complexity-parallel

Parallel execution configuration is determined by inputting a task complexity score, which the script uses to automatically adjust execution modes for agents like Explorers and Architects. It reads memory signals to inform the optimal parallelization strategy for the team.

Yes, memory signals are utilized from the global-memory.md file to inform parallelization strategies. The script incorporates these signals alongside the complexity score to determine the optimal execution configuration for agents with predefined roles.

Yes, Python is required as a dependency to execute the complexity-parallel script. The Python environment processes the complexity score and memory signals to output the optimal parallel execution configuration for the project team.

The best way to optimize parallel agent execution is to run a complexity score assessment first. The resulting score is then passed into the script to automatically adjust execution modes for predefined agent roles like Analysts and coders.

You should adjust parallel execution modes after assessing a task's complexity score. The script uses this score to determine when and how to modify the execution configuration for each predefined agent role within the multi-agent system.