trainer-demo-deploy: Skill for Claude Code

.github/skills/az-azure-validate/SKILL.md

azure-validate is a skill for Claude Code, Codex from MicrosoftLearning/trainer-demo-deploy. It costs 36 tokens per session (3,338 once invoked), scanned A, original, MIT.

A set of checks for Azure infrastructure before and after deployment. It checks login, subscriptions, Bicep templates, parameters, required Azure services, planned changes, and the health of deployed resources.

In plain words
What is it for?
It is for validating Azure deployments with template linting, what-if analysis, resource-provider checks, and post-deployment health checks.
Why use it?
It helps catch invalid templates, missing access, missing services, and unexpected destructive changes before deployment, then confirms that deployment worked.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

This is MicrosoftLearning/trainer-demo-deploy's own configuration. It tells Claude Code and Codex how to work on trainer-demo-deploy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything trainer-demo-deploy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MicrosoftLearning/trainer-demo-deploy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MicrosoftLearning/trainer-demo-deploy/main/.github/skills/az-azure-validate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MicrosoftLearning/trainer-demo-deploy

Made for: Claude Code, Codex.

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.

agentmods badge for azure-validate

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoftlearning/trainer-demo-deploy/az-azure-validate/github.svg)](https://agentmods.dev/skills/microsoftlearning/trainer-demo-deploy/az-azure-validate)
Your own site
<a href="https://agentmods.dev/skills/microsoftlearning/trainer-demo-deploy/az-azure-validate"><img src="https://agentmods.dev/badge/skills/microsoftlearning/trainer-demo-deploy/az-azure-validate/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.

agentmods 80×15 button for azure-validate

Your own site · 80×15
<a href="https://agentmods.dev/skills/microsoftlearning/trainer-demo-deploy/az-azure-validate"><img src="https://agentmods.dev/badge/skills/microsoftlearning/trainer-demo-deploy/az-azure-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,338 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.03338
Opus 5.5 $0.00014 $0.01335
Sonnet 5.5 $0.00007 $0.00668
Haiku 4.5 $0.00004 $0.00334

Measured today against content hash 239e8a0676b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

azure-validate 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 today.

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.

.github/skills/az-azure-validate/SKILL.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Azure Validate Skill

Pre-deployment and post-deployment validation gates that ensure Azure infrastructure is ready for deployment and correctly provisioned afterward. Used by the Deploy agent as hard gates before executing any deployment.


1. Pre-Deployment Validation Gates

All gates must pass before deployment proceeds. Each gate is a hard stop — failure means the deployment cannot continue until the issue is resolved.

[!CAUTION] GATE FAILURE POLICY: If a gate fails and cannot be auto-remediated, present the failure to the user and ask how to proceed. Do NOT autonomously skip deployment or generate a dry-run summary. The user must explicitly decide whether to:

  1. Fix the issue and retry
  2. Skip the gate (accepting risk)
  3. Abort the deployment

Gate Sequence

Gate 1: Authentication    → az login / azd auth status
Gate 2: Subscription      → correct subscription selected
Gate 3: Template          → bicep build + bicep lint pass
Gate 4: Parameters        → required params have values
Gate 5: Resource Providers → all needed providers registered
Gate 6: What-If           → no unexpected destructive changes

2. Gate 1 — Authentication Check

Azure CLI

# Check if logged in
$account = az account show 2>$null | ConvertFrom-Json
if (-not $account) {
    Write-Error "Not authenticated. Run 'az login' first."
    exit 1
}
Write-Host "Authenticated as: $($account.user.name)"
Write-Host "Tenant: $($account.tenantId)"

Azure Developer CLI

# Check azd authentication
azd auth login --check-status

Expected Output

Field Check
user.name or user.type Non-empty; matches expected identity
tenantId Matches the target tenant
state Enabled

[!WARNING] Service principal authentication (user.type: "servicePrincipal") may have restricted permissions compared to interactive login. Verify RBAC before proceeding.

Read the full file on GitHub · 410 lines

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.

  1. today First seen · 410 lines · 36 tokens per session scan A 239e8a0676b0

Subscribe to this mod's changes

azure-validate is a skill published in the GitHub repository MicrosoftLearning/trainer-demo-deploy (31 stars, last pushed 11d ago), licensed MIT. It adds 36 tokens to every session and 3,338 once invoked, about $0.0001 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 2026-11-07.

Related

azure-validate compared with skills from other repositories

azure-validate next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
azure-validateMicrosoftLearning/trainer-demo-deploySkill3111d agoMITA36Claude Code, Codex
gke-compute-classesgoogle/skillsSkill23ktodayApache-2.0A83Claude Code, Codex
gke-reliabilitygoogle/skillsSkill23ktodayApache-2.0A85Claude Code, Codex
gke-workload-securitygoogle/skillsSkill23ktodayApache-2.0A171Claude Code, Codex
cloud-architectJeffallan/claude-skillsSkill12k7d agoMITA71Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9ktodayApache-2.0A30Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2ktodayMITA78Claude Code