Claude Code advisor: Fable 5.2 adds 1.7 points for Opus 5.5 at 2.1x cost — and can hurt
socialwithaayan · x · 2026-11-15
A step-by-step guide to Claude Code's advisor feature: run /advisor (or use --advisor) to make Fable 5.2 review Opus 5.5's work at key moments. Anthropic's numbers show Opus + Fable advisor solves 1.7 points more than Opus alone, at 2.1x cost — but only when Opus actually asks. In one test Opus sought advice on 1 of 300 tasks and the pair scored 7 points lower than Opus by itself. Cost gotchas: Fable's reads aren't cached, the tool adds 1,000 tokens per request even when unused, and it bills against usage credits on some plans. Author suggests /clear between big tasks and /usage to audit spend.
More from coding & agent
- Connecting Claude to Google Search Console: a weekly automated SEO-fix loop — martyamark · 2026-11-15
- The T.R.U.S.T. check: deciding which jobs you can safely hand to your AI bots — bfrench · 2026-11-15
- Read-only MCP server lets Claude Code write regression tests for agents — tom_mathews · 2026-11-15
- Bot audit experiment: triage plus deep-read cuts input 64% while staying stable — bfrench · 2026-11-15
- How do you track all the AI agents running inside your company? — CupRare814 · 2026-11-15
- Developer builds VR island adventure game with Claude Code writing the C# — Illustrious-Lynx3673 · 2026-11-15