帖子
- 桑丘2026-08-3153278
- shiner2026-08-319779
加skill,我今天也看到了一个skill不过暂时没时间测试效果
github.com

GitHub - DietrichGebert/ponytail: Makes your AI agent think like the laziest senior...
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
- VRxiaojie2026-08-3153279
我是用luna xhigh作为主agent分配任务,让它开sol medium做子agent真正干活。目前消耗量还可以,做的东西也能用
- FFFFFFFFFir2026-08-3118888
换pi,粗略估计token消耗少一半,然后善用额度几无限制的web chat,比如我现在就是web chat聊规划和代码审计,本地agent就纯执行
- zoffy2026-08-3112189
- Joshua2026-08-3122003
听说pi很省,用codex可以试一下fast-context-mcp
- 🐟2026-08-315821
试试
Sol Medium 规划 → Luna Max 主编排 → Luna Max 执行 - OpenAI-linuxdo2026-08-3127753
全局提示词里要求GPT禁止写任何测试
- 4437294252026-08-3124399
github.com

GitHub - XiaoDuoYa/codex-with-chatgpt: ChatGPT thinks. Codex works. Use ChatGPT as the...
ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
可以参考这个,用 web 端规划,调用本地 codex 执行
