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:
ChatGPT served as a journal for the Chinese operative to keep track of the covert network, while much of the network’s content was generated by other tools and spread through social media accounts and websites. OpenAI banned the user after discovering the activity.
，推荐阅读safew官方版本下载获取更多信息
Enterprise: Custom Price
// 核心过滤：弹出栈中「≤当前元素」的数（易错点2：必须是≤，不是<）