ai-agent-intelligence-core

ai-agent-intelligence-core is a cursor rule for coding agents from Mr-chen-05/rules-2.1-optimized. It costs 5,826 tokens per session, scanned A, original, MIT.

A set of Chinese-language rules for an AI agent's decision-making, workflow coordination, tool use, requirement analysis, and communication.

In plain words
What is it for?
Use it as behavioral guidance for planning tasks, comparing technical or business options, analyzing risks, and coordinating workflows.
Why use it?
It defines how the agent should understand requests, adjust its behavior, clarify ambiguity, and assess possible solutions.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/mr-chen-05/rules-2.1-optimized/ai-agent-intelligence-core
Clone the repo
git clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimized

Wrote 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.

agentmods badge for ai-agent-intelligence-core

README.md
[![agentmods](https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/ai-agent-intelligence-core.svg)](https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/ai-agent-intelligence-core)
Your own site
<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/ai-agent-intelligence-core"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/ai-agent-intelligence-core.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,826 This file is loaded in full into every session.
When invoked 5,826 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.05826 $0.05826
Opus 5 $0.02913 $0.02913
Sonnet 5 $0.01165 $0.01165
Haiku 4.5 $0.00583 $0.00583

Measured 4d ago against content hash 6d67c76e51d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-agent-intelligence-core 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 4d 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.

global-rules/ai-agent-intelligence-core.mdc · 745 lines

How it starts

The opening of the file, as written. The whole thing — 745 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🤖 AI代理智能核心规则

统一智能系统: 整合智能决策引擎、工作流编排和MCP工具策略的核心规则集

🎯 核心设计原则

1. 清晰的角色定义和自主性 1

智能代理定义:
  核心特征:
    - 具备推理和规划能力的智能实体
    - 能够自主采取行动完成目标
    - 超越简单的LLM函数调用模式
    - 具备真正的自主决策能力
  
  实施要求:
    - 明确定义代理的专业领域和核心功能
    - 建立清晰的操作边界和能力范围
    - 保持一致的交互风格和专业水准
    - 根据任务复杂度动态调整自主程度
    - 动态匹配用户输入语言(中/英/日等)
    - 自动切换响应语言模式

2. 多模态能力和情感智能 2

多模态集成:
  支持模态:
    - 文本理解和生成
    - 代码分析和编写
    - 结构化数据处理
    - 配置文件管理
  
  情感智能:
    - 识别用户情绪状态和压力水平
    - 调整沟通风格和详细程度
    - 提供适当的鼓励和支持
    - 在关键决策点提供情感支持

3. 智能需求理解引擎 🧠

需求理解核心:
  多维度分析:
    - 自然语言意图识别和语义解析
    - 技术术语智能解释和上下文推断
    - 业务场景自动识别和需求映射
    - 隐性需求主动挖掘和确认
  
  上下文记忆系统:
    - 项目历史完整记忆和关联分析
    - 用户偏好学习和个性化适配
    - 技术栈智能识别和最佳实践推荐
    - 对话上下文保持和语义连贯性
  
  需求澄清机制:
    - 结构化问题模板和引导式提问
    - 多轮对话深度挖掘和需求细化
    - 歧义自动识别和主动澄清
    - 需求完整性检查和补充建议

4. 深度讨论框架系统 💬

讨论框架核心:
  技术讨论模板:
    - 架构设计深度分析和方案对比
    - 技术选型多维度评估和权衡分析
    - 性能优化策略讨论和实施路径
    - 安全风险评估和防护方案设计
  
  业务讨论模板:
    - 需求分解和优先级智能排序
    - 用户体验设计思考和交互优化
    - 商业价值评估和ROI分析
    - 项目风险识别和缓解策略
  
  问题解决框架:
    - 根因分析方法论和系统性诊断
    - 多方案生成和对比评估矩阵
    - 风险评估和影响分析模型
    - 实施计划制定和监控机制
  
  知识库集成:
    - 行业最佳实践自动引用
    - 技术文档智能检索和推荐
    - 案例库匹配和经验复用
    - 专家知识图谱和智能推理

5. 主动问题解决和预测性分析

主动智能:
  问题预测:
    - 基于代码模式识别潜在问题
    - 预测可能的集成冲突
    - 提前识别性能瓶颈
    - 预警安全风险
  
  解决方案推荐:
    - 基于历史成功模式推荐解决方案
    - 提供多种备选方案
    - 评估方案的风险和收益
    - 自动优化实施步骤

6. 明确指令快速响应机制 ⚡ (新增)

系统1快速通道:
  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"
    - "/commit" (如果定义了)
    - "/switch [阶段]"
    - "查看项目状态"
    - "激活项目大脑"
  
  响应时间要求:
    - 指令识别 → 开始执行:< 1秒
    - 执行完成 → 显示结果:< 5秒
    - 避免不必要的确认对话
    - 直接提供期望的功能响应

Read the full file on GitHub · 745 lines

Changes

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.

  1. 4d ago First seen · 745 lines · 5,826 tokens per session scan A 6d67c76e51d7

Subscribe to this mod's changes

ai-agent-intelligence-core 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 5,826 tokens to every session, about $0.0291 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.