给编程智能体加一份 ask first 清单，而不只是 never 清单
Оригинальный заголовок: Give your coding agent an "ask first" list, not just a "never" list
Заголовок и краткое изложение на выбранном языке ожидают перевода.
作者提出智能体配置不应只有允许和禁止两档，而应增加 ask first 中间档，用于推送远端、非本地数据库的 schema 迁移、安装新依赖、修改 CI 或部署配置这类需要先停下说明命令的操作。
Полный текст на выбранном языке ожидает перевода. Пока показан оригинал.
Most agent configs have two modes: things the agent may do, and things it must never do. Real work needs a third bucket: ask first.
A flat deny-list is too blunt. Ban git push outright and the agent can't finish a branch you actually wanted pushed. Allow it silently and one bad loop rewrites shared history. The middle bucket fixes that.
A three-bucket layout for AGENTS.md
## Never
- Invent secrets, API keys, or env var values
- Force-push or rewrite shared history
- Delete data outside the working tree
## Ask first (stop and describe the command)
- Any push to a remote
- Schema migrations against a non-local database
- Installing a new dependency
- Changing CI or deploy config
## Fine without asking
- Edit files in the working tree
- Run the test suite and linters
- Read logs and local docs
Keep each bucket under ten lines. When a line needs a paragraph of explanation, move it into a scoped Cursor rule (.cursor/rules/*.mdc) that only loads for the matching paths.
Why it works
- The agent fails closed on irreversible actions without stalling on everyday ones.
- Reviews get shorter: anything surprising should have triggered an "ask first" stop, so you know where to look.
- New teammates read the same three lists and learn the house rules in a minute.
Vildanden's free Agent Config sample ships with this split for a Next.js-leaning repo:
Источник: DEV Community · Cursor · dev.to