Borrowing it
Nothing to install: this file belongs to alexpizarro/azure-lean-stack-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alexpizarro/azure-lean-stack-skills/main/CLAUDE.mdgit 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/instructions/alexpizarro/azure-lean-stack-skills/claude-md)<a href="https://agentmods.dev/instructions/alexpizarro/azure-lean-stack-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/alexpizarro/azure-lean-stack-skills/claude-md/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/instructions/alexpizarro/azure-lean-stack-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/alexpizarro/azure-lean-stack-skills/claude-md.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 | $0.02394 | $0.02394 |
| Opus 5.5 | $0.00958 | $0.00958 |
| Sonnet 5.5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade A, and why
azure-lean-stack-skills CLAUDE.md 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 1mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Azure Lean Stack (v2.3.1)
Azure apps that cost nothing when nobody's using them.
A Claude Code plugin of composable skills for scaffolding and deploying consumption-priced, low-cost Azure web apps. One thin orchestrator + 16 single-purpose sub-skills + a learnings-feedback loop. Built around branch-per-environment CI/CD where each git branch maps 1:1 to an isolated Azure resource group. Complementary to Microsoft's azure-skills plugin.
Every pattern in here is proven in at least one real production project (see RECIPES.md). If no shipping project uses it, it doesn't get added.
Plugin structure
.
├── .claude-plugin/
│ └── plugin.json # Plugin manifest (v2.3.1)
├── skills/
│ ├── orchestrating-azure-deployments/ # ORCHESTRATOR — routes to sub-skills
│ │ ├── SKILL.md
│ │ └── references/
│ │ ├── composition-with-azure-skills.md # Delegation rules to MS azure-skills
│ │ ├── architecture-decisions.md
│ │ └── stack-versions.md
│ │
│ ├── scaffolding-azure-bicep-infrastructure/ # Bicep root (SQL/Storage/Observability toggles), 3 workflows, sqlcmd installer
│ ├── configuring-azure-oidc-for-github-actions/ # SPs + federated creds + GH secrets (branch-scoped, azure/login@v3)
│ ├── managing-azure-sql-migrations/ # Migration system, sqlcmd runner
│ ├── deploying-azure-static-web-apps/ # SWA + managed functions
│ ├── deploying-fc1-flex-consumption-functions/ # FC1 (Bicep/ARM REST, CommonJS, az-CLI zip deploy, MI host storage)
│ ├── deploying-azure-container-apps/ # ACA + Jobs + sidecars + shared env + KEDA cron + retirement checklist
│ ├── scheduling-with-azure-logic-apps-consumption/ # Logic Apps recurring trigger (~$0.22/mo)
│ ├── developing-azure-apps-locally/ # Fully-offline local stack (Docker SQL + Azurite)
│ ├── optimizing-azure-blob-storage-cost/ # Lifecycle rules, CORS, tiers
│ ├── adding-azure-communication-services-email/ # ACS Email + safeSend pattern
│ ├── instrumenting-azure-app-insights/ # Workspace-based AI + dailyCap + alerts
│ ├── securing-azure-sql-and-storage-with-managed-identity/ # Entra SQL auth + user-delegation SAS via MI (flag-gated)
│ ├── scaffolding-multi-tenant-azure-apps/ # One RG per tenant pattern
│ ├── applying-azure-cost-guardrails/ # 15 guardrails, 3 audit scripts, costGuardrails.bicep (budget + stuck-warm alert)
│ ├── diagnosing-azure-deployment-failures/ # 56-entry gotcha catalogue
│ └── curating-azure-deployment-learnings/ # META: learnings → gotchas pipeline
│ ├── SKILL.md
│ └── scripts/
│ ├── capture-learning.sh
│ ├── review-learnings.sh
│ └── promote-to-gotchas.sh
│
├── evals/ # Review-spec scenarios (JSON) — no runner yet
├── CHANGELOG.md · RECIPES.md · README.md
└── learnings/ # Private field notes (gitignored — only promoted gotcha rows are shared)
└── YYYY-MM-DD_{project}.md # With frontmatter (project, severity, tags)
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.
- 1mo ago Changed · +3 lines · +88 tokens per session 35dcaa2dab39
- 1mo ago Changed · +10 lines · +429 tokens per session 5cc9f5f928d4
- 1mo ago First seen · 132 lines · 1,877 tokens per session scan A 0060762b0fb6
azure-lean-stack-skills CLAUDE.md is an instructions file published in the GitHub repository alexpizarro/azure-lean-stack-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,394 tokens to every session, about $0.0096 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.