fable-judge
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite TARGET".
Why this score
This repo hosts 5 skills, so its 2,304 stars are split between them (about 461 each) for scoring.
Popularity score: 72/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit 9924067e82bd, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onefable-judge Sahir619/fable-method · Skill | 72 | ★ 2.3k | ≈133 always | 1mo ago |
| fable-review davidondrej/skills · Skill Both about fable | 76 | ★ 4.2k | ≈33 always | 16d ago |
| write-judge-prompt ai-evals-course/evals-skills · Skill Both about judge | 66 | ★ 1.5k | ≈24 always | 1mo ago |
| skill-judge shareAI-lab/Kode-CLI · Skill Both about judge and against | 77 | ★ 5.2k | ≈63 always | 19d ago |
| fable Junhan2/oh-my-fable · Skill Both about fable | 60 | ★ 58 | ≈55 always | 16d ago |
| judge-task-lifecycle sno-ai/sno-station · Skill Both about judge | 70 | ★ 765 | ≈38 always | 16d ago |