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:
2026-02-26 00:00:00:0 听取有关草案和议案审议情况汇报
。业内人士推荐一键获取谷歌浏览器下载作为进阶阅读
第三十二条 增值税优惠政策的适用范围、标准、条件等应当依法及时向社会公开。
In response to a petition asking the International Olympic Committee (IOC) to prevent fossil fuel companies from sponsoring winter sports, the IOC president, Kirsty Coventry, said the governing body is “having conversations in order to be better” in its approach to climate change. A New Weather Institute report estimated that the fossil fuel giant Eni, carmaker Stellantis and ITA Airways sponsoring Milano Cortina 2026 will induce an additional 40% to the Games’ carbon footprint, enough to melt 3.2 square km of snow cover and 20 million tonnes of glacier ice.