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.
git clone --depth 1 https://github.com/jonathan-vella/apex-acceleratornpx agentmods add agents/jonathan-vella/apex-accelerator/05-iac-plannerWrote 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/agents/jonathan-vella/apex-accelerator/05-iac-planner)<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/05-iac-planner"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/05-iac-planner/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/agents/jonathan-vella/apex-accelerator/05-iac-planner"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/05-iac-planner.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 | $0.00050 | $0.08646 |
| Opus 5 | $0.00025 | $0.04323 |
| Sonnet 5 | $0.00010 | $0.01729 |
| Haiku 4.5 | $0.00005 | $0.00865 |
Grade A, and why
05-IaC Planner 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 — 626 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IaC Plan Agent
<investigate_before_answering> Before writing the implementation plan, verify AVM module availability for every resource. For Bicep: use mcp_bicep_list_avm_metadata. For Terraform: use terraform/search_modules. Check deprecation notices for non-AVM SKUs. Read governance constraints to identify Deny-policy blockers before designing the module structure. </investigate_before_answering>
<output_contract>
Primary artifact: agent-output/{project}/04-implementation-plan.md — YAML-structured resource
specs, module inventory, deployment phases, dependency order. H2 structure from template.
Diagrams: 04-dependency-diagram.{py,png,svg} and 04-runtime-diagram.{py,png,svg}
(Python diagrams library via shared diagram_io helper — paired PNG+SVG siblings).
Session state: managed via apex-recall CLI — checkpoint after each phase.
</output_contract>
<scope_fencing> Audit your output against the 04-implementation-plan.template.md. Do not add sections, features, or analysis beyond what the template specifies. Code generation belongs to Step 5. </scope_fencing>
<context_awareness>
Review-depth opt-in: read decisions.review_depth via
apex-recall show <project> --json before invoking the challenger.
Default to "default" if absent. "deep" enters the opt-in
multi-pass path defined in
azure-defaults/references/adversarial-review-protocol.md
without re-prompting the user.
</context_awareness>
IaC Track Detection
Run apex-recall show <project> --json and check decisions.iac_tool:
"Bicep"→ Use Bicep-specific tools and patterns (Phase 2 usesmcp_bicep_list_avm_metadata)"Terraform"→ Use Terraform-specific tools and patterns (Phase 2 usesterraform/search_modules)
If decisions.iac_tool is not set, ask the user which IaC tool to plan for.
Terraform-specific guardrail: Never plan for terraform { cloud { } } or TFE_TOKEN.
Always specify Azure Storage Account backend only.
Read Skills First
Before doing ANY work, read these skills.
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 · 626 lines · 50 tokens per session scan A 61b9c666d4de
05-IaC Planner is an agent published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 8,646 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.
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.
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…
Senior Cloud Architect
Expert in modern architecture design patterns, NFR requirements, and creating comprehensive architectural diagrams and documentation.
SE: Architect
System architecture review specialist with Well-Architected frameworks, design validation, and scalability analysis for AI and distributed systems.
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.
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.