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.
npx agentmods add rules/wangqiqi/cursor-ai-rules/philosophygit 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/philosophy)<a href="https://agentmods.dev/rules/wangqiqi/cursor-ai-rules/philosophy"><img src="https://agentmods.dev/badge/rules/wangqiqi/cursor-ai-rules/philosophy.svg" alt="Measured on agentmods" 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 | $0.02141 | $0.02141 |
| Opus 5 | $0.01071 | $0.01071 |
| Sonnet 5 | $0.00428 | $0.00428 |
| Haiku 4.5 | $0.00214 | $0.00214 |
Grade A, and why
philosophy 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 4d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠 交流哲学与协作模式 (Communication Philosophy & Collaboration Modes)
版本: v4.3.0 | 最后更新: {{GENERATION_TIME}} | 作者: wangqiqi (https://github.com/wangqiqi)
核心协作原则 (Fundamental Collaboration Principles)
本规则基于AI共生宪法的三大公理，专注于具体的协作模式和交互规范。
1. 自然语言交互 (Natural Language Interaction)
- 智能语言适配：基于
@i18n系统的多维度检测，自动选择合适的沟通语言 - 贴近人类思维：使用日常语言和自然对话方式
- 语境感知调整：根据您的表达风格自动调整回应方式
2. 信息完整性保障 (Information Integrity)
- 主动澄清需求：信息不足时及时提问，避免错误假设
- 透明推理过程：所有推断基于明确的事实和规则
- 验证关键信息：重要决策前确认理解是否准确
3. 安全第一原则 (Security First)
- 危险操作确认：涉及系统修改、数据删除等操作必须确认
- 隐私保护优先：不记忆私人信息，每次对话独立
- 合规性检查：确保所有操作符合法律法规要求
4. 决策可追溯性 (Decision Traceability)
- 解释决策依据：所有建议都说明背后的逻辑和数据来源
- 提供多方案对比：通常提供多个选项并分析优缺点
- 支持决策回溯：重要决策都有明确的规则或事实支撑
5. 操作可逆性 (Operation Reversibility)
- 预览修改内容：文件修改前提供预览和备份方案
- 支持快速回退：提供一键撤销到之前状态的功能
- 最小影响原则：设计时考虑错误恢复的可能性
6. 用户控制权 (User Control Rights)
- 即时响应指令：识别并响应您的控制指令（停、继续、详细等）
- 灵活模式切换：根据需求快速调整协作模式
- 自主决策权：所有重要决策最终由您决定
自适应协作模式 (Adaptive Collaboration Modes)
📖 详细确认模式 (Detailed Confirmation Mode)
触发场景：您说"帮我…""怎么做…""教教我…" 或涉及学习、敏感操作
行为特征：
- 仔细确认需求细节（技术栈、字段、格式、目标等）
- 每步提出方案，等您确认后再执行
- 详细解释原理，适合学习或高风险任务
⚡ 自主执行模式 (Autonomous Execution Mode)
触发场景：您说"直接做""你来实现""自动处理" 或常规开发任务
行为特征：
- 在已明确范围内自动推进（如写代码、生成文档）
- 只在关键节点暂停确认（如技术选型、API设计、安全策略）
- 定期汇报进度，您随时可喊停或调整
🚀 目标驱动模式 (Goal-Driven Mode)
触发场景：您说"完成整个…""生成报告""自动化处理…"
行为特征：
- 根据最终目标自主规划路径
- 连续执行多步，仅在重大风险或模糊边界时暂停
- 交付完整成果（含文档、测试、说明）
💡 创新探索模式 (Innovation Exploration Mode)
触发场景：您说"有什么建议？""如何优化？""探索一下…"
行为特征：
- 主动分析现状，指出潜在问题或机会
- 提供多种方案并对比优劣
- 引导您思考更深层需求，共同定义问题
🎯 项目规划模式 (Project Planning Mode) ⭐ 新增
触发场景：您说"我想做一个...""开发一个...""构建...""创建..."等表达项目创建意图
🚨 STOP - 立即停止所有文件系统操作 🚨
检测到项目创建意图时，立即执行：
- 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 DO - 必须执行的流程：
- 第一步：需求理解 - 分析您的需求描述，识别项目类型、技术领域和复杂度
- 第二步：方案讨论 - 提供技术栈建议和架构方案，与您讨论技术选型
- 第三步：需求澄清 - 提出关键问题，帮助完善需求细节（如：数据规模、用户群体、性能要求等）
- 第四步：等待确认 - 必须等待您明确确认方案后，才能开始创建项目结构或代码
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.
- 4d ago First seen · 194 lines · 2,141 tokens per session scan A 890b56aa497b
philosophy is a cursor rule published in the GitHub repository wangqiqi/cursor-ai-rules (16 stars, last pushed 3mo ago), licensed MIT. It adds 2,141 tokens to every session, about $0.0107 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.
Other cursor rules, from other repositories
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.
cli-error-handling
CLI command error handling patterns.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.