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 llm-d-incubation/llm-d-skills --skill create-gke-infra-llm-dgit clone --depth 1 https://github.com/llm-d-incubation/llm-d-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/llm-d-incubation/llm-d-skills/create-gke-infra-llm-d)<a href="https://agentmods.dev/skills/llm-d-incubation/llm-d-skills/create-gke-infra-llm-d"><img src="https://agentmods.dev/badge/skills/llm-d-incubation/llm-d-skills/create-gke-infra-llm-d/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/llm-d-incubation/llm-d-skills/create-gke-infra-llm-d"><img src="https://agentmods.dev/badge/skills/llm-d-incubation/llm-d-skills/create-gke-infra-llm-d.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 | $0.00103 | $0.03710 |
| Opus 5 | $0.00051 | $0.01855 |
| Sonnet 5 | $0.00021 | $0.00742 |
| Haiku 4.5 | $0.00010 | $0.00371 |
Grade A, and why
create-gke-infra-llm-d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create GKE Infrastructure for llm-d
📋 Command Execution Notice
Before executing any command, I will:
- Explain what the command does - a clear description of the command's purpose and expected outcome
- Show the actual command - the exact command that will be executed
- Explain why it's needed - how this command fits into the overall provisioning workflow
🔔 ALWAYS NOTIFY THE USER BEFORE CREATING ANYTHING
RULE: Before creating ANY cloud resource - VPCs, subnets, firewall rules, clusters, node pools, DaemonSets, Helm releases, or any Kubernetes object - you MUST first tell the user what you are about to create, in which project/region, and why.
GPU node pools (A3 Ultra, A4) are expensive. Always confirm machine type, node count, and consumption model (reservation, Spot, flex-start) with the user before creating a node pool. Never guess the GCP project or region - ask if not provided.
Scope of this skill. This skill owns everything up to "the cluster is llm-d-ready": cluster, node pools, RDMA networking, DRA drivers, and Gateway API prerequisites. It is the one skill in this repository that is expected to create cluster-level and cloud-level resources. It does NOT deploy llm-d itself - when the cluster passes validation, hand off to deploy-llm-d (config already decided) or the autoconfig skill (config to be recommended).
Sources of Truth
Do not improvise commands. Every step in this skill is anchored in:
- llm-d GKE infrastructure guide:
${LLMD_PATH}/docs/infrastructure/providers/gke/README.md - llm-d RDMA and networking guide:
${LLMD_PATH}/docs/infrastructure/rdma/README.md - llm-d GKE gateway guide:
${LLMD_PATH}/docs/infrastructure/gateway/gke.md - GCP: AI Hypercomputer custom GKE cluster
- GCP: Set up GPU Dynamic Resource Allocation (DRA)
- GCP: Allocate network resources using GKE managed DRANET
- GCP: Deploying Gateways
What ships with it
4 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 First seen · 153 lines · 103 tokens per session scan A 9a0d41a70b88
create-gke-infra-llm-d is a skill published in the GitHub repository llm-d-incubation/llm-d-skills (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 103 tokens to every session and 3,710 once invoked, about $0.0005 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 2026-08-31.
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…