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:
create code from natural language descriptions of software tasks. The system is
。业内人士推荐搜狗输入法2026作为进阶阅读
建设单位：西安保亿名筑置业有限公司（企业法人：乔爱军，项目负责人：姚波）；施工单位：南通建工集团股份有限公司（企业法人：张向阳，项目经理：胥蜀）；监理单位：正博工程管理有限公司（企业法人：郑波，总监理工程师：翁召）
The website you are visiting is protected.
const { writer, readable } = Stream.push();