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:
27 марта 2026, 05:42 Международные отношения。业内人士推荐WhatsApp網頁版作为进阶阅读
Предсказано возможное изменение в отношении ЕС к РоссииПолитолог Журавлев допустил появление более прагматичного руководства в Европе。业内人士推荐WhatsApp API教程,WhatsApp集成指南,海外API使用作为进阶阅读
0x200 v v 0x200