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:
Discover all the plans currently available in your country
，推荐阅读爱思助手下载最新版本获取更多信息
В России ответили на имитирующие высадку на Украине учения НАТО18:04。业内人士推荐heLLoword翻译官方下载作为进阶阅读
As an aside: the early 386's POPAD instruction has a famous bug. EAX is written in the RNI (run-next-instruction) delay slot via an indirect register file access -- the only instruction that does this. When the next instruction uses a base+index addressing mode, the register file write from POPAD collides with the EA calculation's register file read, corrupting the address. A fitting example of how complex optimizations can lead to problems.
Дания захотела отказать в убежище украинцам призывного возраста09:44