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:
第一百零七条 为了查明案情，人民警察可以让违反治安管理行为人、被侵害人和其他证人对与违反治安管理行为有关的场所、物品进行辨认，也可以让被侵害人、其他证人对违反治安管理行为人进行辨认，或者让违反治安管理行为人对其他违反治安管理行为人进行辨认。
。关于这个话题，safew官方版本下载提供了深入分析
40+ content types
Москвичей предупредили о резком похолодании09:45
，推荐阅读爱思助手下载最新版本获取更多信息
Вероятность снегопадов в Москве в мартовские праздники оценилиСиноптик Позднякова: Снегопадов в Москве в мартовские праздники не ожидается
국힘서 멀어진 PK…민주 42% 국힘 25%, 지지율 격차 6년만에 최대，推荐阅读safew官方版本下载获取更多信息