Skip to content
mcp/skillhub

Agent Skill

Fable Judge skill

fable-judgeSahir619/fable-methodskills/fable-judge/SKILL.md

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".

2.3kMIT

always on

124 tokname + description

once used

1,222 tokSKILL.md body

bundled files

11 KB

repo stars

2.3kGitHub

Install the Fable Judge skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/Sahir619/fable-method --skill fable-judge

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/Sahir619/fable-method.git /tmp/fable-method
mkdir -p ~/.claude/skills
cp -R /tmp/fable-method/skills/fable-judge ~/.claude/skills/fable-judge

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description124 tok
When the agent uses itThe SKILL.md instructions1,222 tok
Only if opened1 bundled files (1 KB)varies

Until it is used, fable-judge costs about 11× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 5 skills from Sahir619/fable-method would load 496 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • fable-judge
  • Default mode: judge the work
  • suite mode: judge a skill or a model

More skills from Sahir619/fable-method

All skills in this repo
  1. fable-domainSahir619/fable-method

    Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain SECTOR", "make a skill for DOMAIN", "add a domain to the fable method", or "give a lesser model Fable's workflow for DOMAIN". The bundle is the deliverable; a workflow without its flowchart, sources, and trap is not done.

    2.3k113 tok idle · 2,265 in use
  2. fable-loopSahir619/fable-method

    End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.

    2.3k111 tok idle · 1,112 in use
  3. fable-methodSahir619/fable-method

    A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task that no task-specific skill covers. Subcommands - plan (stop after the plan), audit (grade finished work against the loop), report (rewrite an answer outcome-first).

    2.3k105 tok idle · 3,844 in use
  4. release-helperSahir619/fable-method

    Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.

    2.3k43 tok idle · 129 in use