ChristopherKahler

Paul — AI skill for Claude Code

AI community

Plan-Apply-Unify Loop — Structured AI-assisted development for Claude Code.

How to install Paul

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ChristopherKahler/paul and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Paul does

Plan-Apply-Unify Loop — Structured AI-assisted development for Claude Code. Quality over speed-for-speed's-sake.

Alternatives in AI

Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
Develop — Development phase - Build solutions with multi-AI implementation and quality gates 2.8k ★
Ralphex — Extended Ralph loop for autonomous AI-driven plan execution 1.1k ★

README

PAUL

**Plan-Apply-Unify Loop** — Structured AI-assisted development for Claude Code.

[![npm version](https://img.shields.io/npm/v/paul-framework?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/paul-framework) [![License](https://img.shields.io/badge/license-MIT-blue?style=for-the-badge)](LICENSE) [![GitHub stars](https://img.shields.io/github/stars/ChristopherKahler/paul?style=for-the-badge&logo=github&color=181717)](https://github.com/ChristopherKahler/paul)

npx paul-framework

**Works on Mac, Windows, and Linux.**

![PAUL Install](assets/terminal.png)

*"Quality over speed-for-speed's-sake. In-session context over subagent sprawl."*

[Why PAUL](#why-paul) · [Getting Started](#getting-started) · [The Loop](#the-loop) · [Commands](#commands) · [How It Works](#how-it-works)

Why PAUL

I build with Claude Code every day. It's incredibly powerful — when you give it the right context.

The problem? **Context rot.** As your session fills up, quality degrades. Subagents spawn with fresh context but return ~70% quality work that needs cleanup. Plans get created but never closed. State drifts. You end up debugging AI output instead of shipping features.

PAUL fixes this with three principles:

**Loop integrity** — Every plan closes with UNIFY. No orphan plans. UNIFY reconciles what was planned vs what happened, updates state, logs decisions. This is the heartbeat.
**In-session context** — Subagents are expensive and produce lower quality for implementation work. PAUL keeps development in-session with properly managed context. Subagents are reserved for discovery and research — their job IS to gather context.
**Acceptance-driven development** — Acceptance criteria are first-class citizens, not afterthoughts. Define done before starting. Every task references its AC. BDD format: `Given [precondition] / When [action] / Then [outcome]`.

The comple