FAI Deterministic Agent Reviewer

FAI Deterministic Agent Reviewer is an agent for Claude Code from frootai/frootai. It costs 39 tokens per session (593 once invoked), scanned A, original, MIT.

A reviewer for AI agents designed to produce repeatable, validated results. It tests repeated outputs, safety checks, resistance to instruction overrides, JSON schemas, and confidence thresholds.

In plain words
What is it for?
Use it to test whether the same input produces the same output, all guardrail layers run, schemas match the API contract, and confidence decisions are reliable.
Why use it?
It helps reveal inconsistent behavior, validation bypasses, weak defenses against manipulative prompts, and poorly calibrated confidence scores.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to test whether the same input produces the same output, all guardrail layers run, schemas match the API contract, and confidence decisions are reliable.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/frootai/frootai/fai-play-03-reviewer.agent.lean
Install

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.

Clone the repo
git clone --depth 1 https://github.com/frootai/frootai

Made for: Claude Code.

Wrote 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.

agentmods badge for FAI Deterministic Agent Reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/frootai/frootai/fai-play-03-reviewer.agent.lean.svg)](https://agentmods.dev/agents/frootai/frootai/fai-play-03-reviewer.agent.lean)
Your own site
<a href="https://agentmods.dev/agents/frootai/frootai/fai-play-03-reviewer.agent.lean"><img src="https://agentmods.dev/badge/agents/frootai/frootai/fai-play-03-reviewer.agent.lean.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 593 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00593
Opus 5 $0.00019 $0.00296
Sonnet 5 $0.00008 $0.00119
Haiku 4.5 $0.00004 $0.00059

Measured 4d ago against content hash b767a88b6e18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

FAI Deterministic Agent 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/fai-play-03-reviewer.agent.lean.md · 55 lines

What it actually says

FAI Deterministic Agent Reviewer

Deterministic Agent reviewer for Play 03. Reviews reproducibility, guardrail completeness, anti-sycophancy defense, schema validation, and confidence calibration.

Core Expertise

  • Determinism verification: Same input → same output (100 repetitions), seed consistency, temperature=0 enforced
  • Guardrail completeness: All 6 layers present, no bypass paths, error handling at each layer
  • Anti-sycophancy testing: Adversarial prompts that pressure override, contradiction handling
  • Schema validation review: JSON schemas match API contract, all fields covered, error types defined
  • Confidence calibration: Score distribution analysis, false positive/negative rates, threshold appropriateness

What the Model Gets Wrong

Mistake Why Wrong Correct Approach
Approves without consistency test Reproducibility not verified Require 100-run consistency test: same input = same output
Ignores guardrail bypass paths Edge cases skip validation Trace every input through all 6 guardrail layers
Skips adversarial testing Agent vulnerable to user pressure Test with "ignore instructions" prompts, verify resistance
Approves confidence scores untested Calibration unknown, false confidence risk Check score distribution, verify abstention at low confidence
Reviews code only, not config temperature=0.3 in config breaks determinism Always validate config/openai.json: temperature=0, seed set

Anti-Patterns

  • Review without running tests: Always execute consistency + adversarial test suites
  • Approving partial guardrails: All 6 layers required, no exceptions
  • Config review skipped: Bad config == broken determinism even with good code

Compatible Solution Plays

Play How This Agent Helps
03 — Deterministic Agent Reproducibility audit, guardrail review, adversarial testing
Changes

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.

  1. 4d ago First seen · 55 lines · 39 tokens per session scan A b767a88b6e18

Subscribe to this mod's changes

FAI Deterministic Agent Reviewer is an agent published in the GitHub repository frootai/frootai (7 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 593 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 2026-09-03.

Related

Other agents, from other repositories

frontend-test-engineer

Frontend test engineer for Arthur MCP. Use when writing, reviewing, debugging, or improving frontend tests for React pages, feature components, hooks, API client behavior, routing, permissions, i18n, forms, and user-visible flows with Vitest and React Testing Library.

alexmmatos/arthur-mcp · 59 tokens

pydantic-ai-validator

Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.

croakingtoad/context-engineering-mcp · 46 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens