AI 导读
你们希望能更清楚地看到 token 都花在了哪里。 /cost 现在新增了 prompt-cache 一行，/usage 按运行次数和 token 拆分你的 /loop 任务，让你看到哪些循环消耗了大量 token，/tasks 则显示每个 subagent 运行所用的模型和 effort 等级。
正文
You asked for more visibility into where your tokens go.
/cost now has a prompt-cache line, /usage breaks down your /loop tasks by runs and tokens so you can see which loops burn many tokens, and /tasks shows which model and effort level each subagent ran on.
来源：@ClaudeDevs · x.com