What problem does it solve? Choosing how to orchestrate multiple AI agents for a phase or fan-out task is error-prone: teams default to parallel subagents even when a deterministic workflow or a coordinating agent team fits better, wasting tokens or losing coordination. This Skill evaluates four execution strategies with an explicit scoring rubric so the recommendation is consistent and cost-aware. ## Core Features & Use Cases - 7-Signal Scoring Table: Counts signals like multi-package scope, schema/API surface, 3+ viable directions, phase-program classification, and 5+ file blast radius to produce a 0-7 score mapped to a strategy threshold. - Four Strategy Comparison: Always evaluates sequential, parallel subagents, dynamic workflow, and agent team side by side, with explicit agent count math and cost guards at >30 and >100 agents. - Simple and Deep Modes: Scores from existing conversation context by default, or runs targeted codebase scans (touchpoint files, test infrastructure, phase dependencies) before scoring when signals are ambiguous. - Use Case: Before spawning agents to validate five phase plans, run this Skill to get a scored recommendation showing whether parallel subagents, a workflow, or an agent team fits, plus the expected agent count and model assignment (sonnet by default, opus only for code execution). ## Quick Start Ask the agent to run vc-agent-strategy-compare on your current phase or fan-out task, for example: compare execution strategies for validating these five phase plans.
