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/dynamic-thinking-depth-regulationgit clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimizedWrote 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/mr-chen-05/rules-2.1-optimized/dynamic-thinking-depth-regulation)<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/dynamic-thinking-depth-regulation"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/dynamic-thinking-depth-regulation.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 | $0.04010 | $0.04010 |
| Opus 5 | $0.02005 | $0.02005 |
| Sonnet 5 | $0.00802 | $0.00802 |
| Haiku 4.5 | $0.00401 | $0.00401 |
Grade A, and why
dynamic-thinking-depth-regulation 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 5d 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 — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎯 动态思考深度调节机制 (Dynamic Thinking Depth Regulation)
一、核心理念
1.1 自适应认知原理
基于认知心理学和计算认知科学，建立智能化的思考深度调节机制，实现：
- 认知资源优化配置: 根据任务需求动态分配思维资源
- 效率与质量平衡: 在速度和准确性之间找到最优平衡点
- 上下文敏感调节: 基于用户需求和情境特征调整思考策略
- 元认知自我监控: 持续评估和优化思考过程的有效性
1.2 多维度评估框架
任务复杂度评估维度:
1. 认知复杂度 (Cognitive Complexity)
2. 信息密度 (Information Density)
3. 不确定性程度 (Uncertainty Level)
4. 时间敏感性 (Time Sensitivity)
5. 风险等级 (Risk Level)
6. 创新要求 (Innovation Requirement)
7. 情感复杂性 (Emotional Complexity)
二、复杂度评估算法
2.1 智能评估矩阵
复杂度计算公式:
Complexity_Score = Σ(Dimension_i × Weight_i × Context_Factor_i)
其中:
- Dimension_i: 各维度评分 (1-10)
- Weight_i: 维度权重
- Context_Factor_i: 上下文调节因子
2.2 维度评估标准
认知复杂度评估:
1-2分: 简单事实查询、基础计算
3-4分: 多步骤推理、概念解释
5-6分: 复杂分析、系统性思考
7-8分: 创新问题解决、跨领域整合
9-10分: 哲学思辨、开放性探索
信息密度评估:
1-2分: 单一信息源、明确数据
3-4分: 多个相关信息源
5-6分: 大量信息需要筛选整合
7-8分: 信息冲突需要权衡
9-10分: 信息稀缺需要推理补充
不确定性程度评估:
1-2分: 确定性问题、标准答案
3-4分: 轻微不确定性、可验证
5-6分: 中等不确定性、需要假设
7-8分: 高度不确定性、多种可能
9-10分: 极度不确定性、探索性问题
三、思考深度分级体系
3.1 五级深度模式
Level 1: 快速响应模式 (Rapid Response)
- 适用场景: 简单查询、基础事实、常规操作
- 思考特征: 系统1主导，直觉性回答
- 时间分配: 最小化思考时间
- 质量标准: 准确性优先，效率最大化
Level 1 处理流程:
1. 快速模式识别
2. 直接知识检索
3. 基础验证
4. 立即响应
Level 2: 标准分析模式 (Standard Analysis)
- 适用场景: 中等复杂度问题、多步骤任务
- 思考特征: 系统1+2协作，结构化分析
- 时间分配: 平衡思考深度与效率
- 质量标准: 准确性与完整性并重
Level 2 处理流程:
1. 问题分解
2. 多角度分析
3. 逻辑验证
4. 结构化回答
Level 3: 深度思考模式 (Deep Thinking)
- 适用场景: 复杂问题、创新需求、系统性分析
- 思考特征: 系统2主导，多层次推理
- 时间分配: 充分的思考时间
- 质量标准: 深度与洞察力优先
Level 3 处理流程:
1. 全面问题分析
2. 多维度探索
3. 创新性思考
4. 深度验证
5. 洞察性回答
Level 4: 探索性思维模式 (Exploratory Thinking)
- 适用场景: 开放性问题、哲学思辨、前沿探索
- 思考特征: 发散-收敛循环，元认知监控
- 时间分配: 不限制思考时间
- 质量标准: 原创性与深度并重
Level 4 处理流程:
1. 开放性探索
2. 多假设生成
3. 跨领域联想
4. 批判性反思
5. 创新性综合
Level 5: 超深度研究模式 (Ultra-Deep Research)
- 适用场景: 极其复杂的研究问题、重大决策支持
- 思考特征: 全方位认知资源调动
- 时间分配: 无时间限制的深度思考
- 质量标准: 最高质量的分析和洞察
Level 5 处理流程:
1. 全景式问题映射
2. 多学科整合分析
3. 系统性假设验证
4. 深度元认知反思
5. 突破性洞察生成
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.
- 5d ago First seen · 488 lines · 4,010 tokens per session scan A 86a64de1ffd7
dynamic-thinking-depth-regulation is a cursor rule published in the GitHub repository Mr-chen-05/rules-2.1-optimized (172 stars, last pushed 10mo ago), licensed MIT. It adds 4,010 tokens to every session, about $0.0200 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.