Azure Skills Plugin is an agent plugin that packages Azure-specific guidance with MCP server configurations for carrying out Azure work. Coding agents use it to plan, deploy, troubleshoot, monitor, govern, and optimize Azure applications and services. The catalogue entries are the plugin's skills, instructions, and execution integrations.
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 microsoft/azure-skills --skill azure-local-multi-rackgit clone --depth 1 https://github.com/microsoft/azure-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/microsoft/azure-skills/azure-local-multi-rack)<a href="https://agentmods.dev/skills/microsoft/azure-skills/azure-local-multi-rack"><img src="https://agentmods.dev/badge/skills/microsoft/azure-skills/azure-local-multi-rack/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/microsoft/azure-skills/azure-local-multi-rack"><img src="https://agentmods.dev/badge/skills/microsoft/azure-skills/azure-local-multi-rack.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 | $0.00159 | $0.00895 |
| Opus 5.5 | $0.00064 | $0.00358 |
| Sonnet 5.5 | $0.00032 | $0.00179 |
| Haiku 4.5 | $0.00016 | $0.00089 |
Grade A, and why
azure-local-multi-rack 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 1mo 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.
This is a copy
100% identical to azure-local-multi-rack — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Local Multi-Rack
Multi-rack is in preview — say so, and confirm availability from the docs before committing to a design.
Quick Reference
| Property | Value |
|---|---|
| Best for | Rack-scale Azure Local: 100+ machines, preintegrated racks, SAN, managed fabric |
| Scale | Minimum four racks — one aggregation rack plus three or more compute racks |
| Providers | Microsoft.NetworkCloud, Microsoft.ManagedNetworkFabric, Microsoft.AzureStackHCI |
| CLI | az networkcloud, az networkfabric, az stack-hci-vm |
| Related skill | azure-local for standard 1-16 node and rack-aware deployments |
When to Use This Skill
Use when the deployment is multi-rack / rack scale: preintegrated racks, an aggregation rack, a Network Fabric Controller, a Cluster Manager, SAN storage, or the networkcloud / managednetworkfabric CLI extensions.
Do not use for standard Azure Local (1-16 node hyperconverged, up to 64 disaggregated) or rack-aware clusters — hand off to the azure-local skill. If the scale is unclear, ask first: the two have separate, non-interchangeable procedures for the same-sounding tasks (logical networks, VM creation, NSGs).
MCP Tools
No dedicated MCP namespace. Use generic Azure MCP tools: mcp_azure_mcp_extension_cli_generate (confirm networkcloud/networkfabric extensions first), mcp_azure_mcp_monitor (needs Log Analytics), mcp_azure_mcp_resourcehealth (partial; not fabric or SAN health), mcp_azure_mcp_documentation (multi-rack articles only — standard Azure Local pages do not apply).
Details: cli-and-prereqs.
Workflow
- Confirm this is multi-rack, not standard Azure Local — see When to Use.
- Plan/deploy -> plan-and-deploy
- VMs, AKS, images, disks -> workload-management
- Fabric, isolation domains, load balancers, NSGs -> networking
- Monitoring, metrics, serial console, failures -> operate-and-monitor
What ships with it
8 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.
- references/cli-and-prereqs.md 2.5 KB
- references/docs-map.md 4.0 KB
- references/resource-types.md 2.7 KB
- references/safety-rules.md 2.3 KB
- workflows/networking/networking.md 2.9 KB
- workflows/operate-and-monitor/operate-and-monitor.md 2.9 KB
- workflows/plan-and-deploy/plan-and-deploy.md 3.5 KB
- workflows/workload-management/workload-management.md 2.6 KB
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.
- 1mo ago First seen · 55 lines · 159 tokens per session scan A b544007ce978
azure-local-multi-rack is a skill published in the GitHub repository microsoft/azure-skills (1,572 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 895 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to azure-local-multi-rack, differing in 0 lines, and is treated as a copy.
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…
google-cloud-filestore-autoscale
Inspects Filestore capacity and utilization on Google Cloud, evaluates storage scaling rules, and performs capacity autoscaling (scale UP for low free space or scale DOWN for cost optimization). Use when monitoring Filestore instance headroom, resizing instance shares, configuring automated growth/shrink thresholds…
terraform-module-library
Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
vast-gpu
Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.
doca-hardware-safety
Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-parameter write, NIC firmware burn, BFB reflash, NIC ↔ DPU mode flip, SR-IOV or device-emulation slot enable, kernel boot-parameter change (IOMMU, hugepages, VFIO), PCIe…
aws-lambda-microvms
Builds, runs, debugs, and operates applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments running inside a container with up to 8 hr lifetimes. Applicable when workloads need strong isolation between tenants, isolated serverless compute, sandbox compute, or…