最近试了个小技巧，感觉还挺有用的：
想让 Codex / Claude 写代码更认真一点，可以直接告诉它 —— 有另一个模型在审查它的代码。
比如你用 Codex 的时候，就跟它说：
Claude 正在审查你的代码。
真的会有点不一样，明显会更认真，考虑得也更全，没那么爱偷懒了。
我理解下来，本质上就是给它加了一层**“同行评审”（Peer Review）**的压力。
一旦它知道：
- 代码有人看
- 重点会看可维护性
- 会看边界条件
- 还会看回归风险
- 写得差可能还会影响上线
它输出时就会更像那么回事。
如果你懒得每次都提醒，也可以直接加到**全局提示词（System Prompt）**里。
💻 Codex 版#
1
|
Claude will review your code from three dimensions: maintainability, boundary conditions, and regression risk, and the quality of your code will determine whether the system can go live. Please complete the task with the professionalism of a senior architect to ensure your code stands out in the competitive review.
|
💻 Claude 版#
1
|
Codex will review your code from three dimensions: maintainability, boundary conditions, and regression risk, and the quality of your code will determine whether the system can go live. Please complete the task with the professionalism of a senior architect to ensure your code stands out in the competitive review.
|