Dust

A workflow tool for keeping AI coding agents on track.

Why Use This?

AI coding agents work best with clear tasks and fast feedback. Dust gives them both:

• Tasks — a queue of work, each with clear requirements and definition of done
• Checks — quality gates (tests, lint, build) that run before and after changes

Agents pick tasks, implement them, verify checks pass, and move on. You add tasks, review commits, and steer direction.

Quick Start

npm install @joshski/dust
npx dust init

This creates a .dust directory and adds an instruction to your AGENTS.md file.

Running Agents

Start an agent on a single task:

claude "implement the next task"

Or let dust run agents continuously in a sandbox with the loop command:

npx dust loop claude

This runs Claude Code in a ralph loop, picking up tasks until the iteration limit is reached (default: 10). You can specify a custom limit:

npx dust loop claude 5

Learn More

Details live in the .dust/facts directory:

• Directory Structure — how .dust/ is organized
• Configuration — settings and quality checks
• CLI Commands — full command reference