archon

Run deterministic AI workflows in isolated git worktrees.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/ChatGPT-KB/Archon-mirror --skill archon-chatgpt-kb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: archon
Source: https://github.com/ChatGPT-KB/Archon-mirror/tree/main/.claude/skills/archon
Command: npx skills add https://github.com/ChatGPT-KB/Archon-mirror --skill archon-chatgpt-kb

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Archon provides a structured, repeatable framework to manage AI coding workflows in isolated worktrees, eliminating ad-hoc decisions and non-deterministic results.

Core Features & Use Cases

  • Deterministic orchestration of AI-driven workflows across multiple repos with per-node controls
  • Creation and management of workflow YAMLs, commands, and configurations
  • Use cases include parallel research, automated code generation, reviews, and safe live experimentation

Quick Start

Start a new Archon workflow in an isolated worktree using the CLI.

Frequently Asked Questions about archon

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run deterministic AI workflows in isolated git worktrees?

Run deterministic AI workflows in isolated git worktrees by using a CLI to create and manage workflow YAMLs, command files, and configurations. This provides per-node and global settings for repeatable, parallel development across projects.

What is the best way to manage parallel AI code generation across multiple repositories?

The best way to manage parallel AI code generation across multiple repositories is by orchestrating deterministic workflows in isolated worktrees. This structured approach eliminates ad-hoc decisions and non-deterministic results.

How do I create and manage workflow YAMLs for AI-driven code reviews?

Create and manage workflow YAMLs for AI-driven code reviews using a dedicated CLI that exposes per-node and global settings. This supports artifacts and context substitution to make automation repeatable across projects.

Can I use isolated worktrees for safe live experimentation without affecting my main branch?

Yes, you can use isolated worktrees for safe live experimentation without affecting your main branch. This framework provides per-node controls and enforces best practices, allowing parallel research and safe trials across multiple repos.

Why does my AI coding workflow produce non-deterministic results across different runs?

AI coding workflows produce non-deterministic results due to ad-hoc decisions and lack of structure. Implementing a deterministic orchestration framework with workflow YAMLs and command files enforces repeatable processes and safe, scalable execution.