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:
“By approving this deal, the FCC ensures big wins for Americans," FCC Chairman Brendan Carr said in a statement. "This deal means that jobs are coming back to America that had been shipped overseas. It means that modern, high-speed networks will get built out in more communities across rural America. And it means that customers will get access to lower priced plans. On top of this, the deal enshrines protections against DEI discrimination."
。旺商聊官方下载对此有专业解读
Жители Санкт-Петербурга устроили «крысогон»17:52，推荐阅读搜狗输入法2026获取更多信息
- Include sensible aggregate metrics, e.g. number of comments on the video.。下载安装 谷歌浏览器 开启极速安全的 上网之旅。对此有专业解读