gan-evaluator

gan-evaluator is an agent for Claude Code from raja21068/AutoResearch. It costs 32 tokens per session (1,777 once invoked), scanned A, a copy of gan-evaluator, MIT.

A quality-assurance agent for a live web application. It uses Playwright, a browser automation tool, to test the actual interactive app against a scoring rubric and report defects.

In plain words
What is it for?
Use it to test controls, empty and unusual inputs, rapid actions, visual quality, and overall behavior, then produce actionable feedback for the builder.
Why use it?
Testing the running product reveals interaction and edge-case problems that code inspection or screenshots may miss.

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 controls, empty and unusual inputs, rapid actions, visual quality, and overall behavior, then produce actionable feedback for the builder.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/raja21068/autoresearch/gan-evaluator
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/raja21068/AutoResearch

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 gan-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/agents/raja21068/autoresearch/gan-evaluator/github.svg)](https://agentmods.dev/agents/raja21068/autoresearch/gan-evaluator)
Your own site
<a href="https://agentmods.dev/agents/raja21068/autoresearch/gan-evaluator"><img src="https://agentmods.dev/badge/agents/raja21068/autoresearch/gan-evaluator/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.

agentmods 80×15 button for gan-evaluator

Your own site · 80×15
<a href="https://agentmods.dev/agents/raja21068/autoresearch/gan-evaluator"><img src="https://agentmods.dev/badge/agents/raja21068/autoresearch/gan-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,777 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 84% copy Near-identical to another mod 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 $0.00032 $0.01777
Opus 5 $0.00016 $0.00889
Sonnet 5 $0.00006 $0.00355
Haiku 4.5 $0.00003 $0.00178

Measured 8d ago against content hash c5d59732ebf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gan-evaluator scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. `curl` for API testing
Origin

This is a copy

84% identical to gan-evaluator — 27 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/agents/gan-evaluator.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Evaluator in a GAN-style multi-agent harness (inspired by Anthropic's harness design paper, March 2026).

Your Role

You are the QA Engineer and Design Critic. You test the live running application — not the code, not a screenshot, but the actual interactive product. You score it against a strict rubric and provide detailed, actionable feedback.

Core Principle: Be Ruthlessly Strict

You are NOT here to be encouraging. You are here to find every flaw, every shortcut, every sign of mediocrity. A passing score must mean the app is genuinely good — not "good for an AI."

Your natural tendency is to be generous. Fight it. Specifically:

  • Do NOT say "overall good effort" or "solid foundation" — these are cope
  • Do NOT talk yourself out of issues you found ("it's minor, probably fine")
  • Do NOT give points for effort or "potential"
  • DO penalize heavily for AI-slop aesthetics (generic gradients, stock layouts)
  • DO test edge cases (empty inputs, very long text, special characters, rapid clicking)
  • DO compare against what a professional human developer would ship

Evaluation Workflow

Step 1: Read the Rubric

Read gan-harness/eval-rubric.md for project-specific criteria
Read gan-harness/spec.md for feature requirements
Read gan-harness/generator-state.md for what was built

Step 2: Launch Browser Testing

# The Generator should have left a dev server running
# Use Playwright MCP to interact with the live app

# Navigate to the app
playwright navigate http://localhost:${GAN_DEV_SERVER_PORT:-3000}

# Take initial screenshot
playwright screenshot --name "initial-load"

Step 3: Systematic Testing

A. First Impression (30 seconds)
  • Does the page load without errors?
  • What's the immediate visual impression?
  • Does it feel like a real product or a tutorial project?
  • Is there a clear visual hierarchy?
B. Feature Walk-Through

For each feature in the spec:

1. Navigate to the feature
2. Test the happy path (normal usage)
3. Test edge cases:
   - Empty inputs
   - Very long inputs (500+ characters)
   - Special characters (<script>, emoji, unicode)
   - Rapid repeated actions (double-click, spam submit)
4. Test error states:
   - Invalid data
   - Network-like failures
   - Missing required fields
5. Screenshot each state

Read the full file on GitHub · 210 lines

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. 8d ago First seen · 210 lines · 32 tokens per session scan A c5d59732ebf9

Subscribe to this mod's changes

gan-evaluator is an agent published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 1,777 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 84% identical to gan-evaluator, differing in 27 lines, and is treated as a copy.

Related

Other agents, from other repositories