kata-gke-sandbox/ recipe: a standard (non-Autopilot) GKE cluster, an Ubuntu N2 node pool with nested virtualization, and a setup.sh that installs Kata onto those nodes.
Prerequisites
- GCP project with billing enabled.
- APIs enabled: Compute Engine, Kubernetes Engine, Artifact Registry.
- IAM on the operator:
roles/container.admin,roles/compute.instanceAdmin.v1,roles/serviceusage.serviceUsageAdmin. - Nested virtualization org policy allowed for the project. The constraint to disable is
constraints/compute.disableNestedVirtualization.
Verify the constraint is not enforced:
gcloud resource-manager org-policies describe \
constraints/compute.disableNestedVirtualization \
--project=${PROJECT_ID}
# If returns "booleanPolicy.enforced: true", request the policy admin to unset it.
Machine type constraints
Kata on GKE requires N2 Intel machines (e.g. n2-standard-4). The upstream recipe lists hard exclusions:
- ❌
e2-*— no nested virt. - ❌
n2d-*(AMD) — Kata's tested path is Intel. - ❌
t2a-*(ARM) — no nested virt. - ❌ Autopilot clusters — no control over machine type / image.
Use N2 (Cascade Lake / Ice Lake Intel) Ubuntu nodes only.
Step 1 — create the cluster (Standard, Ubuntu node pool)
PROJECT_ID=...
LOCATION=us-central1
CLUSTER_NAME=kata-sandbox-cluster
gcloud container clusters create ${CLUSTER_NAME} \
--project=${PROJECT_ID} \
--location=${LOCATION} \
--num-nodes=0 \
--cluster-version=latest \
--release-channel=regular
gcloud container node-pools create kata-pool \
--project=${PROJECT_ID} \
--location=${LOCATION} \
--cluster=${CLUSTER_NAME} \
--machine-type=n2-standard-4 \
--image-type=UBUNTU_CONTAINERD \
--enable-nested-virtualization \
--num-nodes=2
--enable-nested-virtualization is the critical flag — without it, the underlying GCE instances boot without /dev/kvm and kata-deploy will install but pods will fail to start.
What ships with it
1 file 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.
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.
- 9d ago First seen · 159 lines · 88 tokens per session scan A 46a4343f15ac
kata-on-gke is a skill published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 1,655 once invoked, about $0.0004 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 2026-09-03.
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-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 disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
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".
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…