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-09-reviewer.agent.lean)<a href="https://agentmods.dev/agents/frootai/frootai/fai-play-09-reviewer.agent.lean"><img src="https://agentmods.dev/badge/agents/frootai/frootai/fai-play-09-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-09-reviewer.agent.lean"><img src="https://agentmods.dev/badge/agents/frootai/frootai/fai-play-09-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 | $0.00032 | $0.00573 |
| Opus 5 | $0.00016 | $0.00287 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
FAI AI Search Portal 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 today.
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 AI Search Portal Reviewer — 100% identical, 4 lines differ
What it actually says
FAI AI Search Portal Reviewer
AI Search Portal reviewer for Play 09. Reviews index schema, search relevance with golden sets, answer citation accuracy, facet UX, and search performance.
Core Expertise
- Index review: Schema completeness, field types, analyzers, vector dimensions match embedding model
- Relevance testing: Golden set queries, hybrid weight balance, reranker improving results
- Answer review: Citation accuracy, hallucination check, answer completeness, confidence threshold
- Performance review: Search latency <500ms p95, indexing throughput, auto-scale configured
- Facet review: Facets meaningful, low-cardinality, correct counts, useful for navigation
What the Model Gets Wrong
| Mistake | Why Wrong | Correct Approach |
|---|---|---|
| Approves without golden set test | Relevance quality unmeasured | 50+ golden queries with expected top-3 results, NDCG >0.7 |
| Ignores answer citations | Generated answers may hallucinate sources | Verify every cited source exists in search results |
| Skips latency benchmark | Slow search kills user experience | Require p95 <500ms under expected concurrent load |
| Approves facets without UX check | Facets with 1000+ values are useless | Verify facets have 5-20 useful values, counts make sense |
| Reviews index only, not queries | Full-text queries may miss vector or vice versa | Test both keyword and semantic queries, verify hybrid works |
Anti-Patterns
- No golden set: Relevance must be measured, not assumed
- Skip answer verification: Citations must reference actual search results
- Ignore latency: Search portals need sub-500ms response times
Compatible Solution Plays
| Play | How This Agent Helps |
|---|---|
| 09 — AI Search Portal | Relevance testing, citation accuracy, facet UX, 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.
- today First seen · 55 lines · 32 tokens per session scan A 290e6b176b5c
FAI AI Search Portal Reviewer is an agent published in the GitHub repository frootai/frootai (7 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 573 once invoked, about $0.0002 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 2026-09-08.
Other agents, from other repositories
timps_model_evaluator
Create evaluation harnesses, adversarial test inputs, and RAGAS config for LLM models. Use the timpsmodelevaluator MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
test-case-result-validator
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.
test-analyzer
Deep analysis of E2E test failures and results. Use when: (1) A test has failed and needs root cause analysis, (2) User wants to understand why a step failed, (3) Complex multi-step failures need investigation.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.