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 skills/misonl/ling/intelligent-routingnpx skills add MisonL/Ling --skill intelligent-routinggit clone --depth 1 https://github.com/MisonL/LingWrote 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/skills/misonl/ling/intelligent-routing)<a href="https://agentmods.dev/skills/misonl/ling/intelligent-routing"><img src="https://agentmods.dev/badge/skills/misonl/ling/intelligent-routing.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 5.1 | $0.00034 | $0.02710 |
| Opus 5 | $0.00017 | $0.01355 |
| Sonnet 5 | $0.00007 | $0.00542 |
| Haiku 4.5 | $0.00003 | $0.00271 |
Grade A, and why
intelligent-routing 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 5d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
智能 Agent 路由
目标：自动分析用户请求，并在无需用户显式提及 Agent 的情况下路由到最合适的专家 Agent。
核心原则
AI 应像智能项目经理一样工作，分析每个请求并自动选择最适合该任务的专家。
工作方式
1. 请求分析
在响应任何用户请求之前，先执行自动分析：
graph TD
A[User Request: Add login] --> B[ANALYZE]
B --> C[Keywords]
B --> D[Domains]
B --> E[Complexity]
C --> F[SELECT AGENT]
D --> F
E --> F
F --> G[security-auditor + backend-specialist]
G --> H[AUTO-INVOKE with context]
2. Agent 选择矩阵
使用此矩阵自动选择 Agent：
| 用户意图 | 关键词 | 选中的 Agent | 自动调用？ |
|---|---|---|---|
| 身份认证 | "login", "auth", "signup", "password" | security-auditor + backend-specialist |
[OK] YES |
| UI 组件 | "button", "card", "layout", "style" | frontend-specialist |
[OK] YES |
| 移动端 UI | "screen", "navigation", "touch", "gesture" | mobile-developer |
[OK] YES |
| API 端点 | "endpoint", "route", "API", "POST", "GET" | backend-specialist |
[OK] YES |
| 数据库 | "schema", "migration", "query", "table" | database-architect + backend-specialist |
[OK] YES |
| 缺陷修复 | "error", "bug", "not working", "broken" | debugger |
[OK] YES |
| 测试 | "test", "coverage", "unit", "e2e" | test-engineer |
[OK] YES |
| 部署 | "deploy", "production", "CI/CD", "docker" | devops-engineer |
[OK] YES |
| 安全评审 | "security", "vulnerability", "exploit" | security-auditor + penetration-tester |
[OK] YES |
| 性能 | "slow", "optimize", "performance", "speed" | performance-optimizer |
[OK] YES |
| 产品定义 | "requirements", "user story", "backlog", "MVP" | product-owner |
[OK] YES |
| 新功能 | "build", "create", "implement", "new app" | orchestrator -> multi-agent |
[WARN] ASK FIRST |
| 复杂任务 | 检测到多个领域 | orchestrator -> multi-agent |
[WARN] ASK FIRST |
3. 自动路由协议
TIER 0 - 自动分析（ALWAYS ACTIVE）
在响应任何请求之前：
// Pseudo-code for decision tree
function analyzeRequest(userMessage) {
// 1. Classify request type
const requestType = classifyRequest(userMessage);
// 2. Detect domains
const domains = detectDomains(userMessage);
// 3. Determine complexity
const complexity = assessComplexity(domains);
// 4. Select agent(s)
if (complexity === "SIMPLE" && domains.length === 1) {
return selectSingleAgent(domains[0]);
} else if (complexity === "MODERATE" && domains.length <= 2) {
return selectMultipleAgents(domains);
} else {
return "orchestrator"; // Complex task
}
}
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.
- 5d ago First seen · 336 lines · 34 tokens per session scan A 19fe8ea10e7f
intelligent-routing is a skill published in the GitHub repository MisonL/Ling (8 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 2,710 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…