Borrowing it
Nothing to install: this file belongs to timothywarner-org/context-engineering. 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/timothywarner-org/context-engineering/main/.claude/skills/azure-iac-bicep/SKILL.mdgit clone --depth 1 https://github.com/timothywarner-org/context-engineeringWrote 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/timothywarner-org/context-engineering/azure-iac-bicep)<a href="https://agentmods.dev/skills/timothywarner-org/context-engineering/azure-iac-bicep"><img src="https://agentmods.dev/badge/skills/timothywarner-org/context-engineering/azure-iac-bicep/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/timothywarner-org/context-engineering/azure-iac-bicep"><img src="https://agentmods.dev/badge/skills/timothywarner-org/context-engineering/azure-iac-bicep.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 | $0.00150 | $0.01603 |
| Opus 5 | $0.00075 | $0.00801 |
| Sonnet 5 | $0.00030 | $0.00321 |
| Haiku 4.5 | $0.00015 | $0.00160 |
Grade A, and why
azure-iac-bicep 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.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure IaC: Bicep + ARM
Production-grade Azure infrastructure as code. Bicep is the default authoring language; ARM JSON is the compile target and the fallback for tooling that has not adopted Bicep. Decompile legacy ARM to Bicep, never hand-author new ARM JSON.
When to load reference files
This file is the index. Load the deeper material only when the task needs it:
| You are... | Read |
|---|---|
| Authoring a module, picking a scope, choosing decorators, wiring outputs | references/module-patterns.md |
| Migrating ARM JSON to Bicep, or deciding Bicep vs ARM vs Terraform | references/arm-vs-bicep.md |
| Running lint / what-if / deploy / deployment stacks, or building a CI pipeline | references/deploy-runbook.md |
Documentation-first mandate
Resource API shapes drift. Before emitting any resource declaration, confirm the type, apiVersion, and required properties against the live schema rather than memory:
- Call the
mcp__azure__bicepschematool for the exact resource type (for exampleMicrosoft.Storage/storageAccounts) to get current apiVersion and property names. - For Terraform-adjacent questions, call
mcp__azure__azureterraformbestpractices. - For broader service guidance, call
mcp__azure__get_azure_bestpracticesandmcp__ms-learn__microsoft_docs_search.
If those tools are unavailable, state plainly that you are reasoning from training knowledge and flag that the user must validate the apiVersion against the current provider schema. Never invent an apiVersion or a property name. A template that fails at deploy time on a bad property is a sprint blocker.
Non-negotiable authoring rules
- No secrets in templates or parameter files. Reference Key Vault with the
getSecret()function from a.bicepparamfile or aMicrosoft.KeyVault/vaultsexistingreference. Never a literal password, key, or connection string. Mark sensitive parameters@secure(). - Identity over keys. Default to system-assigned managed identity and RBAC role assignments. Reach for shared keys or SAS only when a service genuinely lacks managed-identity support, and say so.
- Parameterize environment, not structure. Parameters carry what changes per environment (name prefixes, SKUs, region, scale). The resource graph stays declarative and identical across environments.
- Idempotent by construction. Bicep deployments are incremental and re-runnable. Use deterministic names (
uniqueString(resourceGroup().id)patterns) so re-runs converge rather than duplicate. - Every parameter is decorated.
@description()on every parameter and output.@allowed(),@minLength(),@maxLength(),@minValue(),@maxValue()wherever a constraint exists. - Comments justify design, not syntax. Explain why a SKU, a scope, or a dependency exists. The Bicep already shows what.
- Modules for reuse, not for everything. Extract a module when a unit is reused or independently testable. Do not shred a single-purpose template into ceremony.
What ships with it
3 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.
- 9d ago First seen · 123 lines · 150 tokens per session scan A ede6000eea5b
azure-iac-bicep is a skill published in the GitHub repository timothywarner-org/context-engineering (27 stars, last pushed 2mo ago), licensed MIT. It adds 150 tokens to every session and 1,603 once invoked, about $0.0007 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 skills, from other repositories
claude-memory
Access the persistent memory database (PostgreSQL claudememory) for long-term context across Claude Code sessions. Triggers on "what do I know about", "memory lookup", "recall", "memory db", "what did we decide about", "similar conversations", "lookup context", "/memory". Provides semantic search, SQL queries and the…
project-context-loader
Load relevant memory, decisions and contacts for the current project at the start of a session.
modal
Serverless GPU cloud for ML jobs and model APIs.
torchtitan
Pretrain LLMs at scale with PyTorch 4D parallelism.
publish-site
Versioned site deploys to GitHub/Cloudflare/Netlify Pages.
cloudflare-temporary-deploy
Deploy a Worker live, no account, via wrangler --temporary.