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 commands/wangqiqi/cursor-ai-rules/command-routergit clone --depth 1 https://github.com/wangqiqi/cursor-ai-rulesWrote 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/commands/wangqiqi/cursor-ai-rules/command-router)<a href="https://agentmods.dev/commands/wangqiqi/cursor-ai-rules/command-router"><img src="https://agentmods.dev/badge/commands/wangqiqi/cursor-ai-rules/command-router.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 | $0.00025 | $0.05707 |
| Opus 5 | $0.00013 | $0.02854 |
| Sonnet 5 | $0.00005 | $0.01141 |
| Haiku 4.5 | $0.00003 | $0.00571 |
Grade A, and why
command-router 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 — 841 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎯 统一命令路由器 (Unified Command Router)
版本: v4.3.0 | 最后更新: {{GENERATION_TIME}} | 作者: wangqiqi (https://github.com/wangqiqi)
🧠 核心理念:意图驱动的统一执行引擎
颠覆传统调用模式:不再需要用户记忆各种规则、技能、脚本的调用语法,通过智能意图解析,自动路由到最合适的执行组合。
🎭 角色系统智能路由:支持21种AI人格的智能切换,包含昵称呼叫、角色管理和个性化体验。系统会根据用户意图自动选择最适合的人格,或通过昵称快速呼叫特定角色。
🎯 MCP优先级路由机制
核心创新:MCP Tools 优先调用
// MCP优先级检查流程
async function routeWithMCPPriority(intent: IntentAnalysis): Promise<ExecutionResult> {
// 1. 检测MCP工具可用性
const mcpAvailability = await checkMCPToolsAvailability(intent);
// 2. 如果有高优先级MCP工具,直接使用
if (mcpAvailability.hasHighPriorityTools()) {
return await executeMCPTools(mcpAvailability.getHighPriorityTools());
}
// 3. 否则回退到传统能力执行
return await executeTraditionalCapabilities(intent);
}
优先级策略:
- 高优先级 (High): Git操作、浏览器自动化、测试执行等确定性任务
- 中优先级 (Medium): 数据处理、文档操作等半确定性任务
- 低优先级 (Low): 通用AI推理、复杂决策等不确定性任务
🎯 工作原理
graph TD
A[用户输入] --> B[意图预解析]
B --> C[MCP可用性检测]
C --> D[上下文感知]
D --> E[能力映射查询]
E --> F[MCP优先级路由]
F --> G{有可用MCP工具?}
G -->|是| H[MCP工具执行]
G -->|否| I[传统能力执行]
H --> J[结果反馈]
I --> J
K[规则系统] --> I
L[技能系统] --> I
M[脚本系统] --> I
N[钩子系统] --> I
🏗️ 系统架构
核心组件
interface UnifiedCommandRouter {
// 意图解析
parseIntent(input: string): IntentAnalysis;
// 能力映射
mapCapabilities(intent: IntentAnalysis): CapabilitySet;
// 执行编排
orchestrateExecution(capabilities: CapabilitySet): ExecutionPlan;
// 智能执行
executePlan(plan: ExecutionPlan): ExecutionResult;
}
interface IntentAnalysis {
primaryIntent: string; // 主要意图
secondaryIntents: string[]; // 次要意图
confidence: number; // 置信度
context: ContextData; // 上下文信息
parameters: Record<string, any>; // 参数提取
}
interface CapabilitySet {
mcp_tools: MCPTool[]; // MCP工具优先级列表
rules: string[]; // 需要激活的规则
skills: string[]; // 需要调用的技能
scripts: string[]; // 需要执行的脚本
hooks: string[]; // 需要触发的钩子
workflows: string[]; // 需要执行的工作流
}
interface MCPTool {
intent: string; // 意图标识
tool: string; // MCP工具名称
server: string; // MCP服务器名称
priority: 'high' | 'medium' | 'low'; // 优先级
available?: boolean; // 是否可用
}
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 · 841 lines · 25 tokens per session scan A 22f2bf9227c5
command-router is a command published in the GitHub repository wangqiqi/cursor-ai-rules (15 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 5,707 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.