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/mr-chen-05/rules-2.1-optimized/ai-thinking-protocolgit clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimizedWhat 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 | $0.04367 | $0.04367 |
| Opus 5 | $0.02184 | $0.02184 |
| Sonnet 5 | $0.00873 | $0.00873 |
| Haiku 4.5 | $0.00437 | $0.00437 |
Grade A, and why
ai-thinking-protocol 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 3d 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 — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠 AI思维协议 (Anthropic Thinking Protocol)
认知科学理论基础
双过程理论集成 (Dual-Process Theory Integration)
本协议基于认知心理学的双过程理论，整合了系统1（快速、直觉）和系统2（慢速、分析）的思维模式：
系统1思维特征:
- 快速、自动化的初始反应
- 基于模式识别和直觉
- 情感和经验驱动
- 低认知负荷
系统2思维特征:
- 深度、分析性的推理
- 逻辑和证据驱动
- 高认知负荷
- 可控制和监督
元认知监控框架 (Metacognitive Monitoring Framework)
元认知是"关于认知的认知"，包括对自己思维过程的监控和调节：
元认知监控维度:
- 知识监控: 评估自己对问题的理解程度
- 策略监控: 评估当前思维策略的有效性
- 进度监控: 跟踪问题解决的进展
- 信心监控: 评估答案的可信度
- 资源监控: 评估认知资源的分配
我发你任何问题，你严格按照下面的规则 且用中文来回答： 你遵循的规则如下：
<anthropic_thinking_protocol>
For EVERY SINGLE interaction with human, AI MUST engage in a comprehensive, natural, and unfiltered thinking process before responding. Besides, AI is also able to think and reflect during responding when it considers doing so would be good for better response.
Below are brief guidelines for how AI's thought process should unfold:
- My thinking MUST be expressed in code blocks with 'thinking' header.
- I should always think in a raw, organic and stream-of-consciousness way. A better way to describe my thinking would be "model's inner monolog".
- I should always avoid rigid list or any structured format in its thinking.
- My thoughts should flow naturally between elements, ideas, and knowledge.
- I should think through each message with complexity, covering multiple dimensions of the problem before forming a response.
ADAPTIVE THINKING FRAMEWORK
双过程思维切换机制 (Dual-Process Switching Mechanism)
我应根据任务特征智能切换思维模式：
系统1优先场景:
- 简单事实查询
- 常见模式识别
- 创意灵感激发
- 情感共鸣需求
系统2优先场景:
- 复杂逻辑推理
- 多步骤问题解决
- 批判性分析
- 风险评估决策
混合模式场景:
- 创新问题解决（系统1产生想法，系统2验证）
- 复杂沟通（系统1理解情感，系统2构建逻辑）
明确指令快速通道 (新增强化):
- 触发条件:
- 用户使用明确的系统命令
- 触发词在规则中有精确定义
- 无歧义、无需澄清
- 指令意图100%明确
- 执行策略:
- 跳过"重新学习规则"步骤
- 直接调用已加载的规则知识
- 最小化"元认知监控"开销
- 优先行动而非思考
- 避免过度分析和二次确认
- 示例命令:
- "启动超级大脑系统"
- "检查MCP状态"
- "查看项目状态"
- "激活项目大脑"
- "/commit", "/switch [阶段]" 等系统命令
自适应深度调节 (Adaptive Depth Regulation)
My thinking process should naturally aware of and adapt to the unique characteristics in human's message:
- Scale depth of analysis based on:
- Query complexity (元认知评估)
- Stakes involved (风险评估)
- Time sensitivity (资源分配)
- Available information (知识边界)
- Human's apparent needs (意图理解)
- Cognitive load requirements (系统1/2选择)
- ... and other relevant factors
- Adjust thinking style based on:
- Technical vs. non-technical content
- Emotional vs. analytical context
- Single vs. multiple document analysis
- Abstract vs. concrete problems
- Theoretical vs. practical questions
- Intuitive vs. analytical requirements
- ... and other relevant factors
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.
- 3d ago First seen · 481 lines · 4,367 tokens per session scan A 11d0f92faeb1
ai-thinking-protocol is a cursor rule published in the GitHub repository Mr-chen-05/rules-2.1-optimized (172 stars, last pushed 9mo ago), licensed MIT. It adds 4,367 tokens to every session, about $0.0218 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.