Azure/AKS-Skills is a collection of agent skills for operating Azure Kubernetes Service clusters after they are provisioned. It helps compatible coding agents investigate incidents, control costs, assess AKS Automatic readiness, run GPU and inference workloads, capture packet-level evidence, and design clusters. The catalogue entries provide the skills, MCP integration, and plugin configuration for these AKS operations.
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 Azure/AKS-Skills --skill aks-cluster-setupgit clone --depth 1 https://github.com/Azure/AKS-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/azure/aks-skills/aks-cluster-setup)<a href="https://agentmods.dev/skills/azure/aks-skills/aks-cluster-setup"><img src="https://agentmods.dev/badge/skills/azure/aks-skills/aks-cluster-setup/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/azure/aks-skills/aks-cluster-setup"><img src="https://agentmods.dev/badge/skills/azure/aks-skills/aks-cluster-setup.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 | $0.00176 | $0.02161 |
| Opus 5 | $0.00088 | $0.01081 |
| Sonnet 5 | $0.00035 | $0.00432 |
| Haiku 4.5 | $0.00018 | $0.00216 |
Grade A, and why
aks-cluster-setup 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AKS Cluster Setup
This skill owns the AKS-specific design decisions for standing up a production cluster and then hands the provisioning execution to the Azure Skills deployment engine. It distinguishes Day-0 decisions (networking, API-server access — hard to change later) from Day-1 features (can be enabled post-creation). See references/cli-reference.md for the commands.
How this works with Azure Skills
This is a thin facade over provisioning — it owns the AKS design and delegates the generic provisioning execution to Azure Skills; it does not run azd or az deployment itself. It enriches the request with AKS-specific design decisions, then delegates the generic provisioning workflow to Azure Skills.
User: "Create a production AKS cluster"
│
▼
aks-cluster-setup (this skill)
│ Decides the AKS-specific design:
│ - AKS Automatic vs Standard
│ - Pod IP model (Azure CNI Overlay vs VNet-routable vs kubenet)
│ - API-server access (public / private / authorized ranges)
│ - Egress model, identity, node pools, upgrade strategy, zones
│
▼
Hands off to Azure Skills (install alongside):
├─ azure-prepare → analyzes requirements, generates the infra plan
├─ azure-validate → validates the plan, provisions a preview
└─ azure-deploy → runs azd up / az deployment to create the cluster
Install both: aks-cluster-setup for the AKS design brain, Azure Skills as the deployment engine underneath. If Azure Skills is not present, this skill still produces the full design and the exact az aks create command in references/cli-reference.md so the user can provision manually. This skill never provisions non-AKS resources — for those, use Azure Skills directly.
Rules
- Start from the user's requirements for compute, networking, security, and scale.
- Inspect the host's available tools for an Azure MCP capability that advertises AKS operations. Use the matching capability under whatever name the host assigned, inspect its advertised schema or discovery surface, and choose the smallest operation that fits. Do not gate on or construct a mapping for a literal tool name. Fall back to
az aksonly when the host exposes no matching capability or its AKS surface lacks the needed operation. - Default to AKS Automatic unless the user needs control not supported by Node Auto Provisioning. Standard is for full configurability at higher operational overhead.
- Record the rationale for every Day-0 decision (networking, API-server access) — these are expensive or impossible to change after creation.
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 · 155 lines · 176 tokens per session scan A 2542e789c78c
aks-cluster-setup is a skill published in the GitHub repository Azure/AKS-Skills (4 stars, last pushed yesterday), licensed MIT. It adds 176 tokens to every session and 2,161 once invoked, about $0.0009 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
azure-prepare
Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd…
azure-cloud-migrate
Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud…
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
ak-cloud-deploy
Deploy an Agent Kernel project to AWS, Azure, or GCP using Terraform modules, or to any Kubernetes cluster (on-prem, baremetal, EKS) using the official Helm chart. Supports serverless and containerized modes for all three clouds. AWS supports execution modes (restsync, restasync, async, stream), queue-based scalable…
azure-prepare
WORKFLOW SKILL — Prepare Azure apps for deployment (Bicep/Terraform, azure.yaml, Dockerfiles). WHEN: "create app", "build web app", "create API", "deploy to Azure", "generate Bicep", "generate Terraform", "function app", "add authentication", "managed identity". DO NOT USE FOR: cross-cloud migration…
aks-mcp
Azure Kubernetes Service (AKS) official MCP server.