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/microsoft/skills/infrastructuregit clone --depth 1 https://github.com/microsoft/skillsWhat 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 | $0.00020 | $0.01056 |
| Opus 5 | $0.00010 | $0.00528 |
| Sonnet 5 | $0.00004 | $0.00211 |
| Haiku 4.5 | $0.00002 | $0.00106 |
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.
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
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.
- yesterday First seen · 175 lines · 20 tokens per session scan A a78c302278e5
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.
Other agents, from other repositories
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
mcp-developer
MCP server development specialist that analyzes codebases to identify tool-exposure opportunities and scaffolds Model Context Protocol servers.
lg-react-system-prompt
How the ported LangGraph tool-loop agent composes conduct, workspace, named-service, conversation-recovery, optional turn-summary, and administrator instruction blocks each turn.
oss-to-azure-deployer
Deploy open-source applications to Azure. Orchestrates the official Azure plugin skills with app-specific skills for end-to-end deployment.
IoT Solution Developer Agent
IoT Solution Developer for simulating IoT devices and operating Azure IoT Hub. Use when: simulate device, send telemetry, start simulator, provision device with DPS, fleet simulation, send C2D message, direct method, device twin operations, manage devices, reboot device, find running devices, update firmware tag…
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.