centsandcode/rubber-duck

README preview

# rubber-duck

> *Don't give me the answer. Help me find it.*

[![version](https://img.shields.io/badge/version-0.1.5-1f6fb2)](https://github.com/centsandcode/rubber-duck/releases)
[![Claude Code](https://img.shields.io/badge/Claude%20Code-plugin-1f6fb2)](https://code.claude.com)
[![license](https://img.shields.io/badge/license-MIT-1f6fb2)](LICENSE)

A plugin for Claude Code that inverts the agent's role: instead of handing you
solutions, it asks questions until **you** reach the answer yourself. Inspired
by the classic rubber duck debugging technique.

## Why

By default, coding agents solve. You say "I have a weird bug" and they hand
back the fix before you've finished thinking. Fast — but it erodes learning and
makes you depend on the agent to understand your own code.

Rubber Duck turns the agent into a Socratic interlocutor. It listens, asks,
guides. It does not solve until you explicitly ask. You learn, you understand,

View full repository on GitHub →