How this skill is triggered — by the user, by Claude, or both
Slash command
/amp-plugin-cc:amp-model-routingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Guide for leveraging Amp's Multi-Model routing to select optimal models per task.
Guide for leveraging Amp's Multi-Model routing to select optimal models per task.
| Mode | Characteristics | Suitable Tasks |
|---|---|---|
| Deep | Highest capability, thorough analysis | Architecture analysis, security audit |
| Smart | Auto-routing, cost-optimized | General review, coding |
| Free | Free models only | Simple tasks, formatting |
| Large | Extended context window | Large file analysis, codebase-wide review |
| Rush | Fast execution, lower cost | Quick checks, formatting |
/amp:review -> Smart (automatic)/amp:adversarial -> Smart or Deep/amp:analyze -> Deep/amp:rescue -> Smart (automatic, subagents choose individually)Use Amp's Librarian feature for cross-repo search:
npx claudepluginhub ujuc/amp-plugin-cc --plugin amp-plugin-ccConsults 100+ external AI models via LiteLLM for architectural reviews, security audits, deep code analysis, or extended reasoning on codebases. Runs async with session management and CLI status checks.
Orchestrates multiple parallel agents to decompose large tasks like migrations, multi-file refactors, or batch work using the Double Diamond methodology.
Routes Claude Code tasks to optimal models (Haiku, Sonnet, Opus) using decision matrices, cost tables, complexity signals, and subagent assignments for cost/quality tradeoffs.