Skip to content

Guides

How-to guides for building and running AI coding workflows with Archon.

  • Loop Nodes — Iterative AI execution with completion conditions and deterministic exit checks
  • Approval Nodes — Human review gates with optional AI rework on rejection
  • Script Nodes — TypeScript/JavaScript (bun) or Python (uv) as a deterministic DAG node, without AI
  • Workflow Triggers — Start workflows from schedules and verified GitHub events
  • Proactive Workflows — Let a cheap agent decide whether an event matters, then keep a person on the loop before the run acts

Support varies by provider. See the provider capability matrix for each feature.

  • Per-Node Hooks — Attach Claude SDK hooks for tool control, context injection, and input modification
  • Per-Node MCP Servers — Connect external tools (GitHub, Postgres, etc.) to individual nodes
  • Per-Node Skills — Preload specialized knowledge into node agents

Archon ships the sdlc workflow pack, a software factory from an incoming issue to a merged pull request. Set up the SDLC factory runs it on your repository, and SDLC pack workflows describes each workflow.

To customize the pack, copy the whole .archon/workflows/sdlc/ folder from the Archon repository into your project’s .archon/workflows/ and modify it — same-named workflows override the bundled ones. Copy the pack rather than one workflow folder: its workflows include each other and share scripts in sdlc/.shared/.