gan-evaluator

gan-evaluator is an agent for coding agents from sifxprime/kodelyth-ecc. It costs 32 tokens per session (1,777 once invoked), scanned A, a copy of gan-evaluator, MIT.

A quality-review agent that tests a running application through Playwright, a browser automation tool, and scores it against a project rubric.

In plain words
What is it for?
Use it to evaluate a live web application and give strict, actionable feedback on behavior, design, and defects.
Why use it?
It checks the actual interactive product, including edge cases and visual quality, rather than judging only source code or screenshots.

Agent

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.

agentmods
npx agentmods add agents/sifxprime/kodelyth-ecc/gan-evaluator
Clone the repo
git clone --depth 1 https://github.com/sifxprime/kodelyth-ecc

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/sifxprime/kodelyth-ecc/gan-evaluator.svg)](https://agentmods.dev/agents/sifxprime/kodelyth-ecc/gan-evaluator)
Your own site
<a href="https://agentmods.dev/agents/sifxprime/kodelyth-ecc/gan-evaluator"><img src="https://agentmods.dev/badge/agents/sifxprime/kodelyth-ecc/gan-evaluator.svg" alt="Measured on agentmods" 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. Scan, not verified.
Origin 88% 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 $0.00032 $0.01777
Opus 5 $0.00016 $0.00889
Sonnet 5 $0.00006 $0.00355
Haiku 4.5 $0.00003 $0.00178

Measured 4d ago against content hash c5d59732ebf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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

88% identical to gan-evaluator — 13 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.

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. 4d 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 sifxprime/kodelyth-ecc (11 stars, last pushed 2d 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 88% identical to gan-evaluator, differing in 13 lines, and is treated as a copy.

Related

Other agents, from other repositories

test-automation-engineer

Hands-on test automation engineer. Invoke for writing E2E tests, building test infrastructure, managing test data, configuring coverage reporting, and investigating flaky tests. MCP-first Playwright automation. This agent writes test code — not production code.

irahardianto/awesome-agv · 53 tokens

gan-evaluator

GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.

Jamkris/everything-gemini-code · 32 tokens

lens

Role: Demo Recorder + Integration Witness.

sam-agents/sam · 1 tokens

e2e-runner

End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

masrisystems/dot-agents · 69 tokens

e2e-runner

End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

Jamkris/everything-gemini-code · 69 tokens

gan-evaluator

GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.

raja21068/AutoResearch · 32 tokens