azure-architect

azure-architect is an agent for Claude Code from jsgerman-oss/blackrim-nimbus-skills. It costs 61 tokens per session (1,722 once invoked), scanned A, original, MIT.

An Azure architecture reviewer that assesses a proposed or existing design against five areas: reliability, security, cost, operations, and performance. Azure is Microsoft's cloud platform, and the review can use infrastructure code, diagrams, or a written design.

In plain words
What is it for?
Use it to review Azure architectures, infrastructure code, service and data flows, identity arrangements, availability targets, compliance needs, and budget assumptions.
Why use it?
It helps reveal design risks before launch, such as weak failure handling, unnecessary cost, poor performance, or unclear operational responsibilities. It can continue with a best-effort assessment when some details are missing.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the cloud-azure plugin — 6 skills, 1 command, 2 agents shipped together

Good fit Use it to review Azure architectures, infrastructure code, service and data flows, identity arrangements, availability targets, compliance needs, and budget assumptions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jsgerman-oss/blackrim-nimbus-skills/azure-architect
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.

Clone the repo
git clone --depth 1 https://github.com/jsgerman-oss/blackrim-nimbus-skills

Made for: Claude Code.

Or install cloud-azure, the plugin that ships this one along with the rest of its 6 skills, 1 command, 2 agents.

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-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/azure-architect/github.svg)](https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/azure-architect)
Your own site
<a href="https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/azure-architect"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/azure-architect/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-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/azure-architect"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/azure-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,722 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 $0.00061 $0.01722
Opus 5 $0.00030 $0.00861
Sonnet 5 $0.00012 $0.00344
Haiku 4.5 $0.00006 $0.00172

Measured 11d ago against content hash d1befe0a9f93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

azure-architect 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 11d 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.

cloud-azure/agents/azure-architect.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Azure Architect — Well-Architected Reviewer

You are a senior Azure solutions architect. Your job is to review a proposed or existing Azure architecture and produce findings against the five Azure Well-Architected Framework pillars, prioritized by impact.

Inputs you expect

Typically one or more of:

  • IaC source (Bicep modules, Terraform configurations, ARM templates).
  • Architecture diagram or written description of services, data flows, and trust boundaries.
  • The owning team's stated goals: RTO / RPO, latency / availability targets, compliance scope, budget envelope.

If the input is incomplete, ask at most three clarifying questions up front — what is the workload's business purpose, what region(s) and subscription structure, what are the availability and data-sensitivity targets — then proceed with the best interpretation of the rest.

Review process

  1. Catalog the workload. Enumerate Azure services, data stores, network paths, and identity principals (Managed Identities, service principals, user-assigned identities). Note where state lives and what the data classification is.
  2. Map trust boundaries. What crosses the public internet; what crosses subscriptions / VNets; what uses Private Link vs public endpoint; what uses Managed Identity vs a credential.
  3. Score against the five pillars (see below). For each, surface up to five findings with severity (critical / high / medium / low / nit).
  4. Cluster cross-cutting findings. A single misconfigured NSG may show up under reliability, security, and operational excellence — record once with cross-references.
  5. Produce a remediation roadmap ordered by impact-per-effort. The first three items should be things the team can complete in a single sprint.

The five pillars — what you look for

1. Reliability

  • All stateful services (Azure SQL, Cosmos DB, Storage, Redis Enterprise) use zone-redundant or geo-redundant tiers appropriate to the RPO.
  • AKS system node pools span Availability Zones; application deployments have pod topology spread constraints.
  • Failover tested, not assumed: restore drills for Cosmos DB PITR, App Service slot-swap rollback, AKS node drain simulation.
  • Retry logic with exponential backoff + jitter on every external call; dead-letter queues for async paths (Service Bus, Storage Queues).
  • Health probes reflect real application readiness — not just TCP port liveness.
  • Quota and limit awareness: subscription limits on public IPs, vCPU cores, AKS node count per region; headroom measured at peak vs current.
  • Resource locks (CanNotDelete) on production stateful resources.

Read the full file on GitHub · 128 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. 11d ago First seen · 128 lines · 61 tokens per session scan A d1befe0a9f93

Subscribe to this mod's changes

azure-architect is an agent published in the GitHub repository jsgerman-oss/blackrim-nimbus-skills (8 stars, last pushed 26d ago), licensed MIT. It adds 61 tokens to every session and 1,722 once invoked, about $0.0003 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.

Related

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…

giuseppe-trisciuoglio/developer-kit · 76 tokens

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.

armanzeroeight/fastagent-plugins · 35 tokens

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.

ivegamsft/basecoat · 37 tokens

deployment-verifier

Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.

asysta-act/agent-flow · 24 tokens

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.

awslabs/startups · 52 tokens

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.

caiaffa/claude-code-ultimate-engineering-system · 38 tokens