Parallel Task Spark

This is a multi-agent orchestrator that reads markdown plan files, extracts task dependencies, and spins up parallel Sparky subagents to execute them in dependency-aware waves. It enforces TDD by default, requiring RED phase test failures before implementation, then GREEN validation evidence before marking tasks complete. Each subagent works in isolation, commits locally without pushing, and logs results back to the plan file. You'd use this when you have a detailed implementation plan with clear task boundaries and want multiple agents working simultaneously without stepping on each other. The coordination overhead is real, but for plans with 10+ loosely coupled tasks, the parallelism pays off. Just don't expect it to magically fix vague requirements or tangled dependencies.