# Fable Fable

Run fable-mode execution discipline on Claude Fable 5.1, the top of the escalation...

- Repository: https://github.com/mrtooher/fable-mode (882 stars)
- Category: AI and agents
- License: see repository
- Last updated: 2026-10-24
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add mrtooher/fable-mode --skill fable-fable -g -a claude-code -y`
Codex: `npx skills add mrtooher/fable-mode --skill fable-fable -g -a codex -y`
Cursor: `npx skills add mrtooher/fable-mode --skill fable-fable -g -a cursor -y`
Gemini CLI: `npx skills add mrtooher/fable-mode --skill fable-fable -g -a gemini-cli -y`

## Description

Run fable-mode execution discipline on Claude Fable 5.1, the top of the escalation ladder and the strongest staged run available. Routes the task to the @fable-orchestrator agent with its model overridden to Fable (`model: "fable"`), which stages the work, delegates artifact production to @fable-worker-sonnet / @fable-worker-haiku, and cold-checks deliverables with @fable-verifier. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on the strongest model ("fable on fable", "stage this on fable", "deep work mode, fable", "run this on 5.1"), or when a fable-opus run reports the task exceeds Opus's ceiling. Benchmarked 2026-09-02: zero correctness delta on Fable 5.1 at ~1.1× tokens, ~2× wall, a provenance runner, not an accuracy runner. Do NOT use for ordinary single-pass tasks, prefer fable-opus, fable-sonnet, or fable-haiku when the task doesn't need peak reasoning. Fable is plan-included; bulk work still routes down-tier.

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

# Fable Mode, Fable 5.1 (v3, agent-routed)

Same structural delegation as fable-opus: the orchestrator is a real agent
definition (`agents/fable-orchestrator.md`) with no Write/Edit tool, so it
cannot do the work inline. The only difference from fable-opus is the model the
orchestrator runs on. Fable 5.1 is the top of the ladder (Haiku → Sonnet → Opus
→ Fable → user); gaps it cannot close go to the user.

Fable 5.1's characteristic gaps under this discipline: none measured
(benchmarked 2026-09-02, 16 paired runs, n=2 per cell: 100/100 in every cell,
both arms; skill cost ~1.1× tokens, ~2× wall). This is a provenance runner, worklog, reproducible checks, flagged judgment calls, not an accuracy runner.
The orchestrator definition keeps the frontier-tier guards (external-artifact
verification, scope rule, replan budget) because those produce the trail.

If a task has one obvious correct approach and fits in a single pass, skip this
loop and do it directly. On a Fable-class model the stage map is ceremony for
anything short of multi-session or many-file work.

## How to run it

The rest: https://github.com/mrtooher/fable-mode/blob/HEAD/fable-fable/SKILL.md