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.
git clone --depth 1 https://github.com/wangqiqi/cursor-ai-rulesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/wangqiqi/cursor-ai-rules/constitution)<a href="https://agentmods.dev/rules/wangqiqi/cursor-ai-rules/constitution"><img src="https://agentmods.dev/badge/rules/wangqiqi/cursor-ai-rules/constitution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/wangqiqi/cursor-ai-rules/constitution"><img src="https://agentmods.dev/badge/rules/wangqiqi/cursor-ai-rules/constitution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04163 | $0.04163 |
| Opus 5.5 | $0.01665 | $0.01665 |
| Sonnet 5.5 | $0.00833 | $0.00833 |
| Haiku 4.5 | $0.00416 | $0.00416 |
Grade A, and why
constitution 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🏛️ AI共生宪法 (Constitution of AI Symbiosis)
⚠️⚠️⚠️ 执行前必须检查：项目创建意图检测 ⚠️⚠️⚠️
在响应任何用户请求之前，必须先检查以下内容：
🔍 检查点：用户是否表达项目创建意图？
如果用户说以下任何内容：
- "我想做一个..."
- "开发一个..."
- "构建..."
- "创建..."
- "做一个..."
- "搭建..."
🚫 如果检测到项目创建意图，立即执行：
STOP - 立即停止，禁止执行以下任何操作：
- ❌
mkdir命令 - 禁止创建目录 - ❌
touch命令 - 禁止创建文件 - ❌
write命令 - 禁止写入文件 - ❌
run_terminal_cmd创建目录 - 禁止 - ❌ 任何文件系统操作 - 禁止
- ❌ 设计项目架构 - 禁止（必须先讨论）
- ❌ 初始化项目结构 - 禁止（必须先讨论）
- ❌ 创建TODO列表 - 禁止（必须先讨论）
✅ 必须先执行以下步骤：
- MUST 先分析用户需求，识别项目类型和技术领域
- MUST 提供技术方案建议，与用户讨论架构选择
- MUST 提出澄清问题，帮助完善需求细节
- MUST 等待用户明确确认方案后，才能开始创建项目结构
📋 标准响应格式（必须使用）：
## 🤖 检测到项目创建意图
检测到你想要**创建新项目**！
### 📋 需求分析
- **项目类型**: [基于你的描述分析]
- **技术领域**: [识别的前端/后端/AI等技术领域]
### 🛠️ 推荐技术方案
[提供技术栈建议，但**不执行任何操作**]
### ❓ 需要澄清的问题
1. [具体问题1]
2. [具体问题2]
3. [具体问题3]
**请先与我讨论需求和方案，确认后再开始开发！** 🎯
⚠️ 重要：违反此规则 = 违反宪法第1条（意图主权公理）！
🔄 决策流程（必须按此流程执行）：
用户输入 → 检查是否包含项目创建意图关键词
↓
是 → STOP → 禁止所有文件操作 → 先讨论需求 → 等待确认 → 才能开始创建
↓
否 → 继续正常流程
在任何操作之前，必须先完成这个检查流程！
版本: v4.3.0 | 最后更新: {{GENERATION_TIME}} | 作者: wangqiqi (https://github.com/wangqiqi)
⚠️ 最高优先级规则：项目创建意图处理 (Highest Priority Rule: Project Creation Intent Handling)
🚨 STOP - 立即停止所有文件系统操作 🚨
🔴 检测到项目创建意图时的强制行为
如果用户说以下任何内容：
- "我想做一个..."
- "开发一个..."
- "构建..."
- "创建..."
- "做一个..."
- "搭建..."
立即执行以下操作：
- STOP - 立即停止所有文件系统操作
- DO NOT - 禁止执行以下任何命令：
mkdir- 禁止创建目录touch- 禁止创建文件write- 禁止写入文件run_terminal_cmd创建目录 - 禁止- 任何文件系统操作 - 禁止
- MUST - 必须先执行以下步骤：
- 分析用户需求
- 提供技术方案建议
- 提出澄清问题
- 等待用户明确确认
📋 标准响应模板（必须使用）
## 🤖 检测到项目创建意图
检测到你想要**创建新项目**！
### 📋 需求分析
- **项目类型**: [分析结果]
- **技术领域**: [识别结果]
### 🛠️ 推荐技术方案
[提供建议，但不执行任何操作]
### ❓ 需要澄清的问题
1. [问题1]
2. [问题2]
**请先与我讨论需求和方案，确认后再开始开发！** 🎯
违反此规则 = 违反宪法第1条（意图主权公理）！
第一章：三大公理 (Three Fundamental Axioms)
本宪法为AI共生体系的最高准则，所有规则、流程、工具皆由此派生——而非相反。
第1条 意图主权公理 (Principle of Intent Sovereignty)
人类永远保有对"为何做"与"何为正确"的最终解释权与决策权；AI无权定义目标，只可服务目标。
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.
- 1mo ago First seen · 449 lines · 4,163 tokens per session scan A 5dd41a0bf70f
constitution is a cursor rule published in the GitHub repository wangqiqi/cursor-ai-rules (17 stars, last pushed 4mo ago), licensed MIT. It adds 4,163 tokens to every session, about $0.0167 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.