Get recommended a cheaper model with this skill

Rightmodeler replays real agent traces through cheaper models, judges outputs against shipped versions, and shows cost-saving opportunities with evidence. The tool supports traces from Claude Code, Codex, LangSmith, OpenAI SDK, Langfuse, Braintrust, Phoenix, and OTel GenAI, generating a report rather than a runtime gateway.

Prove which models you can safely downgrade. rightmodeler replays your real agent traces through cheaper models, judges each output against what you already shipped, and shows exactly where you can cut cost — with evidence and confidence on every call. 0% Approvedpr summary gpt-4.1 → gpt-4o-mini Pending — cascade risktool agent claude-opus-4 → llama-3.3-70b Approvedjson extraction gpt-4o → gpt-4o-mini Approvedsql generation gpt-4o → deepseek-chat Abstainedauth code edit gpt-4.1 → — Approved1pr summarygpt-4.1 → gpt-4o-mini72%0.94reference+judge— Pending — cascade risk2tool agentclaude-opus-4 → llama-3.3-70b41%0.88trajectory Approved3json extractiongpt-4o → gpt-4o-mini68%1.00deterministic— Approved4sql generationgpt-4o → deepseek-chat55%0.91reference— Abstained5auth code editgpt-4.1 → ———none Reads the traces you already have. Reads traces from Claude Code, Codex, LangSmith / LangGraph, OpenAI SDK, Langfuse, Braintrust, Phoenix OpenInference , OTel GenAI. Run it on your own traces. It’s a report, not a runtime gateway — prove the savings on your own data first.