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:
Ранее президент Украины Владимир Зеленский в интервью Sky News заявил, что с удовольствием принял бы ядерное оружие от Франции или Британии, но «таких предложений не поступало».
，详情可参考服务器推荐
Что думаешь? Оцени!，更多细节参见safew官方版本下载
2026-02-27 00:00:00:03014252910http://paper.people.com.cn/rmrb/pc/content/202602/27/content_30142529.htmlhttp://paper.people.com.cn/rmrb/pad/content/202602/27/content_30142529.html11921 我国苹果产量和消费量世界第一。同城约会对此有专业解读
235,625 comparisons"]:::accent