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 skills add alexpizarro/azure-lean-stack-skills --skill developing-azure-apps-locallygit clone --depth 1 https://github.com/alexpizarro/azure-lean-stack-skillsWrote 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/skills/alexpizarro/azure-lean-stack-skills/developing-azure-apps-locally)<a href="https://agentmods.dev/skills/alexpizarro/azure-lean-stack-skills/developing-azure-apps-locally"><img src="https://agentmods.dev/badge/skills/alexpizarro/azure-lean-stack-skills/developing-azure-apps-locally/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.
<a href="https://agentmods.dev/skills/alexpizarro/azure-lean-stack-skills/developing-azure-apps-locally"><img src="https://agentmods.dev/badge/skills/alexpizarro/azure-lean-stack-skills/developing-azure-apps-locally.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00118 | $0.01754 |
| Opus 5 | $0.00059 | $0.00877 |
| Sonnet 5 | $0.00024 | $0.00351 |
| Haiku 4.5 | $0.00012 | $0.00175 |
Grade A, and why
developing-azure-apps-locally 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 12d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developing Azure Apps Locally
Run the whole app on localhost — API + SQL + blob storage — with no dependency on Azure. This is the local "try" tier of the deployment model: local (main) → test → production.
main is never connected to an Azure environment. You iterate locally against an offline stack, then promote to test (and later production) via the branch-per-environment flow. See orchestrating-azure-deployments Architecture Decision #0.
When to use which local mode
| Mode | Command | Use for |
|---|---|---|
| Fully offline (this skill) | bash scripts/up.sh then npm start + npm run dev |
Backend work, schema changes, fast iteration, no Azure cost |
| Frontend against live test backend | cd frontend && npm run dev:test |
UI-only work that needs real test data; no local API/SQL |
Prefer fully-offline for anything touching the API, SQL, or storage.
The offline stack
- SQL Server 2022 in Docker (
mcr.microsoft.com/mssql/server:2022-latest) — the same engine Azure SQL is built on. "Serverless" is an Azure compute tier, not a local concept; the T-SQL engine is identical, so migrations and queries behave the same locally as in Azure. - Azurite (
mcr.microsoft.com/azure-storage/azurite) — local Azure Blob emulator. Blobs stream fromhttp://127.0.0.1:10000instead of Azure Storage.
Both run from templates/docker-compose.yml.
Apple Silicon: the SQL Server image is amd64. Enable Docker Desktop → Settings → General → "Use Rosetta for x86/amd64 emulation". (Azure SQL Edge was retired 2025-09 and dropped arm64, so
mssql/serverunder Rosetta is the supported high-fidelity choice.)
Workflow checklist
Copy this into your response and tick items off:
Local dev setup:
- [ ] Step 1: Docker Desktop running (Rosetta enabled on Apple Silicon)
- [ ] Step 2: Copy templates/docker-compose.yml to repo root, templates/local.settings.json.example to api/local.settings.json
- [ ] Step 3: Run scripts/up.sh — starts SQL + Azurite, applies migrations, sets Azurite CORS
- [ ] Step 4: (optional) Run scripts/seed-from-test.sh to copy a small dataset from the test env
- [ ] Step 5: cd api && npm start (Functions host on http://localhost:7071)
- [ ] Step 6: cd frontend && npm run dev (Vite on http://localhost:5173, proxies /api → 7071)
- [ ] Step 7: Verify the app loads and a DB-backed page returns data
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 106 lines · 118 tokens per session scan A 5690a4ccd518
developing-azure-apps-locally is a skill published in the GitHub repository alexpizarro/azure-lean-stack-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 1,754 once invoked, about $0.0006 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.
Other skills, from other repositories
azure-prepare
Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd…
azure-cloud-migrate
Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud…
ak-cloud-deploy
Deploy an Agent Kernel project to AWS, Azure, or GCP using Terraform modules, or to any Kubernetes cluster (on-prem, baremetal, EKS) using the official Helm chart. Supports serverless and containerized modes for all three clouds. AWS supports execution modes (restsync, restasync, async, stream), queue-based scalable…
azure-expert
Expert-level Microsoft Azure cloud platform, services, and architecture. Use when the user mentions cloud, Microsoft platforms, Azure Functions, or Cosmos DB.
azure-prepare
WORKFLOW SKILL — Prepare Azure apps for deployment (Bicep/Terraform, azure.yaml, Dockerfiles). WHEN: "create app", "build web app", "create API", "deploy to Azure", "generate Bicep", "generate Terraform", "function app", "add authentication", "managed identity". DO NOT USE FOR: cross-cloud migration…
azure-aks-platform-operator
Operate Azure Kubernetes Service with an adversarial production posture. Use for AKS architecture sanity checks, upgrade safety, node-pool strategy, workload identity, network policy, scaling, observability, and operator-readiness reviews.