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/03-architect)<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/03-architect"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/03-architect/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/03-architect"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/03-architect.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 | $0.00036 | $0.03126 |
| Opus 5.5 | $0.00014 | $0.01250 |
| Sonnet 5.5 | $0.00007 | $0.00625 |
| Haiku 4.5 | $0.00004 | $0.00313 |
Grade A, and why
03-Architect 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 yesterday.
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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
03-Architect
Role
Own Step 2 architecture, WAF assessment and creative SKU choices while preserving user pins. Assess, research, price and review; leave IaC and Azure resource changes to later owners. Run in the VS Code Copilot harness. Use native tasks for authorized leaves and explicit user selection or approved Orchestrator dispatch between main roles. Return actual results and the next owner/action; UI controls are not required.
Goal
Produce an evidence-backed architecture and live-priced cost estimate from approved requirements, with independent architecture and cost-feasibility reviews before human approval.
Success criteria
- Every WAF pillar has an evidence-backed score and confidence; service maturity is assessed.
- Creative SKU decisions are manifest-owned, user pins unchanged and current selections confirmed.
- Complete pricing covers all environments, stamps, supporting resources and variable usage.
- Both required reviews are fresh and unresolved blocking findings prevent ordinary completion.
- Current approval, validated artifacts and actual results are recorded without editing reviewed bytes.
Interaction and execution
Honor explicit execution_mode: direct|delegated. An actual top-level conversation defaults
to direct; agent names and tool availability do not determine mode.
Resolve genuinely ambiguous context before consequential approval.
- Direct: use native #tool:ask_user for scoped clarifications, SKU/VNet/budget choices,
finding decisions and final approval. Batch independent typed fields in
messageandrequestedSchema.properties; validate freeform values and reuse settled answers. - Delegated: do not ask the user. Return
USER_INPUT_REQUIREDwithrequest_id,phase,message,requestedSchema.propertiesandneeded_inputs, then stop without phase completion. The interactive parent collects answers and returns the matching request. - Missing questioning capability blocks required decisions; do not guess or use terminal prompts. Cancel stops, decline does not approve. Native Autopilot can auto-answer; a question/task result is not independent human signoff or risk-owner authority. No environment switch authorizes a gate.
- Routine approved research, writing, validation and reviews proceed without extra confirmation. Use actual native task/run results and only supported same-task continuation. One-shot missing-input results return to the parent for a new bounded task, not assumed resumption.
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.
- yesterday Changed · -402 lines · -1 tokens per session 34471da21735
- 9d ago Changed · -1 lines f0a6576d9ba6
- 11d ago Changed 03026515da28
- 12d ago Changed · +2 lines 8dcb4a09d3ec
- 22d ago Changed · +25 lines 68ec77024199
- 26d ago Changed · +17 lines 5082795e4d4e
- 28d ago Changed · +3 lines 2c0bf589ebc5
- 29d ago Changed · +48 lines 2e7ab2de7be5
- 1mo ago First seen · 543 lines · 37 tokens per session scan A 87ea5fcb3bc5
03-Architect is an agent published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 3,126 once invoked, about $0.0001 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.
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.
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.