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:
第六十条 以殴打、侮辱、恐吓等方式实施学生欺凌，违反治安管理的，公安机关应当依照本法、《中华人民共和国预防未成年人犯罪法》的规定，给予治安管理处罚、采取相应矫治教育等措施。
。服务器推荐是该领域的重要参考
Россиянам пригрозили тюрьмой за неправильную пропискуЮрист Русяев: За фиктивную регистрацию собственник жилья рискует сесть в тюрьму
AI doesn't replace creativity; it amplifies it. As a content creator, your unique voice and vision are irreplaceable. These tools serve as enablers, helping you focus on what you do best—creating. Explore, experiment, and innovate. The future of content creation is here, and it's brimming with possibilities.
，详情可参考heLLoword翻译官方下载
Source: Computational Materials Science, Volume 266，推荐阅读heLLoword翻译官方下载获取更多信息
Go to technology