prompt-pro: Skill for Claude Code

.claude/skills/bicep-deployment/SKILL.md

bicep-deployment is a skill for Claude Code from timothywarner-org/prompt-pro. It costs 99 tokens per session (1,744 once invoked), scanned A, original, MIT.

A workflow for writing and deploying Azure infrastructure with Bicep, a language for describing cloud resources and their desired setup. It covers the four Azure deployment scopes and checks planned changes before applying them.

In plain words
What is it for?
Use it to create or review Bicep files, choose an Azure deployment scope, preview infrastructure changes, deploy through GitHub Actions, or teach infrastructure-as-code practices.
Why use it?
It reduces the risk of accidentally creating, changing, or deleting Azure resources. The required lint, validation, preview, deployment, and verification steps make the intended changes visible first.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is timothywarner-org/prompt-pro's own configuration. It tells Claude Code how to work on prompt-pro itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything prompt-pro configures →

Reuse

Borrowing it

Nothing to install: this file belongs to timothywarner-org/prompt-pro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/timothywarner-org/prompt-pro/main/.claude/skills/bicep-deployment/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/prompt-pro

Made for: Claude Code.

Wrote 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.

agentmods badge for bicep-deployment

README.md
[![agentmods](https://agentmods.dev/badge/skills/timothywarner-org/prompt-pro/bicep-deployment/github.svg)](https://agentmods.dev/skills/timothywarner-org/prompt-pro/bicep-deployment)
Your own site
<a href="https://agentmods.dev/skills/timothywarner-org/prompt-pro/bicep-deployment"><img src="https://agentmods.dev/badge/skills/timothywarner-org/prompt-pro/bicep-deployment/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.

agentmods 80×15 button for bicep-deployment

Your own site · 80×15
<a href="https://agentmods.dev/skills/timothywarner-org/prompt-pro/bicep-deployment"><img src="https://agentmods.dev/badge/skills/timothywarner-org/prompt-pro/bicep-deployment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,744 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00099 $0.01744
Opus 5 $0.00049 $0.00872
Sonnet 5 $0.00020 $0.00349
Haiku 4.5 $0.00010 $0.00174

Measured 9d ago against content hash e8446618c3bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bicep-deployment 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 9d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/Deploy-Bicep.ps1, scripts/Invoke-BicepLint.ps1, scripts/Test-BicepWhatIf.ps1), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/bicep-deployment/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bicep deployment

Bicep is Azure's domain-specific language for declarative infrastructure. You describe the desired state of resources, and the Azure Resource Manager (ARM) engine figures out the create, update, or no-op needed to reach it. This skill teaches the safe deployment loop that keeps demos green and production intact.

Teaching note: every example uses the Contoso Robotics scenario (mid-size robotics manufacturer, 500 employees, Austin TX). Swap the names, keep the pattern.

The golden rule: what-if before apply

Never run a bare az deployment ... create against an environment you care about. The loop is always:

  1. Lint the template so syntax and best-practice warnings surface early.
  2. Validate so ARM checks the template against the target scope.
  3. What-if so you see the exact create / modify / delete set before anything changes.
  4. Deploy only after a human (or a gate) reads the what-if output.
  5. Verify the resources match intent, then record outputs.

The two scripts in scripts/ encode steps 1-5 so learners run the loop, not just the last line.

When to reach for this skill

  • You are about to write or review a .bicep or .bicepparam file.
  • You need to pick the right deployment scope (tenant, management group, subscription, resource group).
  • You are wiring Bicep into GitHub Actions with OIDC and want the what-if-as-gate pattern.
  • You are teaching IaC and need a clean, idempotent, real-world demo.

Quick start (Contoso Robotics)

The templates/ folder ships a deployable starter: a storage account plus a Log Analytics workspace at resource group scope. Preview then deploy with the bundled scripts.

# 0. Lint first - free, offline, catches mistakes before any login
./scripts/Invoke-BicepLint.ps1 -Path ./templates/main.bicep

# 1. Preview every change ARM would make - mutates nothing
./scripts/Test-BicepWhatIf.ps1 `
  -TemplateFile ./templates/main.bicep `
  -ParameterFile ./templates/main.bicepparam `
  -ResourceGroup rg-contoso-robotics-dev `
  -Location eastus2

# 2. Deploy after reading the what-if output. Idempotent: safe to re-run.
./scripts/Deploy-Bicep.ps1 `
  -TemplateFile ./templates/main.bicep `
  -ParameterFile ./templates/main.bicepparam `
  -ResourceGroup rg-contoso-robotics-dev `
  -Location eastus2 `
  -WhatIfFirst

Read the full file on GitHub · 108 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. 9d ago First seen · 108 lines · 99 tokens per session scan A e8446618c3bb

Subscribe to this mod's changes

bicep-deployment is a skill published in the GitHub repository timothywarner-org/prompt-pro (47 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 1,744 once invoked, about $0.0005 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.