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:
Maggie 姐在新花都夜总会（图：南方人物周刊记者 方迎忠）
。51吃瓜是该领域的重要参考
Advances in organ and computer models are raising the prospect that some animal experiments could be eliminated. But there are still huge hurdles to overcome.
How to allocate stack
“《重庆·1949》上演4年多来，圈粉一大批外国游客。2025年接待外籍观众近8万人次，同比增长约6倍。”重庆一九四九演艺文化有限公司总经理黄科告诉记者。