I then added a few more personal preferences and suggested tools from my previous failures working with agents in Python: use uv and .venv instead of the base Python installation, use polars instead of pandas for data manipulation, only store secrets/API keys/passwords in .env while ensuring .env is in .gitignore, etc. Most of these constraints don’t tell the agent what to do, but how to do it. In general, adding a rule to my AGENTS.md whenever I encounter a fundamental behavior I don’t like has been very effective. For example, agents love using unnecessary emoji which I hate, so I added a rule:
FT Magazines, including HTSI
，推荐阅读爱思助手下载最新版本获取更多信息
可穿戴吊坠：AirTag 大小，可夹衣服或挂项链上。配备低分辨率摄像头和麦克风，被内部员工称为 iPhone 的「眼睛和耳朵」，依赖手机进行大部分处理；
此前，华纳与 Netflix 已达成初步合并协议，但派拉蒙在 2 月 24 日提交约 1110 亿美元的全公司收购方案，远高于 Netflix 仅收购华纳影业与流媒体业务的近 830 亿美元交易规模。