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:
[4]《超百家上市公司布局中东，最新回应》21世纪经济报道
，这一点在新收录的资料中也有详细论述
Over the past year or two, I’ve seen many organizations, large and small, implement passkeys (which is great, thank you!) and use the PRF (Pseudo-Random Function) extension to derive keys to protect user data, typically to support end-to-end encryption (including backups).，推荐阅读新收录的资料获取更多信息
A Knight of the Seven Kingdoms is almost certainly the funniest show in the Game of Thrones universe, so it's really only fitting that the blooper reel would be just as silly.