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:
Most architectures have specialised instructions for stack allocation,
，更多细节参见旺商聊官方下载
Мерц резко сменил риторику во время встречи в Китае09:25，更多细节参见同城约会
2026-02-27 00:00:00:03014247010http://paper.people.com.cn/rmrb/pc/content/202602/27/content_30142470.htmlhttp://paper.people.com.cn/rmrb/pad/content/202602/27/content_30142470.html11921 中华人民共和国增值税法实施条例，详情可参考爱思助手下载最新版本