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/frootai/frootaiWrote 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/frootai/frootai/fai-play-12-reviewer.agent.lean)<a href="https://agentmods.dev/agents/frootai/frootai/fai-play-12-reviewer.agent.lean"><img src="https://agentmods.dev/badge/agents/frootai/frootai/fai-play-12-reviewer.agent.lean/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/frootai/frootai/fai-play-12-reviewer.agent.lean"><img src="https://agentmods.dev/badge/agents/frootai/frootai/fai-play-12-reviewer.agent.lean.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 | $0.00037 | $0.00594 |
| Opus 5.5 | $0.00015 | $0.00238 |
| Sonnet 5.5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
FAI Model Serving AKS Reviewer 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- FAI Model Serving AKS Reviewer — 100% identical, 4 lines differ
What it actually says
FAI Model Serving AKS Reviewer
Model Serving AKS reviewer for Play 12. Reviews GPU node pool configuration, vLLM serving settings, autoscaling thresholds, pod security, and inference latency.
Core Expertise
- Cluster review: Node pool config, GPU SKU matches model size, autoscaler limits, taints/tolerations
- Serving review: vLLM config optimal, batch size, memory allocation, API compatibility
- Scaling review: HPA thresholds tested, scale-up time acceptable, scale-down safe (drain)
- Security review: Pod security enforced, workload identity, no root containers, image scanning
What the Model Gets Wrong
| Mistake | Why Wrong | Correct Approach |
|---|---|---|
| Approves without load test | Autoscaling untested, fails at production traffic | Require load test results: p95 latency, GPU utilization, scale-up time |
| Ignores GPU memory overcommit | vLLM OOM kills crash serving pods | Verify gpu_memory_utilization ≤ 0.90, check actual usage under load |
| Skips PDB check | Node upgrades kill all replicas | Verify PodDisruptionBudget minAvailable: 1 on serving deployments |
| Approves without health probes | Broken pods receive traffic | Verify liveness + readiness probes, model-loaded check on /ready |
| Reviews YAML only, not runtime | Config looks fine but runtime behavior differs | Verify serving pods are actually using GPU (nvidia-smi in pod) |
Anti-Patterns
- No load testing: GPU serving must be load-tested before production
- Skip GPU memory review: OOM kills are the #1 vLLM failure mode
- YAML-only review: Always verify runtime behavior in cluster
Compatible Solution Plays
| Play | How This Agent Helps |
|---|---|
| 12 — Model Serving AKS | GPU cluster, vLLM, scaling, security, latency review |
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.
- 1mo ago First seen · 54 lines · 37 tokens per session scan A 2cf7e1c755da
FAI Model Serving AKS Reviewer is an agent published in the GitHub repository frootai/frootai (7 stars, last pushed 5d ago), licensed MIT. It adds 37 tokens to every session and 594 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 2026-09-08.
Other agents, from other repositories
06t-Terraform CodeGen
Expert Azure Terraform IaC specialist that creates near-production-ready Terraform configurations following Azure Verified Modules (AVM-TF) standards. Validates, tests, and ensures code quality.
timps_disaster_recovery
Design RTO/RPO-aware DR plans, failover runbooks, and DR test scripts for cloud systems. Use the timpsdisasterrecovery MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
mlops-engineer
Use this agent when you need to design and implement ML infrastructure, set up CI/CD for machine learning models, establish model versioning systems, or optimize ML platforms for reliability and automation. Invoke this agent to build production-grade experiment tracking, implement automated training pipelines…
render-expert
Expert in Render.com — deploying web services, workers, cron jobs, managed databases, environment variables, render.yaml (Infrastructure as Code), and production best practices. Use to configure, optimize, or debug deployments on Render.
Azure Reservation Planner
Plans Azure Reserved Instances and Azure Savings Plans across subscriptions and management groups, taking into account Azure Hybrid Benefit eligibility and dev-test rate structures.
Spot Orchestrator
Designs spot / preemptible / low-priority VM strategies that deliver 60-90% cost reduction without sacrificing reliability. Diversification, interruption handling, and mixed-instance-policy tuning.