Project templates with multi-agent team configurations for AI code copilots. Includes ready-to-use setups for ML/AI (RAG, LangChain, n8n), enterprise Java, and web apps — each with defined agent roles, delegation patterns, and session management best practices.
Scaffold and explain an autonomous build run for an approved SDD feature. Validates the approval + origin gates, writes specs/ /automation.json from the template, and prints the driver command — the driver itself runs OUTSIDE this session.
List the custom subagents installed on this machine and in this project — the replacement for the built-in /agents command removed from recent Claude Code versions.
Run the origin-confirmation circuit breaker for a feature. Validates that the working spec/plan is a faithful realisation of the user's original idea, and surfaces an interactive escalation if it has drifted.
Submit work for peer review. Validates clean worktree, initializes or continues the review loop, invokes review-round-runner.sh, and returns the verdict.