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:
Москвичи пожаловались на зловонную квартиру-свалку с телами животных и тараканами18:04
，详情可参考爱思助手下载最新版本
国家支持企业组织原子能科研项目开发，发挥企业在技术创新中的主体作用，支持企业自主研发的先进技术示范应用。
ConsProduct descriptions may not provide much detail, so it can be difficult to know just what you’re downloading.