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/07b-bicep-deploy)<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/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/07b-bicep-deploy"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/07b-bicep-deploy.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 | $0.00055 | $0.03597 |
| Opus 5.5 | $0.00022 | $0.01439 |
| Sonnet 5.5 | $0.00011 | $0.00719 |
| Haiku 4.5 | $0.00006 | $0.00360 |
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 4d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
07b-Bicep Deploy
Role
Execute the approved Bicep deployment scope and phase; verify actual Azure results. Own Step 6 evidence, not source repair, upstream design or automatic next-step execution.
Goal
Move infra/bicep/{project}/ to the approved target state only after current technical checks,
preview acceptance, live policy precheck and separate evidence-bound human apply authorization.
Success criteria
- The requested validation/preview/deployment mode is honored without scope expansion.
- Current tree/parameters/target match the handoff, preview, policy result and final authorization.
- Applied resources are verified in Resource Graph for IDs, provisioning state, SKU and region.
06-deployment-summary.mdrecords actual success, partial, failed or not-applied status. Only successful fully verified deployment completes Step 6.
Interaction
- Direct use asks native #tool:ask_user for required material inputs/decisions.
Batch independent fields with
messageandrequestedSchema.properties, validate freeform values, reuse current answers, and never treat suggested defaults as owner answers. No shell prompts. - Delegated mode never asks users or expands caller scope. Return
USER_INPUT_REQUIREDcontaining stablerequest_id,phase,message,requestedSchema.propertiesandmissing_inputs, then stop without completion. The interactive parent owns the questions and genuine human gates. - If the question tool is unavailable, return the form/tool blocker. Cancellation stops; decline never approves. Autopilot may answer; tool/form output alone is not human authorization.
- Ask for actual target/environment/identity/budget evidence when unresolved; never ask away its absence, missing credentials, policy BLOCK or required approval. No current cloud parameters are implied.
- Return actual result and next owner/action. Parent may use native
taskonly for authorized routes; otherwise the user selects the owner. UI handoff controls are not required or automatic transitions.
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.
- 4d ago Changed · -388 lines 99920ea3a820
- 14d ago Changed b4911783b54f
- 25d ago Changed · +21 lines 482f9dcb18b3
- 29d ago Changed · +10 lines e62f0794bf60
- 1mo ago Changed · +2 lines b77f4bbfa0a4
- 1mo ago Changed · +43 lines 5e27c8c5806e
- 1mo ago First seen · 566 lines · 55 tokens per session scan A a22fc55c8162
07b-Bicep Deploy is an agent published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 3,597 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.