What is create-gke-infra-llm-d?

A guide for preparing Google Kubernetes Engine (GKE) infrastructure for llm-d, a system for running large language model workloads across Kubernetes resources.

Use it to create or prepare GKE clusters, GPU node pools, RDMA/RoCE networking, DRA and DRANET drivers, and Gateway API prerequisites for llm-d.

It helps ensure the cluster has the required compute, GPU, high-speed networking, drivers, and Gateway API prerequisites before llm-d is deployed.

create-gke-infra-llm-d — Skill by llm-d-incubation/llm-d-skills

Install

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.

Any agent

npx skills add llm-d-incubation/llm-d-skills --skill create-gke-infra-llm-d

Clone the repo

git clone --depth 1 https://github.com/llm-d-incubation/llm-d-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin create-gke-infra-llm-d — /plugin install create-gke-infra-llm-d after adding the marketplace above.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/llm-d-incubation/llm-d-skills/create-gke-infra-llm-d/github.svg)](https://agentmods.dev/skills/llm-d-incubation/llm-d-skills/create-gke-infra-llm-d)

Your own site

<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.

Your own site · 80×15

<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>

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,710 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.5	$0.00041	$0.01484
Sonnet 5.5	$0.00021	$0.00742
Haiku 4.5	$0.00010	$0.00371

Measured 2mo ago against content hash 9a0d41a70b88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

skills/create-gke-infra-llm-d/SKILL.md · 153 lines

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

Read the full file on GitHub · 153 lines

Files

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.

Changes

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.

2mo ago First seen · 153 lines · 103 tokens per session scan A 9a0d41a70b88

Subscribe to this mod's changes

create-gke-infra-llm-d is a skill published in the GitHub repository llm-d-incubation/llm-d-skills (7 stars, last pushed 8d ago), licensed Apache-2.0. It adds 103 tokens to every session and 3,710 once invoked, about $0.0004 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 2026-08-31.

Cloud DevOps and cloud

create-gke-infra-llm-d next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
create-gke-infra-llm-dllm-d-incubation/llm-d-skills	Skill	7	8d ago	Apache-2.0	A	103	Claude Code, Codex
gke-compute-classesgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	83	Claude Code, Codex
gke-reliabilitygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	85	Claude Code, Codex
gke-workload-securitygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	171	Claude Code, Codex
cloud-architectJeffallan/claude-skills	Skill	12k	7d ago	MIT	A	71	Claude Code
nemo-automodel-launcher-configNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	78	Claude Code