GitHub Repository

An open-source skill for running parallel implementations, reviewing them independently, and selecting or synthesizing the best result.

24 starsShell

/slot-machine development (CC vs. Codex; CE vs. superpowers)

Name: /slot-machine development (CC vs. Codex; CE vs. superpowers)
Availability: InStock
Author: pejmanjohn

by pejmanjohn·Mar 29, 2026·5 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainWizardryZero to One

Parallel implementations with blind review beats single-shot AI coding every time.

Strengths

•Novel architecture: implementers, reviewers, and judge are isolated agents.
•Can mix different models (Claude vs Codex) and skills (TDD vs work) per slot.
•Synthesis mode combines best elements from multiple implementations automatically.

Weaknesses

•Higher token and time cost — tradeoff only worth it for production code.
•Currently Claude Code only, limits adoption to paid subscribers.

Post Description

I built an opensource skill that runs N implementations in parallel, has each one reviewed blind by a separate agent, then a judge picks the winner or synthesizes the best parts of each.

Each slot can use a different skill (CE:work in one vs superpowers:test-driven-development) and harness (CC vs. Codex). Or put different emphasis on each slot (functional vs. robustness). Also works for non-coding tasks (writing) and you can create custom slot-machines.

The main insight is simple enough: AI agents are probabilistic. The same spec produces different code every time; different designs, different bugs, different quality.So running parallel implementations can increase quality if we can judge effectively.

There is a real tradeoff here of increased time and tokens for quality but for production code this is often worth it; particularly on long running overnight loops on subscription plans. Also a simple way to learn which skills and harnesses actually work best for your codebase.

Appreciate any feedback / PRs. This is early!