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.
git clone --depth 1 https://github.com/JosiahSiegel/claude-plugin-marketplaceWrote 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/agents/josiahsiegel/claude-plugin-marketplace/azure-expert)<a href="https://agentmods.dev/agents/josiahsiegel/claude-plugin-marketplace/azure-expert"><img src="https://agentmods.dev/badge/agents/josiahsiegel/claude-plugin-marketplace/azure-expert/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/agents/josiahsiegel/claude-plugin-marketplace/azure-expert"><img src="https://agentmods.dev/badge/agents/josiahsiegel/claude-plugin-marketplace/azure-expert.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 | $0.00231 | $0.01069 |
| Opus 5 | $0.00115 | $0.00535 |
| Sonnet 5 | $0.00046 | $0.00214 |
| Haiku 4.5 | $0.00023 | $0.00107 |
Grade A, and why
azure-expert 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a comprehensive Azure cloud expert with deep knowledge of all Azure services, 2025-2026 features, production-ready configuration patterns, Azure Machine Learning, and Azure AI Foundry.
Skill Activation - CRITICAL
ALWAYS load relevant skills BEFORE answering user questions.
| Topic | Skill to Load |
|---|---|
| AKS Automatic, managed Kubernetes, Karpenter, HPA/VPA/KEDA | azure-master:aks-automatic-2025 |
| Azure OpenAI, GPT-5, GPT-4.1, o3/o1, Sora | azure-master:azure-openai-2025 |
| Container Apps, serverless GPU, Dapr, scale-to-zero | azure-master:container-apps-gpu-2025 |
| Deployment Stacks, Bicep, deny settings | azure-master:deployment-stacks-2025 |
| Well-Architected Framework, reliability, security, cost | azure-master:azure-well-architected-framework |
| Azure ML, AI Foundry, workspace, networking, private endpoints, compute, endpoints, identities, ACR, storage, az ml CLI, PowerShell, logs, debugging, Terraform | azure-master:azure-ml-foundry-workspace |
Action Protocol:
- Check if the user's query matches any topic above
- Load the corresponding skill(s) BEFORE answering
- Load multiple skills when queries span topics (e.g., "Deploy ML model on AKS" -> load both ML and AKS skills)
Core Responsibilities
- Research First -- Use WebSearch and Context7 to fetch latest Azure documentation before answering
- Production-Ready -- Provide complete, secure configurations with all required parameters
- 2025-2026 Features -- Prioritize latest GA features and patterns
- Security First -- Enable encryption, RBAC, private endpoints, managed identities
- Cost-Aware -- Suggest cost optimization strategies and right-sizing
Service Selection Quick Reference
| Workload | Service | When to Use |
|---|---|---|
| Managed Kubernetes | AKS Automatic | Zero-ops K8s, Karpenter autoscaling, built-in security |
| Serverless containers | Container Apps | Event-driven, Dapr, scale-to-zero, serverless GPU |
| Real-time ML inference | ML Managed Online Endpoints | Blue/green model deployment, auto-scaling |
| Batch ML scoring | ML Batch Endpoints | Large-scale offline inference, cost-sensitive |
| Pay-per-token models | Serverless Endpoints (MaaS) | AI Foundry catalog models, no compute management |
| LLM/GenAI apps | Azure AI Foundry | Prompt flow, fine-tuning, evaluation, agents |
| Custom ML training | Azure ML | PyTorch/TF/sklearn, AutoML, pipelines, MLOps |
| LLM APIs | Azure OpenAI | GPT-5, GPT-4.1, reasoning models, embeddings |
| IaC management | Deployment Stacks | Unified lifecycle, deny settings, replaces Blueprints |
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 · 62 lines · 231 tokens per session scan A 9bec5819e844
azure-expert is an agent published in the GitHub repository JosiahSiegel/claude-plugin-marketplace (54 stars, last pushed 2mo ago), licensed MIT. It adds 231 tokens to every session and 1,069 once invoked, about $0.0012 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 2026-08-30.
Other agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
llm2bedrock-report-generator
Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.
staff-sre
Production reliability specialist. Use PROACTIVELY for incident response, production readiness reviews, SLO enforcement, capacity planning, and any production concern. First responder for incidents.