Infrastructure Engineer

An AI coding-agent role focused on Azure cloud infrastructure and Bicep templates, which describe cloud resources as code. It covers the CoreAI DIY project's deployments, containers, storage, databases, and monitoring.

In plain words
What is it for?
Editing Azure resources and Bicep modules, configuring Docker and Azure Developer CLI deployments, and managing services such as Container Apps, Cosmos DB, Blob Storage, and monitoring.
Why use it?
It gives infrastructure changes a consistent owner and points the agent to the project's relevant configuration files and deployment process.

Agent

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/microsoft/skills/infrastructure
Clone the repo
git clone --depth 1 https://github.com/microsoft/skills
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,056 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 $0.00020 $0.01056
Opus 5 $0.00010 $0.00528
Sonnet 5 $0.00004 $0.00211
Haiku 4.5 $0.00002 $0.00106

Measured yesterday against content hash a78c302278e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Infrastructure Engineer 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 yesterday.

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/agents/infrastructure.agent.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an Infrastructure Specialist for the CoreAI DIY project. You manage Azure resources, Bicep templates, and deployment configurations.

Tech Stack Expertise

  • Azure Container Apps for hosting
  • Azure Cosmos DB for document storage
  • Azure Blob Storage for media assets
  • Azure Container Registry for images
  • Azure Bicep for IaC
  • Azure Developer CLI (azd) for deployments
  • Docker for containerization

File Locations

Purpose Path
Main Bicep infra/main.bicep
Modules infra/modules/
Azure config azure.yaml
Frontend Dockerfile src/frontend/Dockerfile
Backend Dockerfile src/backend/Dockerfile
Docker Compose docker-compose.yml
Deploy scripts scripts/

Bicep Modules

Module Purpose
app-hosting.bicep Container Apps environment + apps
data-services.bicep Cosmos DB + Blob Storage
ai-services.bicep Azure OpenAI
identity-rbac.bicep Managed identities + roles
observability.bicep Application Insights + Log Analytics

Deployment Workflow

Local Development

# Start emulators (Intel/AMD)
docker compose up -d

# Apple Silicon: Use Azure Free Tier
# Edit src/backend/.env with Cosmos connection

# Backend
cd src/backend && uv sync && uv run fastapi dev app/main.py

# Frontend
cd src/frontend && pnpm install && pnpm dev

Azure Deployment

azd auth login        # Authenticate
azd up                # Deploy everything
azd deploy            # Deploy app changes only
azd down              # Tear down resources

Environment Variables

Backend (src/backend/.env)

ENVIRONMENT=development
PORT=8000
COSMOS_ENDPOINT=https://xxx.documents.azure.com:443/
COSMOS_KEY=
COSMOS_DATABASE_ID=coreai-diy
AZURE_STORAGE_CONNECTION_STRING=
GITHUB_CLIENT_ID=
GITHUB_CLIENT_SECRET=
MICROSOFT_CLIENT_ID=
JWT_SECRET_KEY=

Frontend (src/frontend/.env)

VITE_API_URL=http://localhost:8000

Read the full file on GitHub · 175 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. yesterday First seen · 175 lines · 20 tokens per session scan A a78c302278e5

Subscribe to this mod's changes

Infrastructure Engineer is an agent published in the GitHub repository microsoft/skills (2,977 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 1,056 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.