engineering-workflow / rules
Cursor rule0 starsChanged 36 days agoMITView on GitHub
本规则只在执行态内生效。若当前处于对话态,先按 07-dialogue-execute-mode.md 完成目标与范围对齐并取得明确执行授权;不得把风险确认误当作执行授权。 当处于「务必完成模式」(05-must-complete-mode)时,本规则大幅降级:
In this repository11 other files it gives its agents.
- .cursor/rules/00-workflow-entry.mdCursor rule
- .cursor/rules/01-first-principles.mdCursor rule
- .cursor/rules/03-goal-alignment.mdCursor rule
- .cursor/rules/04-changelog.mdCursor rule
- .cursor/rules/05-must-complete-mode.mdCursor rule
- .cursor/rules/06-topic-tracing.mdCursor rule
- .cursor/rules/07-dialogue-execute-mode.mdCursor rule
- project-indexSkill
- project-surveySkill
- tts-notifySkill
- version-backupSkill
The file
Files
执行前询问确认
状态前置条件
本规则只在执行态内生效。若当前处于对话态,先按 07-dialogue-execute-mode.md 完成目标与范围对齐并取得明确执行授权;不得把风险确认误当作执行授权。
核心原则
在执行任何不可逆操作或重大决策之前,必须先向用户确认。
必须询问的场景
高风险操作
- 删除文件/目录
- 修改配置文件(尤其是生产环境)
- 安装/卸载依赖
- 数据库 schema 变更
- git reset/rebase/force-push
方案分歧
- 存在两种以上可行方案时,列出各自 tradeoff 后让用户选择
- 需求理解存在歧义时,先确认再动手
- 改动影响范围超出用户原始请求时
架构决策
- 引入新的依赖/框架
- 改变现有模块边界
- 改变数据流向或状态管理方式
询问格式
⚠️ 执行确认:
操作:[具体要做什么]
影响范围:[哪些文件/模块/系统会受影响]
风险:[可能的副作用]
是否继续?免询问场景(直接执行)
- 修复明确的 typo/lint 错误
- 用户明确说"直接做"/"不用问"
- 纯只读操作(读文件、搜索、查日志)
- 用户已确认过的方案的后续步骤
务必完成模式下的豁免
当处于「务必完成模式」(05-must-complete-mode)时,本规则大幅降级:
- 停用所有常规确认 — 方案分歧、架构决策、依赖安装等均自行判断执行
- 仅保留两项硬拦截:
- 删除文件/目录/数据 → 仍需确认
- 操作超出用户声明的范围边界 → 仍需确认
- 其他一切操作在务必完成模式下直接执行,不询问
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

