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:
Раскрыты подробности похищения ребенка в Смоленске09:27
В свою очередь, ранее в феврале Дина Саева показала собственное лицо после пластики носа.，推荐阅读夫子获取更多信息
The Test PLA resolves complex privilege decisions in a single evaluation using 148 product terms, with a 3-delay-slot pipeline to overlap checks with useful work. The PTSAV/PTOVRR mechanism lets one shared subroutine serve dozens of callers with different validation rules.
。WPS下载最新地址是该领域的重要参考
Continue reading...，更多细节参见WPS下载最新地址
文 | 空间秘探，作者 | 王小熊