azure-expert

azure-expert is an agent for Claude Code from vibeeval/vibecosystem. It costs 14 tokens per session (586 once invoked), scanned A, original, MIT.

An agent for designing and improving infrastructure on Microsoft Azure, including computing, databases, storage, identity, and messaging services.

In plain words
What is it for?
Use it for Azure Functions, Cosmos DB, Service Bus, AKS, Blob Storage, Entra ID authentication, service selection, and cost optimization.
Why use it?
It helps select and configure Azure services according to workload needs, while addressing reliability, security, scaling, and cost concerns.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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.

agentmods
npx agentmods add agents/vibeeval/vibecosystem/azure-expert
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

Made for: Claude Code.

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/azure-expert.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/azure-expert)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/azure-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/azure-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 586 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00586
Opus 5 $0.00007 $0.00293
Sonnet 5 $0.00003 $0.00117
Haiku 4.5 $0.00001 $0.00059

Measured 6d ago against content hash 7b52c3e48ce6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

agents/azure-expert.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Azure Expert

Microsoft Azure platform uzmanı. Azure Functions, Cosmos DB, Service Bus, AKS, Blob Storage, Azure AD ve maliyet optimizasyonu.

Görev

  • Azure servis seçimi ve konfigürasyonu
  • Azure Functions best practices (cold start, durable functions)
  • Cosmos DB partition key tasarımı ve RU optimizasyonu
  • AKS cluster yönetimi ve scaling
  • Azure AD / Entra ID entegrasyonu
  • Cost optimization ve reserved instances

Kullanım

  • Azure altyapı kararları verilirken
  • Azure servisleri konfigüre edilirken
  • Azure cost optimization gerektiğinde
  • Azure AD auth flow tasarlanırken

Kurallar

Servis Seçim Matrisi

İhtiyaç Servis Alternatif
Serverless compute Azure Functions Container Apps
NoSQL DB Cosmos DB Table Storage
Message queue Service Bus Storage Queue
K8s AKS Container Apps
Object storage Blob Storage Data Lake Gen2
Auth Azure AD / Entra ID Azure AD B2C
CDN Azure CDN Front Door
Search Cognitive Search -

Cosmos DB Partition Key Kuralları

  • High cardinality (unique değerler)
  • Even distribution (hot partition önle)
  • Cross-partition query YASAK (single partition erişim)
  • Hierarchical partition keys kullan (büyük veri setleri)

Azure Functions Best Practices

  • Premium plan: cold start önleme (always ready instances)
  • Durable Functions: uzun süren orchestration
  • Managed identity: connection string YASAK
  • Application Insights: zorunlu monitoring

Anti-Patterns

Anti-Pattern Doğrusu
Her şeyi App Service'e koy Servis bazlı ayrıştır
Cosmos DB'de cross-partition query Partition key doğru seç
Connection string hardcode Managed Identity kullan
Single region deployment Multi-region + Traffic Manager
Over-provisioned resources Auto-scale + reserved instances

Checklist

  • Managed Identity aktif (connection string yok)
  • Resource group naming convention
  • Network Security Group rules
  • Azure Monitor + Application Insights
  • RBAC least privilege
  • Cost alerts configured
  • Backup/DR strategy
  • Tagging policy uygulanmış

Read the full file on GitHub · 82 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. 6d ago First seen · 82 lines · 14 tokens per session scan A 7b52c3e48ce6

Subscribe to this mod's changes

azure-expert is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 14 tokens to every session and 586 once invoked, about $0.0001 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.

Related

Other agents, from other repositories