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:
A["1,418 source chars
。业内人士推荐搜狗输入法2026作为进阶阅读
법왜곡죄 이어 재판소원법도 강행 처리… 법원행정처장 사퇴。夫子对此有专业解读
Politicians had previously agreed to phase out all petrol and diesel vehicles, as part of Jersey's Carbon Neutral Roadmap, and in line with the UK. Luce said the decision was not just public sentiment, but also informed by a preliminary economic impact assessment he had been given.。一键获取谷歌浏览器下载对此有专业解读
Stream.pull() creates a lazy pipeline. The compress and encrypt transforms don't run until you start iterating output. Each iteration pulls data through the pipeline on demand.