What problem does it solve? Multi-agent workflows often accumulate agents, seats, and handoffs that cost more in coordination overhead than they deliver in value. This Skill audits an existing multi-agent setup, counts what each boundary between agents costs, compares it against what the boundary buys, and recommends whether to keep, remove, or restructure agents — including the valid outcome of collapsing to a single agent. ## Core Features & Use Cases - Boundary Cost Analysis: Enumerates every context crossing between agents and names concrete cost terms such as token burden, handoff loss, compression loss, semantic drift, verification burden, and governance overhead. - Gain Verification: Checks each boundary against gains a single agent could not produce, such as genuine specialisation, parallelism, cross-vendor diversity, or adversarial review. - Single-Expert Baseline Comparison: Benchmarks the topology against one capable agent doing the whole task, placing the burden of proof on each boundary. - Use Case: Before adding a fourth review agent to a slow pipeline, run this audit to produce a boundary table showing which crossings are earned and a verdict on whether to collapse, restructure, or keep the setup. ## Quick Start Audit my current multi-agent workflow and tell me whether each agent boundary earns its coordination cost or should be removed.
