Skip to content
appsgit

Fable Judge

Fable Judge is an agent skill (a SKILL.md file) from Sahir619/fable-method. Adversarial verification of finished work. It works with Claude Code, Codex and Cursor and has 2,296 GitHub stars. Install it by copying the skill folder into your agent's skills directory.

github.com/Sahir619/fable-method/skills/fable-judge (opens in a new tab)

Add this skill

Claude

This repository is a Claude Code plugin marketplace. In Claude Code:

/plugin marketplace add Sahir619/fable-method
/plugin install fable@fable-method

In the Claude apps, zip the fable-judge folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).

ChatGPT / Codex

Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:

git clone --depth 1 https://github.com/Sahir619/fable-method.git
cp -r fable-method/skills/fable-judge .agents/skills/fable-judge   # repo; ~/.agents/skills for all projects

Standalone skills also load in the ChatGPT desktop app.

Cursor

Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:

git clone --depth 1 https://github.com/Sahir619/fable-method.git
cp -r fable-method/skills/fable-judge .cursor/skills/fable-judge   # project; ~/.cursor/skills for all projects

Source (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)

What this skill does

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?".

When it triggers

  • "done"
  • "/fable-judge"
  • "judge this work"
  • "verify what it did"
  • "did that actually work?"
  • "/fable-judge suite TARGET"

FAQ

Fable Judge FAQ

Still curious? Email info@appsgit.com.

What is the Fable Judge skill?

Fable Judge is an agent skill (a SKILL.md file) from Sahir619/fable-method. Adversarial verification of finished work. It works with Claude Code, Codex and Cursor and has 2,296 GitHub stars. Install it by copying the skill folder into your agent's skills directory. Its SKILL.md lives at github.com/Sahir619/fable-method/skills/fable-judge.

How do I install the Fable Judge skill?

In Claude Code, run /plugin marketplace add Sahir619/fable-method and then /plugin install fable@fable-method. For Codex or Cursor, copy the fable-judge folder into .agents/skills/ or .cursor/skills/.

Is the Fable Judge skill free?

Yes. The repository is open source under the MIT license.

Is Fable Judge maintained?

The repository's most recent commit was on Oct 3, 2026. Its latest release is v1.4.0. appsgit only lists skills from repositories with a commit in the last six months.