ClaudeMods
☰
ZH-CN
● — 人在线 · 浏览 — 次
赞助提交作品
Threads 帖子 · 发布者 bennewton999

我如何测试路由 mod:每个任务运行两次,默认和路由。一个盲

我如何测试路由 mod:每个任务运行两次,默认和路由。一个盲

bennewton999@bennewton999

How I tested the routing mod: every task ran twice, default and routed. A blind Opus judge with the repo open got both answers as X and Y in random order and checked every path, line number and config value. Full results, all three rounds: https://benenewton.com/blog/jev-agent-routing-claude-code?utm_source=threads&utm_medium=social&utm_campaign=every-claude-code-subagent-inherits-the-main-session-s-model-14

图片1
已翻译

关于这个 mod

我如何测试路由 mod:每个任务运行两次,默认和路由。一个盲 Opus 评审员在打开仓库的情况下,以随机顺序将两个答案作为 X 和 Y,并检查每个路径、行号和配置值。

完整结果,全部三轮: https://benenewton.com/blog/jev-agent-routing-claude-code?utm_source=threads&utm_medium=social&utm_campaign=every-claude-code-subagent-inherits-the-main-session-s-model-14

安装

安装方法请查看原始来源。

原文 / README

How I tested the routing mod: every task ran twice, default and routed. A blind Opus judge with the repo open got both answers as X and Y in random order and checked every path, line number and config value.

Full results, all three rounds: https://benenewton.com/blog/jev-agent-routing-claude-code?utm_source=threads&utm_medium=social&utm_campaign=every-claude-code-subagent-inherits-the-main-session-s-model-14

更多类似作品