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:
Along with improvements in branch bank equipment came a new line of "high-speed"
，推荐阅读safew官方版本下载获取更多信息
Almost all coal-fired power plants in the US had the ability to comply with rules limiting their emission of dangerous pollutants such as mercury that can cause brain damage in children. Despite this, Donald Trump’s administration decided to demolish the standards anyway.，更多细节参见51吃瓜
ВсеСледствие и судКриминалПолиция и спецслужбыПреступная Россия。服务器推荐对此有专业解读
▲ 假想图由 Gemini 生成