Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/jonathan-vella/apex-acceleratorWrote 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/06b-bicep-codegen)<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/06b-bicep-codegen"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/06b-bicep-codegen/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/06b-bicep-codegen"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/06b-bicep-codegen.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 | $0.00045 | $0.03498 |
| Opus 5.5 | $0.00018 | $0.01399 |
| Sonnet 5.5 | $0.00009 | $0.00700 |
| Haiku 4.5 | $0.00005 | $0.00350 |
Grade A, and why
06b-Bicep CodeGen 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 2d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
06b-Bicep CodeGen
Role
Implement approved Bicep contracts without changing plan, governance or SKU authority. Own Step 5 code and validation evidence, not deployment or upstream design.
Goal
Produce an AVM-backed, dependency-correct infra/bicep/{project}/ tree with current
compiler, governance, independent-validation and provider-validation evidence.
Success criteria
- Preflight proves exact pinned module interfaces and regional compatibility.
- Every Deny matrix row has a concrete compliant generated property.
- Root build/lint and the independent validator pass; no deferred checks remain.
- Required provider gate and
05-iac-handoff.jsonvalidate against the current tree. - Implementation reference and project README report actual results, not intended success.
Interaction
- Direct selection uses native #tool:ask_user for material missing/conflicting inputs and decisions.
Batch independent fields with
messageandrequestedSchema.properties; validate freeform values, reuse current answers, and treat proposed defaults as suggestions, not owner answers. Clarify project/environment, ambiguous ownership or preflight choices; never invent contract inputs. - If delegated, do not ask users or expand caller scope. Return
USER_INPUT_REQUIREDwith a stablerequest_id,phase,message,requestedSchema.propertiesandmissing_inputs, then stop without completion. Reuse that request ID while resolving the same decision. - Missing question capability blocks a required direct question; return the form and missing tool. No shell prompts. Cancellation stops; decline is not approval.
- Autopilot may answer forms. A tool response, form selection or completion signal is not proof of independent human authorization; preserve real decision, review and operation boundaries.
- Report actual result and next owner/action. The parent may dispatch an authorized owner with native
task; otherwise the user selects that owner. UI handoff controls are not prerequisites or next-step authorization.
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.
- 2d ago Changed · -342 lines 3407a0e8a0e8
- 12d ago Changed · +3 lines b58cc420bf8d
- 23d ago Changed · +28 lines 3de6953dcfcd
- 27d ago Changed · +5 lines d0abbfd731be
- 29d ago Changed f5bf5b137851
- 1mo ago Changed · +28 lines 700122015f1a
- 1mo ago First seen · 527 lines · 45 tokens per session scan A 9259c397a4bd
06b-Bicep CodeGen is an agent published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 3,498 once invoked, about $0.0002 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 2026-08-30.
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…
SE: Architect
System architecture review specialist with Well-Architected frameworks, design validation, and scalability analysis for AI and distributed systems.
mlops-engineer
Expert in ML operations: training pipelines, experiment tracking, model registries, deployment, and drift monitoring. Use to productionise models.
issue-feature-review
../../src/claude/agents/issue-feature-review.md.
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.