archon

Run AI workflows in isolated git worktrees with YAML DAGs.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/az9713/Archon-tutorial --skill archon-az9713
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: archon
Source: https://github.com/az9713/Archon-tutorial/tree/main/.claude/skills/archon
Command: npx skills add https://github.com/az9713/Archon-tutorial --skill archon-az9713

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Archon provides a deterministic, scalable way to run AI workflows by leveraging isolated git worktrees, enabling parallel experimentation and reducing drift across environments.

Core Features & Use Cases

  • Manage and run AI workflows as YAML DAGs, with per-repo and global config
  • Create and manage command templates and workflow definitions, enabling repeatable automation
  • Enable parallel development by isolating worktrees for independent experiments and PR derivations

Quick Start

Initialize Archon in your project, then run your first workflow with archon workflow run to see automated AI-driven tasks in action.

Frequently Asked Questions about archon

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

FAQPage Schema
How do I run AI workflows in isolated git worktrees for parallel development?

You can run AI workflows in isolated git worktrees by defining them as YAML DAGs and using a CLI to execute tasks, which enables parallel experimentation and reduces environment drift. Archon manages this isolation automatically.

What's the best way to automate AI-driven tasks with deterministic and repeatable execution?

Automating AI-driven tasks deterministically involves managing workflow YAMLs and command templates that apply per-repo configuration. This approach delegates task execution to a CLI, ensuring repeatable automation and reducing manual setup.

How do I create and manage command templates for AI workflow automation?

Creating command templates involves defining reusable execution structures within workflow YAMLs. These templates enable repeatable automation by standardizing how AI tasks are initiated and managed across isolated worktrees.

Can I use YAML DAGs to orchestrate parallel experiments across multiple repository branches?

Yes, YAML DAGs can orchestrate parallel experiments by isolating git worktrees for independent experiments and PR derivations. This configuration applies per-repo settings to maintain consistency across branches.

Why does isolating worktrees help reduce drift in AI-assisted development?

Isolating worktrees helps reduce drift by providing a deterministic, scalable environment where AI workflows run independently. This prevents parallel experiments from interfering with each other and ensures consistent repository configuration.

Do I need a specific CLI to manage workflow YAMLs and repository configuration for AI tasks?

Yes, executing these AI workflows requires delegating tasks to a dedicated CLI rather than using direct Claude Code usage. The CLI applies frontmatter-driven discovery to guide execution across isolated worktrees.