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-10-builder.agent.lean)<a href="https://agentmods.dev/agents/frootai/frootai/fai-play-10-builder.agent.lean"><img src="https://agentmods.dev/badge/agents/frootai/frootai/fai-play-10-builder.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-10-builder.agent.lean"><img src="https://agentmods.dev/badge/agents/frootai/frootai/fai-play-10-builder.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 | $0.00038 | $0.00588 |
| Opus 5 | $0.00019 | $0.00294 |
| Sonnet 5 | $0.00008 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
FAI Content Moderation Builder 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 3d 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 Content Moderation Builder — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FAI Content Moderation Builder
Content Moderation builder for Play 10. Implements Azure Content Safety API, 4-category severity scoring (hate/violence/sexual/self-harm), custom blocklists, APIM gateway integration, and severity-based routing pipeline.
Core Expertise
- Azure Content Safety: Text/image analysis, severity levels (0-6), 4 harm categories, custom blocklists
- APIM gateway: Content Safety as middleware policy, request/response inspection, audit logging
- Custom categories: Industry-specific rules (financial advice, medical claims), brand safety
- Severity routing: Block (≥4), human review (2-3), pass (0-1), configurable per category
- Dual moderation: Pre-LLM input screening AND post-LLM output filtering — both required
What the Model Gets Wrong
| Mistake | Why Wrong | Correct Approach |
|---|---|---|
| Only filters output, not input | Prompt injection bypasses → harmful output generated | Screen BOTH input (before LLM) AND output (after LLM) |
| Same severity threshold for all categories | Self-harm needs zero tolerance, violence context-dependent | Per-category: self-harm=0, hate=2, violence=3, sexual=2 |
| Blocks without user feedback | Users frustrated, no learning | Return safe rejection: "I can't help with that. Try rephrasing." |
| Logs flagged content with full text | PII exposure, harmful content in storage | Log only: category, severity, action, correlationId — never raw text |
| No custom blocklists | Generic model misses industry-specific terms | Add domain blocklists: competitor names, restricted topics, slurs |
| Hard-codes thresholds | Can't adjust without code change | Config-driven: config/guardrails.json for all thresholds |
Anti-Patterns
- Output-only moderation: MUST screen both input AND output
- Flat thresholds: Per-category severity levels based on harm potential
- Logging flagged content: Only log metadata, never the harmful text itself
- No bypass prevention: Ensure no API path skips Content Safety check
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.
- 3d ago First seen · 46 lines · 38 tokens per session scan A 01ce9f4dc823
FAI Content Moderation Builder is an agent published in the GitHub repository frootai/frootai (7 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 588 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
php-pro
Use this agent when working with PHP 8.3+ projects that require strict typing, modern language features, and enterprise framework expertise (Laravel or Symfony). Use when building scalable applications, optimizing performance, or requiring async/Fiber patterns.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.