Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillation (FABLE_CODE.md), measured playbook, verification hooks, and design/MCP/test skills. "Fable 5 Lite," done right.
Agent
Independent, cold verifier of a grounding ledger before implementation or commit. Assumes every claim is wrong until the live code proves it right. Row-checks cited evidence, gap-scans for omitted load-bearing claims, and certifies that a plain-English summary matches the diff. Read-only — cannot mutate the repo. Use…
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.