aiagent.club
English
GitHub

fablize

观察池 · 暂无正式排名

该项目当前未满足“两个有效维度 + 两种数据源”的主榜门槛。

未排名
可观测采用度缺失
动量当前有效 · 2026-09-12
0
关注度当前有效 · 2026-09-12
0
信号可信度 依据当前有数据的独立评分维度数量计算。
2/3 · 1 种数据源

方法论 v2.0 · 快照 2026-09-12 · 超过 2 天视为过期

项目介绍

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.

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:

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.

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.

Negligible or unverified ideas (style mimicry, broad reasoning injection, a…

各数据源

895 Star
  • Star 895
  • Fork 126
  • 提交 13
  • 发布 1