Superlite:可并行调度任务的 Claude Code 插件
开发者发布名为 Superlite 的 Claude Code 插件,称其能规划构建、把任务拆成可并行执行的单元,按任务难度分配给 Opus、Sonnet 和 Haiku 等不同 Claude 模型,随后检查各任务之间的接口并做最终评审。作者自述的基准中,小型 sitegen 任务耗时 8.8 分钟,对照的 superpowers 工作流为 34.4 分钟,两者都通过 89/89 隐藏测试;在含 177 项测试的项目上,Superlite 三次运行平均 25.1 分钟,对照为 33.6 分钟,均通过全部测试。作者称该插件用钩子强制执行规则,例如禁止协调智能体修改代码、把测试放到后台运行,但这些性能数据均为作者自行测试,未经独立验证。
作者认为,智能体工作流之所以慢,往往是因为任务串行排队和频繁的人工审批,而不是模型推理本身;Superlite 试图用代码强制执行并行与边界规则。
I had a dream. I would hand an agent a spec, close the laptop, make a sandwich, and come back to finished, tested, committed work.
Here's what actually happened. I handed over the spec. I made the sandwich. I came back. The agent had written one paragraph and was asking, very politely, whether I approved section 1 of the design.
I approved it. I sat down. I waited.
Section 2. Approve? Yes. Section 3. Approve? Yes. The spec? Yes. The plan? Yes, obviously, it's the plan I just watched you write. And how would I like the plan executed? However is fastest, please, I beg you.
Then it started building. One task. Then a review of that task. Then a fix for the review. Then a re-review of the fix. Then the next task. I watched a progress log scroll past like a train at a level crossing: no stopping it, no getting past it, and no idea how many carriages were left.
I'd refresh the terminal. Still on task 3. I'd answer an email. Still on task 3. I'd start a second sandwich purely to have something to do with my hands. Task 4, under review.
#Superlite#Claude Code#Anthropic#superpowers#GitHub#Claude Opus#Claude Sonnet#Claude Haiku