changeStart

What problem does it solve?

It turns an incoming change request into an actionable, dependency-aware development plan that can run in parallel without duplicating work or stepping outside the approved scope.

Core Features & Use Cases

• DAG-based task orchestration: Builds a dependency graph from the change request and PRD, then layers tasks to determine execution order.
• Dependency-island segmentation: Clusters tasks into segments so tasks touching the same files are grouped together, while verification/testing and shared infra stay separated.
• Manager/Collector coordination: Spawns bounded Manager AIs per segment and optionally spawns a Collector AI to update the consolidated report as segments complete.
• Stateful execution controls: Updates doc/company_state.json task counters and checks collectorMode and monitoringEnabled to decide monitoring and reporting behavior.

Use case: You receive a CHANGE_REQUEST describing multiple fixes and improvements, and you want the system to partition the work into parallel segments, respect file ownership boundaries, and keep report/report.md continuously updated.

Quick Start

Run /changeStart to generate a DAG, split the change into dependency islands, delegate each segment to a Manager AI, and update report/report.md as the segments complete.