gan-build

gan-build is a command for Claude Code from mturac/everything-openai-codex. It costs 16 tokens per session (838 once invoked), scanned A, original, MIT.

A command that repeatedly builds an implementation and checks its result against a score, for a limited number of cycles. It can use browser checks, screenshots, or code-only evaluation.

In plain words
What is it for?
Use it to turn a short build brief into a specification, generate an implementation, evaluate it, and repeat fixes until it reaches the required score.
Why use it?
It helps improve an implementation through measured feedback instead of stopping after one build attempt. The iteration limit prevents the process from running indefinitely.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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 commands/mturac/everything-openai-codex/gan-build
Clone the repo
git clone --depth 1 https://github.com/mturac/everything-openai-codex

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-build

README.md
[![agentmods](https://agentmods.dev/badge/commands/mturac/everything-openai-codex/gan-build.svg)](https://agentmods.dev/commands/mturac/everything-openai-codex/gan-build)
Your own site
<a href="https://agentmods.dev/commands/mturac/everything-openai-codex/gan-build"><img src="https://agentmods.dev/badge/commands/mturac/everything-openai-codex/gan-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 838 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00016 $0.00838
Opus 5 $0.00008 $0.00419
Sonnet 5 $0.00003 $0.00168
Haiku 4.5 $0.00002 $0.00084

Measured 2d ago against content hash 55b01646c3bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gan-build 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 2d 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

2 near-identical copies found in the catalogue:

commands/gan-build.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parse the following from $ARGUMENTS:

  1. brief — the user's one-line description of what to build
  2. --max-iterations N — (optional, default 15) maximum generator-evaluator cycles
  3. --pass-threshold N — (optional, default 7.0) weighted score to pass
  4. --skip-planner — (optional) skip planner, assume spec.md already exists
  5. --eval-mode MODE — (optional, default "playwright") one of: playwright, screenshot, code-only

GAN-Style Harness Build

This command orchestrates a three-agent build loop inspired by OpenAI's March 2026 harness design paper.

Phase 0: Setup

  1. Create gan-harness/ directory in project root
  2. Create subdirectories: gan-harness/feedback/, gan-harness/screenshots/
  3. Initialize git if not already initialized
  4. Log start time and configuration

Phase 1: Planning (Planner Agent)

Unless --skip-planner is set:

  1. Launch the gan-planner agent via Task tool with the user's brief
  2. Wait for it to produce gan-harness/spec.md and gan-harness/eval-rubric.md
  3. Display the spec summary to the user
  4. Proceed to Phase 2

Phase 2: Generator-Evaluator Loop

iteration = 1
while iteration <= max_iterations:

    # GENERATE
    Launch gan-generator agent via Task tool:
    - Read spec.md
    - If iteration > 1: read feedback/feedback-{iteration-1}.md
    - Build/improve the application
    - Ensure dev server is running
    - Commit changes

    # Wait for generator to finish

    # EVALUATE
    Launch gan-evaluator agent via Task tool:
    - Read eval-rubric.md and spec.md
    - Test the live application (mode: playwright/screenshot/code-only)
    - Score against rubric
    - Write feedback to feedback/feedback-{iteration}.md

    # Wait for evaluator to finish

    # CHECK SCORE
    Read feedback/feedback-{iteration}.md
    Extract weighted total score

    if score >= pass_threshold:
        Log "PASSED at iteration {iteration} with score {score}"
        Break

    if iteration >= 3 and score has not improved in last 2 iterations:
        Log "PLATEAU detected — stopping early"
        Break

    iteration += 1

Read the full file on GitHub · 104 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. 2d ago First seen · 104 lines · 16 tokens per session scan A 55b01646c3bd

Subscribe to this mod's changes

gan-build is a command published in the GitHub repository mturac/everything-openai-codex (89 stars, last pushed 12d ago), licensed MIT. It adds 16 tokens to every session and 838 once invoked, about $0.0001 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.