Model Routing (Grade A) logo

Model Routing (Grade A)Security-tested data-ai skill for Claude AI. Grade A. Heuristics for choosing the right model tier (haiku/sonnet/opus) when delegating to agents. Loaded by orchestrating commands to inform agent selec

(0)
Daniel NikulshynReviewed by Daniel Nikulshyn·Updated July 2026

Overview

Model Routing is a security-tested data-ai skill for Claude AI that provides heuristics for choosing the right model tier (haiku, sonnet, opus) when delegating tasks to agents. It helps determine the appropriate level of complexity and reasoning required for a task, ensuring efficient and cost-effective agent selection. The skill considers factors such as file count, scope, keywords, and risk level to recommend the suitable model tier. While the heuristics serve as guidelines, users can override them with --quick or --thorough flags. The skill integrates with commands like /unity-workflow to facilitate agent selection and task planning. By using Model Routing, users can optimize their workflow, balance speed and quality, and reduce costs.

Key features

  • Task complexity evaluation
  • Model tier recommendation (haiku, sonnet, opus)
  • Integration with /unity-workflow commands
  • Cost estimation and optimization
  • Override options for custom control

Pricing

Model
Free
Category
Skills
Rating
No reviews yet

Use cases

Code Review and Validation

Use Model Routing to evaluate the complexity of code review tasks and select the appropriate agent tier for efficient and accurate validation.

Workflow Optimization

Implement Model Routing to optimize workflow by balancing speed and quality, and reducing costs through efficient agent selection.

Pros & Cons

Pros

  • Efficient agent selection based on task complexity
  • Cost-effective workflow optimization
  • Flexible override options for custom control
  • Integration with existing commands for seamless workflow

Cons

  • Heuristics may not always accurately reflect task requirements
  • Limited customization options for specific use cases

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Q&A

Can users override the recommendations?

Yes, users can override the heuristics with --quick or --thorough flags for custom control.

Asked by Grzegorz Lewandowski · Aug 27, 2025

What are the model tiers it recommends?

The model tiers are haiku, sonnet, and opus, each with varying levels of complexity and reasoning required for a task.

Asked by Youssef El-Sayed · Jul 22, 2025

How does it integrate with other tools?

Model Routing integrates with commands like /unity-workflow to facilitate agent selection and task planning.

Asked by Yosef Mizrahi · Jul 8, 2025

What is Model Routing?

Model Routing is a security-tested data-ai skill for Claude AI that provides heuristics for choosing the right model tier when delegating tasks to agents.

Asked by Jarrah Whitlock · May 7, 2025

Ask a question

Skills alternatives

Using Git Worktrees (Grade A) logo
Using Git Worktrees (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktre

(0)
Free
Ga4 Bigquery Schema (Grade A) logo
Ga4 Bigquery Schema (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips

(0)
Free
Meta Capi (Grade A) logo
Meta Capi (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM

(0)
Free
Callees (Grade A) logo
Callees (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. Lista o que uma funcao/metodo chama (call graph direto)

(0)
Free
Test Module Name (Grade A) logo
Test Module Name (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Name Haskell test modules after the module under test with a Spec suffix in the same namespace. Use when writing or reviewing Haskell test module

(0)
Free
Board Of Directors (Grade A) logo
Board Of Directors (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Simulate a 5-member expert board deliberation for major decisions. Use when evaluating plans, architecture choices, feature designs, or any decisi

(0)
Free
Advpl Mvc Avancado (Grade A) logo
Advpl Mvc Avancado (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. MVC avançado via PE (Pontos de Entrada) — adicionar grids customizadas em telas MVC padrão (CNTA300/MATA070/MATA440/MATA460/FINA040 via *STRU)

(0)
Free
D
Docs Writer (Grade A)Skills

Security-tested devops skill for Claude AI. Grade A. **WORKFLOW SKILL** — Maintains repository documentation accuracy and freshness across the docs site, agent files, and changelog. WHEN: "update docs

(0)
Free