ankitkr3/compounded

5 stars · Last commit 2026-06-12

Claude Code plugin that learns from your corrections — approved lessons become rules that earn autonomy through real use: verified → trusted → autonomous. One mistake = one level down. No daemon, no cloud, 100% local.

PluginWorkflow & Automation TDD & Testing Debugging Documentation Design & UI DevOps & Infra Productivity AI & Prompting Data & ML Security

README preview

<div align="center">

<br />

<img src="assets/logo.svg" width="560" alt="compounded — skills that earn trust, and compound" />

### Your AI agent gets better at *you* the longer you use it.

Correct Claude once — it asks to remember the lesson, then never makes that mistake again. **Your approval is the only gate**: saved rules are active immediately at `.verified`, build a track record to reach `.trusted`, and graduate to `.autonomous`. One correction sends them back down. **No daemon. No cloud. No re-explaining.**

<br />

[![Tests](https://github.com/ankitkr3/compounded/actions/workflows/tests.yml/badge.svg)](https://github.com/ankitkr3/compounded/actions/workflows/tests.yml)
[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
[![Claude Code Plugin](https://img.shields.io/badge/claude%20code-plugin-D97757?logo=anthropic&logoColor=white)](https://docs.claude.com/en/docs/claude-code/plugins)
[![Stars](https://img.shields.io/github/stars/ankitkr3/compounded?style=flat&color=yellow)](https://github.com/ankitkr3/compounded/stargazers)
[![Python](https://img.shields.io/badge/python-3.9%2B-3776AB?logo=python&logoColor=white)](https://www.python.org/)

<br />

View full repository on GitHub →