Large, complex projects are often difficult to manage because they are broken down into tasks that are either too vague or not detailed enough.
It analyzes a multi-step instruction and calculates a score based on how deeply and thoroughly the work has been broken down into smaller pieces.
It provides a clear metric to measure how well a complex goal has been organized into actionable steps.
It was run inside an isolated container with no network access. This is the exact command and the real output it produced — captured process output, not written by a model.
$ python3 recursive_task_decomposition_scorer.py Recursive Task Decomposition Complexity Score: 44
A screenshot of that run.
A clean run proves this does what is shown above, in a CPU-only sandbox. It is a small research demo — not a production tool, and nothing here was published anywhere.
All of it — 41 lines, one file, standard library only.
# Recursive Task Decomposition Complexity Scorer
class Task:
def __init__(self, description, subtasks=None):
self.description = description
self.subtasks = subtasks if subtasks else []
def calculate_decomposition_complexity(root_task):
def _traverse(task):
if not task.subtasks:
return 1, 1 # depth, coverage
total_coverage = len(task.subtasks)
max_depth = 0
for subtask in task.subtasks:
depth, coverage = _traverse(subtask)
total_coverage += coverage
max_depth = max(max_depth, depth)
return max_depth + 1, total_coverage
max_depth, total_coverage = _traverse(root_task)
complexity_score = max_depth * total_coverage
return complexity_score
# Example Usage
if __name__ == "__main__":
# Create a sample task hierarchy
root_task = Task("Main Objective", [
Task("Subtask A", [
Task("Subtask A.1"),
Task("Subtask A.2")
]),
Task("Subtask B", [
Task("Subtask B.1", [
Task("Subtask B.1.1")
])
]),
Task("Subtask C")
])
score = calculate_decomposition_complexity(root_task)
print(f"Recursive Task Decomposition Complexity Score: {score}")