一句话：提出可复用的多智能体优化 skill，将源码改动限制在注解与 intrinsics 上，实现有界、可审计的仓库级代码优化。
仓库级代码优化需要广泛诊断，但不受约束的智能体编辑会妨碍审查与归因。MACO-AI 是可复用的多智能体优化 skill，将源码改动限制在注解与内建函数（intrinsics）两类有界形式上。委派前，初始化冻结源码状态与测量契约、profile 不可变基线、审计方法资格并记录计划；五个证据专精角色不编辑代码地勘查八个语义优化空间，规划、构建与审查角色交换持久化产物，验证保持集中。初步单轮评估使用 DeepSeek V4 Pro Preview，五个 benchmark 全部优于基线，95% 置信区间排除 1.0×，加速比为 1.0048×–2.5290×，说明有界可审计的智能体优化可行，但仍需受控比较以隔离各设计选择的贡献。
Repository-scale code optimization demands broad diagnosis, but unconstrained agent edits impede review and attribution. We present MACO-AI, a reusable multi-agent optimization skill that restricts source changes to annotations and intrinsics. Before delegation, initialization freezes the source state and measurement contract, profiles an immutable baseline, audits method eligibility, and records the plan. Five evidence specialties inspect eight semantic optimization spaces without editing; separate planning, construction, and review roles exchange persisted artifacts, while validation remains centralized. In a preliminary single-iteration evaluation with DeepSeek V4 Pro Preview, all five benchmarks improved over their baselines with 95% confidence intervals excluding 1.0×; speedups ranged from 1.0048× to 2.5290×. These results establish the feasibility of bounded, auditable agentic optimization, while controlled comparisons remain necessary to isolate the contributions of individual design choices.