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 gce-compute-fleet-auditgit 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/gce-compute-fleet-audit)<a href="https://agentmods.dev/skills/gke-labs/kube-agents/gce-compute-fleet-audit"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/gce-compute-fleet-audit/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/gce-compute-fleet-audit"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/gce-compute-fleet-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.00576 |
| Opus 5.5 | $0.00018 | $0.00230 |
| Sonnet 5.5 | $0.00009 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
gce-compute-fleet-audit 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.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Audit standalone GCE virtual machines, Managed Instance Groups (MIGs), serial console boot failures, sole-tenant node group headroom, and orphaned disk snapshots, emitting findings for the fleet-audit reporting harness.
Workflow
1. Open the Run, Then Execute Compute Inspection
Open the run first with the fleet-audit harness's start (SOP §0). finish refuses a manifest that finished before start did, as an earlier run's. Then call the platform_control fleet_scope tool (SOP §1) and run the compute fleet collector with its collector_args, which hand it the install's declared scope; an install that declares none passes nothing and the collector sweeps every project the identity can list. It writes a collector manifest to stdout:
python3 /opt/data/profiles/platform/skills/gce-compute-fleet-audit/scripts/compute_fleet_audit.py <collector_args from the fleet_scope tool, verbatim, or nothing on an install that declares no scope> > /opt/data/scratch/manifest_gce-compute-fleet-audit.json
2. Evaluate Findings Against SOP Checks
Read the manifest and follow /opt/data/profiles/platform/governance/gce_compute_fleet_sop.md §2, which owns the copy rules for commands, checks_not_applicable, checks_unevaluated, limitations and candidates:
All four roster checks are collector-verified; none is yours to hand-run.
gce-startup-script-status: serial console boot failures and startup script errors.mig-convergence-stalled: MIGs creating and deleting at once (a resize loop).sole-tenant-headroom: node group reservations at capacity with no failover host spare.orphaned-snapshots: Persistent Disk snapshots of deleted disks older than 90 days.
ops-agent-guest-health is not on the roster — SOP §2.3 says why, and finish rejects a checks_run or a finding.check naming it.
3. Hand Findings to Fleet Audit
Finish the run you opened in step 1 with the fleet-audit harness's finish, passing --manifest-file as the SOP's §5 directs, so it cross-checks checks_run against what the collector ran. This stream's finish requires that flag, or --no-collector-manifest with a reason.
What ships with it
2 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.
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 Changed 6fb4a9ea392d
- 14d ago Changed 6b6c35bf8558
- 19d ago Changed · +3 lines · +8 tokens per session 0aff041c31f9
- 1mo ago First seen · 33 lines · 36 tokens per session scan A 3b89c447e864
gce-compute-fleet-audit is a skill published in the GitHub repository gke-labs/kube-agents (116 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 576 once invoked, about $0.0002 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 2026-09-03.
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-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".