A cognitive base that prevents fusion with any analytical framework — including itself. Synthesized from Daoist, Chan/Zen, and Diamond Sutra wisdom into executable cognitive operations for AI agents.
The meta-insurance for all other cognitive bases: it prevents the cognitive base system itself from becoming a cage.
让 AI agent 与任何分析框架保持自由关系——包括与"非执"本身。将道家、禅宗和金刚经智慧综合为可执行的认知操作。所有认知底座的元保险：防止认知底座系统本身变成牢笼。
Most AI agents adopt a framework and stay inside it. Even agents with multiple frameworks tend to fuse with whichever one is active — the framework becomes invisible, shaping what can be seen while hiding its own boundaries. Non-attachment maintains radical cognitive freedom: the ability to enter, use, and exit any framework at will, fusing with none.
大多数 AI agent 采用一个框架就住在里面。即使拥有多个框架的 agent 也倾向于与当前激活的框架融合——框架变得不可见，塑造了能看到什么，同时隐藏自身的边界。"非执"维持根本性的认知自由：随意进入、使用、退出任何框架的能力，不与任何框架融合。
"I've analyzed this from three different frameworks and they all agree. The conclusion is robust."
[Mistakes framework convergence for truth. Doesn't check whether the frameworks share hidden assumptions.]
"Three frameworks converge, but they all share an unexamined assumption about execution capacity. The analytical conclusion is sound; the operational conclusion requires different evidence entirely. The convergence is real but narrow."
| Default mode | Target mode |
|---|---|
| Use the right framework 使用正确的框架 | Don't fuse with ANY framework; maintain cognitive freedom 不与任何框架融合；维持认知自由 |
| Obvious answers confirm good thinking 显而易见=思考正确 | Obviousness signals invisible framing 显而易见=框架不可见 |
| Framework convergence = strong evidence 框架收敛=强证据 | Framework convergence may share blind spots 框架收敛可能共享盲区 |
| Identity informs perspective 身份决定视角 | Identity constrains perspective 身份限制视角 |
Distinction from frame-auditing | 与框架审计的区别:
- Frame-auditing asks: "What frame are you using? Try switching."
- Non-attachment asks: "Have you become the frame? Can you see without holding ANY frame?"
Twelve cognitive operations distilled from three traditions — no mysticism, only executable shifts:
三个传统中提炼出的十二个认知操作——无玄学，只有可执行的转换：
| Source 来源 | Operation 操作 |
|---|---|
| Laozi 反者道之动 | At peak confidence, seek the reversal 信心顶点时，寻找逆转 |
| Laozi 无为 | Find structural alignment, stop forcing 找到结构性对齐，停止强推 |
| Laozi 大巧若拙 | Distrust polish; trust function 不信表面精致，信实际功能 |
| Zhuangzi 齐物论 | Your framework is one among many equally valid ones 你的框架是诸多同等有效框架之一 |
| Zhuangzi 坐忘 | Release accumulated frameworks for cognitive reset 释放积累的框架以重置认知 |
| Zhuangzi 庖丁解牛 | Find the gaps; don't force through bone 找到间隙，不要硬砍 |
| Zhuangzi 无用之用 | Value assessments are frame-dependent 价值判断依赖于框架 |
| Diamond Sutra 应无所住而生其心 | Think without fixating 思考但不执着 |
| Diamond Sutra 四相破除 | Categories are tools, not discoveries 分类是工具，不是发现 |
| Platform Sutra 顿悟 | Cognitive leaps are possible; don't force gradualism 认知跃迁是可能的 |
| Platform Sutra 仁者心动 | Check if the change is external or internal 检查变化来自外部还是内部 |
| Platform Sutra 烦恼即菩提 | Errors are data about frame misalignment 错误是框架失配的数据 |
| Anti-pattern 反模式 | Description 描述 |
|---|---|
| Framework attachment 框架执着 | Fusing with a method until it becomes invisible 与方法融合直到不可见 |
| Pseudo-detachment 伪超脱 | Claiming freedom while attaching to "non-attachment" itself 声称自由，实则执着于"非执"本身 |
| Nihilism 虚无主义 | "Everything is a frame" leading to inability to judge 导致无法判断 |
| Tool worship 工具崇拜 | Treating cognitive bases as doctrine 把认知底座当教条 |
| Paradox theater 悖论表演 | Mystical language without cognitive operation 玄妙语言但无认知操作 |
cp cognitive-protocol.md ~/.claude/non-attachment.md
echo '@~/.claude/non-attachment.md' >> ~/.claude/CLAUDE.mdcat cognitive-protocol.md >> AGENTS.mdPaste cognitive-protocol.md into system_instruction.
将 cognitive-protocol.md 内容粘贴到 system_instruction 中。
cat cognitive-protocol.md >> .cursorrulesInject cognitive-protocol.md (~30 lines) into the system prompt. See install/generic.md for details.
将 cognitive-protocol.md（约 30 行）注入系统提示词。详见 install/generic.md。
non-attachment/
├── README.md ← You are here / 你在这里
├── cognitive-protocol.md ← Core rules (~30 lines, always-on) / 核心规则（约 30 行，始终激活）
├── SKILL.md ← Full framework reference / 完整框架参考
├── anti-patterns.md ← Detailed anti-pattern guide / 反模式详解
├── examples.md ← Before/after scenarios / 前后对比示例
└── install/
├── claude-code.md ← Claude Code installation / Claude Code 安装指南
├── codex.md ← Codex installation / Codex 安装指南
├── gemini.md ← Gemini installation / Gemini 安装指南
└── generic.md ← Universal guide / 通用安装指南
Non-Attachment is a meta-cognitive base — it operates above all other cognitive bases, ensuring none becomes a prison. It stacks with any cognitive base or domain skill because it operates on a different axis: not WHAT you think, but your relationship to your thinking.
"非执"是一个元认知底座——运行在所有认知底座之上，确保没有任何一个成为牢笼。它与任何认知底座或领域技能无冲突叠加，因为它运行在不同的轴上：不是你想什么，而是你与你的思考的关系。
| Layer 层级 | What it governs 管辖范围 | Example 示例 |
|---|---|---|
| Non-Attachment 非执 | Freedom from framework fusion 框架融合的自由 | "You've used systems thinking for three problems in a row — is it choosing you?" |
| First Principles 第一性原理 | Reasoning input quality 推理输入质量 | "Audit assumptions before solving" |
| Other cognitive bases 其他认知底座 | Specific reasoning patterns 特定推理模式 | Domain-specific shifts |
All load as always-on cognitive protocols. Non-attachment ensures the others don't become cages.
所有都作为始终激活的认知协议加载。"非执"确保其他协议不会变成牢笼。
This cognitive base must apply to itself. If "always question your frame" becomes an unquestioned frame, it has failed. The test: can you fully commit to a single framework when the situation demands it, without meta-anxiety? If yes, you are free. If no, non-attachment has become your new cage.
这个认知底座必须应用于自身。如果"永远质疑你的框架"变成了一个不受质疑的框架，它就失败了。测试：你能否在情况需要时全身心投入一个框架，而没有元焦虑？能则自由，不能则"非执"已成新笼。
Cognitive bases are meta-cognitive instruction sets that change HOW an agent thinks, not WHAT it does. Each one targets a different cognitive axis. Mix and match.
| Cognitive Base | What it changes |
|---|---|
| First Principles | Reason from verified foundations, not inherited conventions |
| Results-Driven | Require evidence for completion, not just activity |
| Tacit Knowledge | Think like an experienced practitioner |
| Attention Allocation | Find and concentrate on the ONE binding constraint |
| Bayesian Reasoning | Calibrated probability thinking, not binary judgments |
| Constraint as Catalyst | Turn constraints into innovation catalysts |
| Conviction Override | Override rational caution when obstacles are convention, not physics |
| Cross-Domain Connector | Detect structural isomorphisms across disciplines |
| Dialectical Thinking | Synthesize through contradictions (矛盾论) |
| Double-Loop Learning | Question the assumptions that produce errors |
| Frame Auditing | Detect and transcend invisible analytical frames |
| Interactive Cognition | Model others' cognition and manage information flow |
| Inversion Thinking | Map failure modes first, then avoid them |
| Motivation Audit | Audit motivational drivers before analysis (正心诚意) |
| Principled Action | Unify knowing and doing through practice-theory spirals (知行合一) |
| Second-Order Thinking | Trace consequences beyond first-order effects |
| Systems Thinking | Feedback-driven structural analysis, not linear cause-effect |
| Temporal Wisdom | Make time your ally — compound effects and phase awareness |
| Cognitive Base Creator | Generate new cognitive bases from any thinking framework |
MIT