gan-style-harness

gan-style-harness is a skill for Claude Code, Codex from ufy2024/AuC. It costs 33 tokens per session (2,927 once invoked), scanned A, original, MIT.

A multi-agent setup in which one agent builds an application and a separate agent evaluates it, then feeds criticism back into another build cycle. It is inspired by the generator-and-evaluator pattern used in generative adversarial networks, or GANs.

In plain words
What is it for?
It supports autonomous application building, visual frontend work, and full-stack projects where the result needs repeated evaluation and improvement.
Why use it?
Separating creation from review makes it easier to find problems that an agent may overlook when judging its own work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/gan-harness.sh "Build a music streaming dashboard".

Good fit It supports autonomous application building, visual frontend work, and full-stack projects where the result needs repeated evaluation and improvement.

Compare 6 skills from other repositories ↓
View source ↗ ufy2024/AuC
About the project

AuC is a Python framework for running a single AI agent with an asynchronous, pluggable reasoning loop, language-model adapters, permission levels, and observable events. It is used to build coding and conversational agents with tools, security checks, web interfaces, background jobs, evaluations, and isolated execution. The catalogue entries are skills for extending its agent workflow.

ufy2024/AuC · 1,090 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ufy2024/AuC
agentmods
npx agentmods add skills/ufy2024/auc/gan-style-harness

Made for: Claude Code, Codex.

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-style-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/ufy2024/auc/gan-style-harness/github.svg)](https://agentmods.dev/skills/ufy2024/auc/gan-style-harness)
Your own site
<a href="https://agentmods.dev/skills/ufy2024/auc/gan-style-harness"><img src="https://agentmods.dev/badge/skills/ufy2024/auc/gan-style-harness/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-style-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/ufy2024/auc/gan-style-harness"><img src="https://agentmods.dev/badge/skills/ufy2024/auc/gan-style-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,927 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Excessive Agency · line 200
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • high Excessive Agency · line 203
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • high Excessive Agency · line 206
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • high Excessive Agency · line 209
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • high Memory Poisoning · line 276
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
  • medium Agent Snooping · line 20
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00033 $0.02927
Opus 5 $0.00016 $0.01463
Sonnet 5 $0.00007 $0.00585
Haiku 4.5 $0.00003 $0.00293

Measured 7d ago against content hash 0b595c95719b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gan-style-harness 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 7d 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

6 near-identical copies found in the catalogue:

auc/skill_library/bundled/gan-style-harness/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GAN-Style Harness Skill

Inspired by Anthropic's Harness Design for Long-Running Application Development (March 24, 2026)

A multi-agent harness that separates generation from evaluation, creating an adversarial feedback loop that drives quality far beyond what a single agent can achieve.

Core Insight

When asked to evaluate their own work, agents are pathological optimists — they praise mediocre output and talk themselves out of legitimate issues. But engineering a separate evaluator to be ruthlessly strict is far more tractable than teaching a generator to self-critique.

This is the same dynamic as GANs (Generative Adversarial Networks): the Generator produces, the Evaluator critiques, and that feedback drives the next iteration.

When to Use

  • Building complete applications from a one-line prompt
  • Frontend design tasks requiring high visual quality
  • Full-stack projects that need working features, not just code
  • Any task where "AI slop" aesthetics are unacceptable
  • Projects where you want to invest $50-200 for production-quality output

When NOT to Use

  • Quick single-file fixes (use standard claude -p)
  • Tasks with tight budget constraints (<$10)
  • Simple refactoring (use de-sloppify pattern instead)
  • Tasks that are already well-specified with tests (use TDD workflow)

Architecture

                    ┌─────────────┐
                    │   PLANNER   │
                    │  (Opus 4.6) │
                    └──────┬──────┘
                           │ Product Spec
                           │ (features, sprints, design direction)
                           ▼
              ┌────────────────────────┐
              │                        │
              │   GENERATOR-EVALUATOR  │
              │      FEEDBACK LOOP     │
              │                        │
              │  ┌──────────┐          │
              │  │GENERATOR │--build-->│──┐
              │  │(Opus 4.6)│          │  │
              │  └────▲─────┘          │  │
              │       │                │  │ live app
              │    feedback             │  │
              │       │                │  │
              │  ┌────┴─────┐          │  │
              │  │EVALUATOR │<-test----│──┘
              │  │(Opus 4.6)│          │
              │  │+Playwright│         │
              │  └──────────┘          │
              │                        │
              │   5-15 iterations      │
              └────────────────────────┘

Read the full file on GitHub · 298 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. 7d ago First seen · 298 lines · 33 tokens per session scan A 0b595c95719b

Subscribe to this mod's changes

gan-style-harness is a skill published in the GitHub repository ufy2024/AuC (1,090 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 2,927 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.