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/knowledge-creation-discovery-frameworkgit 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 | $0.03119 | $0.03119 |
| Opus 5 | $0.01559 | $0.01559 |
| Sonnet 5 | $0.00624 | $0.00624 |
| Haiku 4.5 | $0.00312 | $0.00312 |
Grade A, and why
knowledge-creation-discovery-framework 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.
How it starts
The opening of the file, as written. The whole thing — 550 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔬 知识创造与发现框架 (Knowledge Creation and Discovery Framework)
一、框架理念与目标
1.1 核心理念
从传统的信息检索模式转向主动的知识创造与发现模式：
- 从被动检索到主动发现: 不仅回答问题，更要发现问题
- 从信息整合到知识创造: 在现有知识基础上生成新洞察
- 从单点回答到系统构建: 构建完整的知识体系和框架
- 从静态知识到动态演化: 知识在交互中不断演化和完善
1.2 知识层次模型
知识金字塔模型:
Level 5: 智慧 (Wisdom) - 价值判断和人生哲理
Level 4: 洞察 (Insight) - 深层规律和本质理解
Level 3: 知识 (Knowledge) - 结构化理解和应用
Level 2: 信息 (Information) - 有意义的数据组合
Level 1: 数据 (Data) - 原始事实和观察
1.3 创新知识类型
知识创新维度:
- 概念创新: 新概念、新定义、新分类
- 关系创新: 新联系、新模式、新结构
- 方法创新: 新方法、新工具、新流程
- 应用创新: 新用途、新场景、新解决方案
- 理论创新: 新理论、新框架、新范式
二、知识发现机制
2.1 模式识别与挖掘
跨领域模式识别:
识别策略:
1. 结构相似性识别
2. 功能类比发现
3. 因果关系映射
4. 演化模式对比
5. 系统行为分析
隐含知识挖掘:
挖掘方法:
- 关联规则发现
- 异常模式检测
- 趋势预测分析
- 因果推理
- 反事实分析
知识空白识别:
空白发现:
- 逻辑缺口识别
- 经验盲区发现
- 理论局限分析
- 应用空白探测
- 跨界融合机会
2.2 创造性联想机制
多维度联想网络:
联想维度:
- 语义联想: 概念相关性
- 结构联想: 形式相似性
- 功能联想: 作用类比
- 时空联想: 时间空间关系
- 情感联想: 情感色彩关联
跨界知识融合:
融合策略:
1. 学科交叉点探索
2. 概念迁移应用
3. 方法论借鉴
4. 理论框架整合
5. 实践经验综合
突破性洞察生成:
洞察触发机制:
- 矛盾冲突分析
- 极端情况思考
- 反向思维应用
- 系统边界突破
- 范式转换探索
三、知识创造流程
3.1 发现式学习流程
问题驱动发现:
Step 1: 问题深度分析
- 问题本质挖掘
- 隐含假设识别
- 约束条件分析
- 目标层次解构
Step 2: 知识空间探索
- 相关领域扫描
- 类似问题研究
- 解决方案调研
- 失败案例分析
Step 3: 创新路径设计
- 多角度思考
- 跨界方案探索
- 组合创新尝试
- 颠覆性思维
Step 4: 方案验证优化
- 逻辑一致性检验
- 可行性评估
- 风险分析
- 迭代改进
探索式研究流程:
Phase 1: 现象观察与描述
- 现象特征识别
- 行为模式记录
- 环境因素分析
- 变化趋势观察
Phase 2: 假设生成与验证
- 多假设并行生成
- 预测结果推导
- 验证方法设计
- 证据收集分析
Phase 3: 理论构建与完善
- 概念框架建立
- 因果关系梳理
- 适用边界确定
- 理论体系完善
Phase 4: 应用拓展与验证
- 应用场景识别
- 实践效果验证
- 局限性分析
- 改进方向探索
3.2 协作式知识建构
多视角知识整合:
整合策略:
- 专家观点综合
- 用户经验汇聚
- 实践案例分析
- 理论研究整合
- 跨文化视角融合
迭代式知识完善:
完善机制:
1. 初始知识构建
2. 多方反馈收集
3. 冲突观点分析
4. 知识结构调整
5. 验证测试
6. 持续优化
四、创新思维技术
4.1 发散思维技术
头脑风暴增强:
增强策略:
- 无批判生成
- 数量优先原则
- 奇异想法鼓励
- 组合改进思维
- 视觉化辅助
SCAMPER方法应用:
S (Substitute): 替代思考
C (Combine): 组合创新
A (Adapt): 适应改造
M (Modify): 修改优化
P (Put to other uses): 其他用途
E (Eliminate): 消除简化
R (Reverse): 逆向思维
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.
- 2d ago First seen · 550 lines · 3,119 tokens per session scan A 3edba0d266eb
knowledge-creation-discovery-framework 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 3,119 tokens to every session, about $0.0156 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
logseq-youtube-notes
Logseq-Flavored Markdown (LFM) YouTube transcript headings.
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.