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:
他續稱：「以軍持續在黎巴嫩境內對真主黨目標採取強力行動。這個恐怖組織正在——並將繼續——為其向以色列開火付出沉重代價。」
Крупнейшая нефтяная компания мира задумалась об альтернативе для морских перевозок нефти14:56，这一点在体育直播中也有详细论述
The world of AI is in a constant state of flux. It can feel disorientating, but there are steps you can take to feel more grounded in these shifting sands.
。关于这个话题，同城约会提供了深入分析
The first challenge was getting any video out of it at all. This turned out to be the hardest part of the entire project.，详情可参考体育直播
compiled into the Wasm binary so that it can act as a REPL server.