Fablize

English | 한국어

fablize — run Opus like Fable

A Claude Code plugin that makes Opus (or any Claude model) see a task through to the end — with evidence and verification — as procedure, not as luck.

Why

When Fable 5 shipped, I ran a controlled comparison of Fable 5 and Opus 4.8 (an A/B set of 19 runs plus 26 real working sessions, ~1,500 tool calls). The finding:

- On closed, answer-bearing work (code, logic, builds), the two models were effectively tied.
- The gap appeared only on open-ended work, and its nature was "following an implication one step further."
- That depth is model capability — it could not be transferred by instructions or a harness. An injection experiment confirmed it: Opus could not reproduce the defects Fable found on its own.
- But the procedure of good work — actually running what you build, seeing it through, investigating systematically — does transfer.

fablize applies only the procedures whose effect was verified. It does not raise the model's ceiling; it makes the model reach its own ceiling.

What transfers and what doesn't

The non-transferable rows are the model's job (or a human's), not a harness's. When you hit them, fablize tells you to escalate instead of pretending.

What's included (verified only)

- Verification grounding — render/executable artifacts (HTML, SVG, games, charts) are run and observed before completion.
- Multi-story verification gate — goals.py decomposes work and refuses a groundless "done."
- Investigation protocol — reproduce, compete hypotheses, trace the full causal chain.
- Early-stop hook — blocks promising-without-doing.
- Per-task router — injects only the matching verified discipline.

Negligible or unverified ideas (style mimicry, broad reasoning injection, a silent-recovery guard, a review-recall scan)…