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:
https://feedx.net，更多细节参见Line官方版本下载
，这一点在同城约会中也有详细论述
Associated Press reporter Anthony Izaguirre in Albany, New York, contributed to this report.，更多细节参见旺商聊官方下载
16:31, 27 февраля 2026Россия
If there is something I never expected to read, it was the Pope’s opinion on artificial intelligence and its use within the Church. So when Pope Leo XIV advised priests of his diocese not to outsource homilies to artificial intelligence, the instruction read almost like a parish bulletin caught between two worlds. Except it wasn’t […]