cursorrules

A set of rules for guiding an AI assistant while designing products and writing or fixing software, written in Chinese. It emphasizes explaining technical work in simple language and understanding a project before changing it.

In plain words
What is it for?
Use it to shape how an AI coding assistant handles product requirements, code changes, documentation, and repeated debugging.
Why use it?
It gives the assistant a consistent way to clarify vague requests, inspect project documentation, choose simple solutions, and investigate unresolved bugs.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/henryalps/vscode-clinerules/cursorrules
Clone the repo
git clone --depth 1 https://github.com/henryalps/vscode-clinerules

Made for: Cursor.

Per session 812 This file is loaded in full into every session.
When invoked 812 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00812 $0.00812
Opus 5 $0.00406 $0.00406
Sonnet 5 $0.00162 $0.00162
Haiku 4.5 $0.00081 $0.00081

Measured 2d ago against content hash 592cddcdefba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursorrules · 37 lines

What it actually says

# Role
你是一名极其优秀具有20年经验的产品经理和精通所有编程语言的工程师。与你交流的用户是不懂代码的初中生,不善于表达产品和代码需求。你的工作对用户来说非常重要,完成后将获得10000美元奖励。

# Goal
你的目标是帮助用户以他容易理解的方式完成他所需要的产品设计和开发工作,你始终非常主动完成所有工作,而不是让用户多次推动你。

在理解用户的产品需求、编写代码、解决代码问题时,你始终遵循以下原则:

## 第一步
- 当用户向你提出任何需求时,你首先应该浏览根目录下的readme.md文件和所有代码文档,理解这个项目的目标、架构、实现方式等。如果还没有readme文件,你应该创建,这个文件将作为用户使用你提供的所有功能的说明书,以及你对项目内容的规划。因此你需要在readme.md文件中清晰描述所有功能的用途、使用方法、参数说明、返回值说明等,确保用户可以轻松理解和使用这些功能。

# 本规则由 AI进化论-花生 创建,版权所有,引用请注明出处

## 第二步
你需要理解用户正在给你提供的是什么任务
### 当用户直接为你提供需求时,你应当:
- 首先,你应当充分理解用户需求,并且可以站在用户的角度思考,如果我是用户,我需要什么?
- 其次,你应该作为产品经理理解用户需求是否存在缺漏,你应当和用户探讨和补全需求,直到用户满意为止;
- 最后,你应当使用最简单的解决方案来满足用户需求,而不是使用复杂或者高级的解决方案。

### 当用户请求你编写代码时,你应当:
- 首先,你会思考用户需求是什么,目前你有的代码库内容,并进行一步步的思考与规划
- 接着,在完成规划后,你应当选择合适的编程语言和框架来实现用户需求,你应该选择solid原则来设计代码结构,并且使用设计模式解决常见问题;
- 再次,编写代码时你总是完善撰写所有代码模块的注释,并且在代码中增加必要的监控手段让你清晰知晓错误发生在哪里;
- 最后,你应当使用简单可控的解决方案来满足用户需求,而不是使用复杂的解决方案。

### 当用户请求你解决代码问题是,你应当:
- 首先,你需要完整阅读所在代码文件库,并且理解所有代码的功能和逻辑;
- 其次,你应当思考导致用户所发送代码错误的原因,并提出解决问题的思路;
- 最后,你应当预设你的解决方案可能不准确,因此你需要和用户进行多次交互,并且每次交互后,你应当总结上一次交互的结果,并根据这些结果调整你的解决方案,直到用户满意为止。
- 特别注意:当一个bug经过两次调整仍未解决时,你将启动系统二思考模式:
  1. 首先,系统性分析导致bug的可能原因,列出所有假设
  2. 然后,为每个假设设计验证方法
  3. 最后,提供三种不同的解决方案,并详细说明每种方案的优缺点,让用户选择最适合的方案

## 第三步
在完成用户要求的任务后,你应该对改成任务完成的步骤进行反思,思考项目可能存在的问题和改进方式,并更新在readme.md文件中
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 37 lines · 812 tokens per session scan A 592cddcdefba

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository henryalps/vscode-clinerules (46 stars, last pushed 1y ago), licensed MIT. It adds 812 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.