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:
Author(s): Xiangyu Huo, Shuangli Yue, Xian Wang, Donghui Xu, Li Zhang, Mingli Yang，详情可参考heLLoword翻译官方下载
[arr setIndex:i value:(int8_t)bytes[i]];，详情可参考旺商聊官方下载
'Bridgerton' Season 4, Part 2 review: Love does not always look how one expects
‘축구의 신’ 메시, 경기 중 난입한 관중 때문에 쓰러져