- add scripts/main_board_top50_zf_{claude,codex,qwen3.6-27b}.tsl as produced - sync round-1 code block and archived filename in README Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- rewrite Part 2 as real tests: Claude Fable 5 / Codex GPT-5.5 / Qwen3.6-27B - add cross-env comparison table with per-round token caliber caveats - backfill roadmap evidence: lookup.py encoding fix, equity/misc.md 9252-line pile-up Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>