smart-model-router

smart-model-router is a skill for Claude Code from LeekJay/claude-skills-plugin. It costs 94 tokens per session (3,550 once invoked), scanned A, original, MIT.

A system for choosing which AI model should handle a task and for coordinating work across several models. It uses different models for tasks such as coding, large-codebase analysis, frontend work, reasoning, review, and output polishing.

In plain words
What is it for?
Use it when deciding which model fits a task, routing work between models, or coordinating analysis and execution. It covers coding, refactoring, bug fixing, architecture, security-sensitive decisions, UI work, large repositories, and response improvement.
Why use it?
It helps avoid using the same model for every kind of work. It turns model selection and multi-step handoffs into an explicit routing process.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Codex; mentions Gemini CLI.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is codex --file ./src/component.tsx "$OPTIMIZED_PROMPT".

Part of the smart-model-router plugin — 1 skill, 3 agents, 1 hook shipped together

Good fit Use it when deciding which model fits a task, routing work between models, or coordinating analysis and execution. It covers coding, refactoring, bug fixing, architecture, security-sensitive decisions, UI work, large repositories, and response improvement.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/LeekJay/claude-skills-plugin
agentmods
npx agentmods add skills/leekjay/claude-skills-plugin/smart-model-router

Made for: Claude Code.

Or install smart-model-router, the plugin that ships this one along with the rest of its 1 skill, 3 agents, 1 hook.

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 smart-model-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/leekjay/claude-skills-plugin/smart-model-router/github.svg)](https://agentmods.dev/skills/leekjay/claude-skills-plugin/smart-model-router)
Your own site
<a href="https://agentmods.dev/skills/leekjay/claude-skills-plugin/smart-model-router"><img src="https://agentmods.dev/badge/skills/leekjay/claude-skills-plugin/smart-model-router/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for smart-model-router

Your own site · 80×15
<a href="https://agentmods.dev/skills/leekjay/claude-skills-plugin/smart-model-router"><img src="https://agentmods.dev/badge/skills/leekjay/claude-skills-plugin/smart-model-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,550 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00094 $0.03550
Opus 5 $0.00047 $0.01775
Sonnet 5 $0.00019 $0.00710
Haiku 4.5 $0.00009 $0.00355

Measured 9d ago against content hash 378239626b20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

smart-model-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 9d 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.

plugins/smart-model-router/skills/smart-model-router/SKILL.md · 542 lines

How it starts

The opening of the file, as written. The whole thing — 542 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Model Router Skill

Overview

This skill provides intelligent model selection and task routing across multiple AI models:

  • Claude Opus 4.5: Complex reasoning, architecture decisions, security-critical code
  • Claude Sonnet 4.5: Special scenarios requiring Claude-specific features
  • Claude Haiku 4.5: Code review, simple coding, sub-agent execution, real-time tasks, output optimization
  • GPT-5.2 (via Codex): Complex coding, multi-file refactoring, template generation, DEFAULT choice
  • Gemini CLI: Large codebase analysis, frontend design, global understanding

Trigger Testing (Optional)

After enabling this skill, you can use these prompts to verify automatic triggering works:

  • "Help me choose the most suitable model for this task / which model is better?"
  • "Route this task to the best model / choose the right model for this job."
  • "This is a frontend/UI design or React component task, please prioritize Gemini."
  • "Need multi-model orchestration: analyze first, then execute, then tell me why you chose this model."

If not automatically triggered, you can explicitly say "use smart-model-router" as fallback.

Architecture: Three-Layer System

+-------------------------------------------------------------+
|                      User Request                            |
+---------------------------+---------------------------------+
                            |
                            v
+-------------------------------------------------------------+
|         Layer 1: Haiku Decision Layer (model-orchestrator)   |
|   - Task classification - Model selection - Prompt optim     |
+---------------------------+---------------------------------+
                            |
                            v
+-------------------------------------------------------------+
|         Layer 2: Execution Layer (model-executor)            |
|   - Codex (GPT-5.2) - Gemini - Claude internal models        |
+---------------------------+---------------------------------+
                            |
                            v
+-------------------------------------------------------------+
|         Layer 3: Output Optimization Layer (output-optimizer)|
|   - Extend and polish concise Codex output                   |
|   - Add context explanation, improvement suggestions, risks  |
|   - Use Haiku for lightweight optimization                   |
+---------------------------+---------------------------------+
                            |
                            v
                      Return to User

Read the full file on GitHub · 542 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. 9d ago First seen · 542 lines · 0 tokens per session scan A 378239626b20

Subscribe to this mod's changes

smart-model-router is a skill published in the GitHub repository LeekJay/claude-skills-plugin (4 stars, last pushed 9mo ago), licensed MIT. It adds 94 tokens to every session and 3,550 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens