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:
On Saturday January 24, Duncan Ferguson walked into the Winslow Hotel pub on Goodison Road and handed licensee Dave Bond £1,000 to put behind the bar. Ferguson, the former Everton centre-forward, was there because the Winslow, 140 years old and standing in the shadow of Goodison Park’s towering Main Stand, was closing. Eight months after Everton’s men left Goodison, this was another farewell party and Ferguson had turned up to say goodbye. “It was a brilliant gesture,” said Bond.。关于这个话题，safew官方下载提供了深入分析
快速原型，无需微调 → Hammer 或 FunctionGemma 基础模型。。搜狗输入法下载对此有专业解读
Display: Making snake look nice in the terminal，推荐阅读搜狗输入法2026获取更多信息
区域红利观察：一线城市与新兴增长极的差异化机遇