#opus

Finish-First Autonomous Agent Loop for Claude Opus 4.7 – 2026 Edition

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.

A Claude Code skill that fans one hard question out to several frontier models (GPT-5.5, Gemini, Kimi, GLM) blind and in parallel, then has Opus 4.8 judge and synthesize one grounded answer. Multi-model test-time scaling with independence enforced and the judge kept separate from the panel.

Local proxy that rewrites any Anthropic API client's requests to impersonate the official Claude Code CLI, letting it use a Claude Code OAuth subscription token against api.anthropic.com.