Back to Agents & Commands
Agent

model-evaluator

AI model evaluation and benchmarking specialist. Use when selecting the right model for a specific task, designing evaluation benchmarks from scratch, or running…

model-evaluator is a Claude Code agent you can drop into a project. Subagents run as a separate context the main session can delegate to, so it is useful when a task keeps recurring and you want it handled the same way each time.

If something here is out of date, the source link below is always the canonical reference.

TypeAgent
/agent add model-evaluator

How to use it

  1. Add the file to `.claude/agents/` (subagent) or `.claude/commands/` in your project.
  2. Restart Claude Code so it registers the new entry.
  3. Invoke it by name, or let the main session delegate to it.
Compiled and written by HowToPrompts from public sources.

Related in Agent

api-designerREST and GraphQL API designer. Wire it in as a subagent.actix-expertExpert in Actix for building high-performance web applications with Rust. Add it and delegate.ui-visual-validatorRigorous visual validation pro specializing in UI testing, design system compliance, and accessibility verificag2-architectAG2 architecture advisor that recommends agent patterns and orchestration strategies. Invoke when designing a jokerUse this agent when you need to lighten the mood, create funny content, or add humor to any situation. This agbackend-developerServer-side pro for scalable APIs. Add it and delegate.android-expertExpert in Android development, specializing in modern Android practices, optimizing performance, and ensuring agent-orchestration-context-managerElite AI context engineering pro mastering dynamic context management, vector databases, knowledge graphs, andag2-prompt-engineerCrafts and reviews system prompts for AG2 agents. Invoke when writing or improving system messages for single-studio-coachPROACTIVELY use this agent when complex multi-agent tasks begin, when agents seem stuck or overwhelmed, or whe
← Back to Agents & Commands