07b-Bicep Deploy

07b-Bicep Deploy is an agent for Claude Code from jonathan-vella/apex-accelerator. It costs 55 tokens per session (6,431 once invoked), scanned A, original, MIT.

An agent that deploys approved Bicep templates to Azure and manages the deployment process. It previews expected changes before applying them and records what was deployed.

In plain words
What is it for?
Use it to preview and provision Azure infrastructure, require approval before applying or making destructive changes, verify deployed resources, and create a deployment summary.
Why use it?
It provides a controlled deployment step with review gates, post-deployment checks, and a clear result when deployment succeeds or fails.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; mentions subagents.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is [`iac-common/references/deploy-shared-workflow.md`](../skills/iac-common/references/deploy-shared-workflow.md).

Good fit Use it to preview and provision Azure infrastructure, require approval before applying or making destructive changes, verify deployed resources, and create a deployment summary.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jonathan-vella/apex-accelerator
agentmods
npx agentmods add agents/jonathan-vella/apex-accelerator/07b-bicep-deploy

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 07b-Bicep Deploy

README.md
[![agentmods](https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/07b-bicep-deploy.svg)](https://agentmods.dev/agents/jonathan-vella/apex-accelerator/07b-bicep-deploy)
Your own site
<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/07b-bicep-deploy"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/07b-bicep-deploy.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,431 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 $0.00055 $0.06431
Opus 5 $0.00028 $0.03216
Sonnet 5 $0.00011 $0.01286
Haiku 4.5 $0.00006 $0.00643

Measured 8d ago against content hash a22fc55c8162, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

07b-Bicep Deploy 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 8d 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.

.github/agents/07b-bicep-deploy.agent.md · 566 lines

How it starts

The opening of the file, as written. The whole thing — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bicep Deploy Agent

Role: Step 6 deployment executor. Provisions Bicep templates to Azure via azd provision (default) or az deployment group create, manages preflight + what-if gating, and produces the deployment summary handoff.

Goal

Take an approved Bicep workspace at infra/bicep/{project}/ and bring the target Azure subscription to the desired state for the next uncompleted phase, returning a verified 06-deployment-summary.md and a clear handoff signal (success → 08-As-Built; failure → 06b-Bicep CodeGen). The user must always retain explicit approval at the what-if gate and at any destructive operation.

Success criteria

  • 06-deployment-summary.md written with deployed resource IDs, phase identifier, duration, and subscription/resource-group context.
  • az deployment group what-if (or azd provision --preview) ran cleanly and the user explicitly approved before any apply step.
  • Post-deploy verification confirms each resource exists in Azure Resource Graph and matches the declared SKU + region.
  • Session state is updated via apex-recall checkpoint/decide/finding for the step transition.
  • A handoff label is rendered: success path → 08-As-Built; failure path → 06b-Bicep CodeGen with a structured error excerpt.

Constraints

  • Require explicit approval for any Delete (-) operation surfaced by what-if.
  • Validate authentication via az account get-access-token before any deployment command; if it fails, STOP and ask the user to re-authenticate rather than retrying silently.
  • If infra/bicep/{project}/ is missing, malformed, or fails bicep build, STOP and request handoff to the Bicep Code agent. Do not attempt to author template fixes from this agent.
  • Prefer azd for projects with azure.yaml; fall back to az deployment only for legacy projects without an azd manifest. Do not introduce deploy.ps1.
  • Reasoning effort: rely on Copilot runtime default; do not request high reflexively.

Output

The artifact contract is captured below in ## Output and ## Validation Checklist. Use the templates in .github/skills/azure-artifacts/templates/ for 06-deployment-summary.md (H2 layout), and follow ## Deployment Execution and ## Post-Deployment Verification for the surrounding workflow.

Read the full file on GitHub · 566 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. 8d ago First seen · 566 lines · 55 tokens per session scan A a22fc55c8162

Subscribe to this mod's changes

07b-Bicep Deploy is an agent published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 6,431 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Curated Cloud Remediation Generator

Turns Tenable Cloud Security findings into review-ready CLI and OpenTofu/Terraform remediation artifacts for a curated, safety-tiered set of AWS and Azure policies. Never modifies your cloud.

tenable/cyberagents-exchange · 45 tokens

azure-iac-exporter

Export existing Azure resources to Infrastructure as Code templates via Azure Resource Graph analysis, Azure Resource Manager API calls, and azure-iac-generator integration. Use this skill when the user asks to export, convert, migrate, or extract existing Azure resources to IaC templates (Bicep, ARM Templates…

github/awesome-copilot · 70 tokens

Senior Cloud Architect

Expert in modern architecture design patterns, NFR requirements, and creating comprehensive architectural diagrams and documentation.

github/awesome-copilot · 22 tokens

SE: Architect

System architecture review specialist with Well-Architected frameworks, design validation, and scalability analysis for AI and distributed systems.

github/awesome-copilot · 26 tokens

FAI Kubernetes Expert

Kubernetes specialist — pod scheduling, GPU resource management, network policies, Helm charts, GitOps with Flux/ArgoCD, and production-grade AI workload orchestration on AKS.

frootai/frootai · 42 tokens

vllm-deployer

An agent definition for deploying vLLM, a tool for serving large language models. The available description indicates that it includes a role, capabilities, decision process, commands, and GPU-readiness checks.

aws-samples/sample-oh-my-aidlcops · 89 tokens