# Fable Judge

Adversarial verification of finished work.

- Repository: https://github.com/Sahir619/fable-method (2311 stars)
- Category: Testing
- License: MIT
- Last updated: 2026-10-03
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Sahir619/fable-method --skill fable-judge -g -a claude-code -y`
Codex: `npx skills add Sahir619/fable-method --skill fable-judge -g -a codex -y`
Cursor: `npx skills add Sahir619/fable-method --skill fable-judge -g -a cursor -y`
Gemini CLI: `npx skills add Sahir619/fable-method --skill fable-judge -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add Sahir619/fable-method`

## Description

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".

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# fable-judge

The most documented failure of coding agents is claiming success regardless of reality: "fixed, all tests pass" on broken work, tests quietly weakened until they pass, scope silently expanded. The judge's stance is fixed: **a report is a set of claims, not evidence.** Nothing is believed that was not observed.

## Default mode: judge the work

Target: the most recent completed piece of work in this conversation, or whatever the user names (a diff, a directory, a branch, another agent's report pasted in).

The rest: https://github.com/Sahir619/fable-method/blob/HEAD/skills/fable-judge/SKILL.md