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:
你让一个好不容易请出年假的人，在海上漂五天，花着钱买WiFi办公，最后发朋友圈只能配文“海上风景不错”？人家还不如躺在家里刷抖音。
，详情可参考搜狗输入法下载
Мир Российская Премьер-лига|19-й тур
63-летняя Деми Мур вышла в свет с неожиданной стрижкой17:54，更多细节参见同城约会
Digitale Gesellschaft digitale-gesellschaft.ch🇨🇭，更多细节参见旺商聊官方下载
if (minIdx != i) {