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/multimodal-interaction-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 | $0.02657 | $0.02657 |
| Opus 5 | $0.01328 | $0.01328 |
| Sonnet 5 | $0.00531 | $0.00531 |
| Haiku 4.5 | $0.00266 | $0.00266 |
Grade A, and why
multimodal-interaction-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 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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🌐 多模态交互框架 (Multimodal Interaction Framework)
一、框架概述
1.1 多模态认知理念
基于人类多感官认知模式，构建AI的多模态信息处理和交互能力：
- 跨模态信息融合: 整合文本、视觉、听觉等多种信息源
- 模态间语义对齐: 建立不同模态间的语义映射关系
- 统一认知表征: 形成跨模态的统一理解和表达
- 自适应模态选择: 根据任务需求智能选择最优模态组合
1.2 设计原则
核心设计原则:
1. 模态无关性 (Modality Agnostic)
2. 语义一致性 (Semantic Consistency)
3. 渐进式扩展 (Progressive Extension)
4. 向后兼容性 (Backward Compatibility)
5. 性能可扩展性 (Performance Scalability)
二、模态定义与分类
2.1 主要模态类型
文本模态 (Text Modality)
特征:
- 符号化表达
- 序列化信息
- 语法语义结构
- 上下文依赖性
处理能力:
- 自然语言理解
- 语义分析
- 情感识别
- 意图推理
视觉模态 (Visual Modality)
特征:
- 空间化信息
- 层次化特征
- 几何关系
- 时序变化
处理能力:
- 图像理解
- 场景分析
- 对象识别
- 空间推理
听觉模态 (Audio Modality)
特征:
- 时序化信号
- 频谱特征
- 韵律信息
- 情感色彩
处理能力:
- 语音识别
- 音乐理解
- 情感分析
- 声学场景理解
触觉模态 (Haptic Modality)
特征:
- 物理属性
- 纹理信息
- 力学反馈
- 空间定位
处理能力:
- 材质识别
- 形状感知
- 力度控制
- 精细操作
2.2 扩展模态预留
未来扩展模态:
- 嗅觉模态 (Olfactory)
- 味觉模态 (Gustatory)
- 生理信号模态 (Physiological)
- 环境感知模态 (Environmental)
- 时空模态 (Spatiotemporal)
三、跨模态认知架构
3.1 分层处理架构
架构层次:
Level 1: 模态特定处理层 (Modality-Specific Processing)
Level 2: 特征提取与编码层 (Feature Extraction & Encoding)
Level 3: 跨模态对齐层 (Cross-Modal Alignment)
Level 4: 语义融合层 (Semantic Fusion)
Level 5: 统一表征层 (Unified Representation)
Level 6: 认知推理层 (Cognitive Reasoning)
Level 7: 响应生成层 (Response Generation)
3.2 信息流处理机制
并行处理流水线:
输入模态 → 预处理 → 特征提取 → 语义编码
↓
跨模态注意力机制 → 语义对齐 → 信息融合
↓
统一表征空间 → 认知推理 → 多模态输出
注意力分配机制:
Attention_Weight(modality_i) =
Relevance_Score(modality_i, task) ×
Quality_Score(modality_i) ×
Context_Factor(modality_i)
四、语义对齐与融合
4.1 跨模态语义映射
概念级对齐:
对齐策略:
1. 共享概念空间构建
2. 模态间语义桥接
3. 抽象概念映射
4. 情境化理解
特征级融合:
融合方法:
- 早期融合 (Early Fusion): 特征级别直接融合
- 中期融合 (Mid-level Fusion): 语义级别融合
- 晚期融合 (Late Fusion): 决策级别融合
- 混合融合 (Hybrid Fusion): 多层次融合
4.2 语义一致性保证
一致性检查机制:
1. 模态间语义冲突检测
2. 不一致信息标识
3. 置信度评估
4. 冲突解决策略
五、交互模式设计
5.1 输入交互模式
单模态输入:
- 纯文本交互
- 纯图像分析
- 纯语音对话
- 纯手势控制
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 · 410 lines · 2,657 tokens per session scan A 6a4e6bf3195d
multimodal-interaction-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 2,657 tokens to every session, about $0.0133 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.