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:
As Clark and Carol's affair progresses, DTF St. Louis begins to lionize Floyd, highlighting his kindheartedness and his understanding relationship with his stepson Richard (Arlan Ruf). It's as if the show forgets that he, too, is actively trying to cheat, reducing him instead to a virtuous teddy bear in death. Clark and Carol risk being flattened as well, turned into nothing more than streaks of blithe idiocy and cold manipulation.
，详情可参考搜狗输入法2026
Recent club form has not translated to USMNT
Раскрыты подробности о договорных матчах в российском футболе18:01
// Flush: yield any remaining data