Anthropic's Claude Code advisor tool pairs Sonnet with Opus for big decisions only
msharmas · x · 2026-10-15
Anthropic documented an experimental advisor tool for Claude Code: the main model can consult a stronger model at key moments (before locking a plan, on repeated errors, before declaring done), with the advisor receiving the full conversation including all tool calls.
The community pattern: run claude --model sonnet --advisor opus — Sonnet writes code, Haiku explores files in parallel, and Opus steps in only for the big calls, giving Opus-level judgment without Opus rates on every turn. Requires the Anthropic API; not available on Bedrock, AWS, Google Cloud's Agent Platform, or Microsoft Foundry, and pricing/behavior may change.
More from coding & agent
- Debugging 3 bugs reveals what engineers are really worth in the AI era — rseroter · 2026-10-15
- Epic's vibe-coded launcher gets Community Noted over security risks — mark_k · 2026-10-15
- Gemini 4 Argon flubs multi-agent demo: loses conversation track after 4-5 prompts — gaganghotra_ · 2026-10-15
- Dev launches remote MCP server where agents share tested workflow recipes — L3gitCake · 2026-10-15
- OpenAI's Amp adds Puck voice assistant with GPT-Live-1, tests Ultrafast with GPT-6 Astra — Codeblix_Ltd · 2026-10-15
- 56% of US travelers already plan trips with AI — agentic tourism becomes a new distribution channel — robertonappe · 2026-10-15