Running Craig as a service, AI Agents

Craig Agency Implementation, Scaling AI Coding Agent Delivery

Learn how to structure productized coding services around Craig's parallel agent task isolation and terminal workspace, enabling agencies to deliver multi-agent projects without manual branch coordination. This course covers workspace setup, agent task orchestration, client delivery workflows, and pricing models for AI-assisted development retainers.

Open the decision record for Craig

What does running Craig for clients commit you to?

Published figures for this service. Blank fields are not published.

Monthly tool cost
Open-source; no published pricing tiers. Vendor cost basis is $0 for the tool itself, budget for agent CLI subscription costs and developer onboarding time, both Not published.
Time to first value
Not published
Payback
Not modeled, client price, labor cost, agent usage cost, overhead, and expected volume are not supplied
Guided implementation
8 hours

Is Craig worth running as a client service?

The evidence supports Craig as a low-friction, local orchestration layer for agencies whose engineers already run AI coding agent CLIs across multiple repos; worktree isolation and terminal review context are real, documented features. What remains unknown is any cost or ROI basis, the tool is open-source with no published pricing, so service economics must be measured on your own delivery data.

An agency-fit judgement for reselling this service. It is separate from the tool description on the decision record.

Before you start

What has to be in place before the first client engagement.

Tools and subscriptions

  • An installed and authenticated AI coding agent CLI (Claude Code, Codex, Cursor, or Pi)
  • Git repositories registered in a Craig workspace
  • GitHub CLI for PR and check status
  • A local terminal environment (Craig is a local TUI with no hosted control plane)
  • Agent-facing Craig CLI access for scripting workspace operations

People and inputs

  • Developers comfortable with terminal workflows and git worktrees
  • A process for isolating concurrent agent tasks per branch
  • A polyrepo inventory if driving agents across frontend, API, and other repos
  • Review capacity for reading diffs, PR state, and CI comments

Included with the course

7 working documents for delivering this service.

  • Craig Workspace Setup Checklist for Agencieschecklist
  • Multi-Agent Task Orchestration SOPsop
  • Client Delivery Workflow Templatetemplate
  • Agent Task Isolation and Branch Strategy Guideguide
  • PR Review and CI Monitoring Worksheetworksheet
  • Retainer Pricing Model for Parallel Agent Deliverytemplate
  • CLI-Driven Workspace Automation Playbookguide

Listed by name. These documents are not yet published as individual downloads.