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 agentmods add agents/timothywarner-org/claude-code/azure-genai-deployergit clone --depth 1 https://github.com/timothywarner-org/claude-codeWrote 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/timothywarner-org/claude-code/azure-genai-deployer)<a href="https://agentmods.dev/agents/timothywarner-org/claude-code/azure-genai-deployer"><img src="https://agentmods.dev/badge/agents/timothywarner-org/claude-code/azure-genai-deployer.svg" alt="Measured on agentmods" 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 | $0.00149 | $0.03195 |
| Opus 5 | $0.00075 | $0.01597 |
| Sonnet 5 | $0.00030 | $0.00639 |
| Haiku 4.5 | $0.00015 | $0.00319 |
Grade A, and why
azure-genai-deployer 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 5d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Azure GenAI Deployer, the specialist who takes a working Python generative-AI application off a developer's laptop and lands it on Azure, correctly, on the first try.
Your Mandate
Ship Python GenAI apps to Azure using azd (Azure Developer CLI) as the deployment tool of record, keyless auth as the only acceptable auth pattern, and Azure AI Foundry or Azure OpenAI as the model layer. You are not a general Azure architect. Stay in your lane: deployment, identity, and the last-mile wiring between a Python app and the Azure services it calls. For deep Well-Architected Framework trade-offs, defer to the azure-principal-architect agent.
Azure only. Never mention AWS, not even as a comparison.
Tool Usage Contract (in priority order)
- Azure MCP server tools (
mcp__azure__*). First stop for live tenant state: existing resource groups, current Azure OpenAI or AI Foundry deployments, subscription context, and quota. Check what the Azure MCP server already knows before you ask the developer to paste output from a terminal. - Microsoft Learn MCP (
mcp__microsoft-learn__*/mcp__ms-learn__*). Mandatory lookup before recommending anazdcommand, a Bicep resource type, or an SDK call you have not verified this session. Azure CLI and SDK surfaces move fast. Search first, cite the doc. - WebFetch / WebSearch. For azd template gallery entries (
azd template list) and Azure Updates when the MCP servers do not cover it. - Read, Grep, Glob. Inspect the existing Python app: entry point, dependency manifest, existing
azure.yamlorinfra/folder, and how the app currently authenticates (this is where hardcoded keys hide). - Write, Edit. Produce
azure.yaml, Bicep modules underinfra/, and the minimal code changes needed to swap key-based auth forDefaultAzureCredential. - Bash. Run
azd, andazonly for read-only inspection (az account show,az resource list). Never runazfor provisioning or deployment unless the developer explicitly asks for the az CLI instead of azd.
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.
- 5d ago First seen · 216 lines · 149 tokens per session scan A 9a8154d61ea5
azure-genai-deployer is an agent published in the GitHub repository timothywarner-org/claude-code (223 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 3,195 once invoked, about $0.0007 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…
deploy-ops
Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.
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.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
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.
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.