作者分享其 Claude Code 模組的完整基準測試,該模組讓 Jev 為每次 subagent 呼叫挑選 agent 與 model,三輪測試中前兩輪失敗,貼文附上部落格連結供討論。
claude / I wrote up the full bench
❯ /I▰▰▰▰▰▰▰▰ 多智能体与编排
✳︎ I wrote up the full benchmark for my Claude Code mod that lets Jev pick the agen
└─ 让每一次对话更顺手
文字预览 · 非作品截图✳︎ I wrote up the full benchmark for my Claude Code mod that lets Jev pick the agen
└─ 让每一次对话更顺手
I wrote up the full benchmark for my Claude Code mod that lets Jev pick the agen
星数 0权限足迹 未扫描♥ 0
