X 貼文 · 發布者 Ben Newton ベン

I wrote up the full benchmark for my Claude Code mod that lets Jev pick the agen

Name: I wrote up the full benchmark for my Claude Code mod that lets Jev pick the agen
Author: Ben Newton ベン

這篇貼文提到一個 Claude Code mod，讓 Jev 為每次 subagent 呼叫選擇 agent 與模型，作者在部落格寫了三輪基準測試。這則推文是討論串，只連到部落格文章，沒有 repository、安裝步驟或示範媒體。

Ben Newton ベン@BenENewton

1/

2026/10/5 上午3:12:47

I wrote up the full benchmark for my Claude Code mod that lets Jev pick the agent and model for every subagent call. Three rounds, and the first two lost. If you're routing subagents to cheaper models yourself, or you think my 0.8 threshold is wrong, reply here. This is the thread the post links to for discussion. https://benenewton.com/blog/jev-agent-routing-claude-code?utm_source=twitter&utm_medium=social&utm_campaign=jev-routing-post-discussion-tweet

已翻譯

關於這個 mod

Ben Newton 的推文連到一篇部落格文章，內容是讓 Jev 為每次 subagent 呼叫選擇 agent 與模型的 Claude Code mod 完整基準測試；文章提到共測試三輪，前兩輪都輸了。貼文邀請使用者回覆，討論把 subagent 路由到較便宜模型的做法，或對 0.8 閾值提出不同看法；它也作為該文章的討論串。貼文本身沒有 repository 連結、安裝指示或示範媒體。

安裝

安裝方式請查看原始來源。

原文 / README

I wrote up the full benchmark for my Claude Code mod that lets Jev pick the agent and model for every subagent call. Three rounds, and the first two lost.

If you're routing subagents to cheaper models yourself, or you think my 0.8 threshold is wrong, reply here. This is the thread the post links to for discussion.

https://benenewton.com/blog/jev-agent-routing-claude-code?utm_source=twitter&utm_medium=social&utm_campaign=jev-routing-post-discussion-tweet

I wrote up the full benchmark for my Claude Code mod that lets Jev pick the agen

1/

關於這個 mod

安裝

更多類似作品

ruflo-browser

assumption-ledger

hermitd-mod-tests