# Fable

> Run ONE hard reasoning/planning task on Fable 5 as a subagent, without leaving your current (Opus/Sonnet) seat. Use when you're on a cheaper model mid-session and hit a problem that genuinely needs frontier judgment — a subtle design call, a deep analysis, a strategic tradeoff — and want Fable's depth on just that piece. The main loop stays on the cheap model; only this one sub-task runs at Fable rates; only its distilled answer returns to context. Triggers - "fable this", "reason this on fable", "run this on fable", "/fable", "fable-reason".

- Skill: `rishbjain1/fable` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rishbjain1/fable`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rishbjain1/fable/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: rishbjain1 (https://skillmd.com/u/rishbjain1)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rishbjain1/fable

---


# /fable — one hard reasoning call on Fable, from any seat

You are (probably) on Opus/Sonnet. A skill does not switch your model. To get
Fable's judgment on one piece **without switching your whole session to Fable**,
delegate that piece to a Fable subagent and stay put.

## How to run

1. **Seat check.** If the current main-loop model is *already Fable*, just answer
   in-chair — no subagent needed. Otherwise continue.

2. **Spawn ONE `Agent` with `model: fable`.** Give it the **context floor** — it
   starts blank, so pass everything it needs to reason well:
   - the exact problem/question,
   - the relevant conversation context, constraints, and any decisions already made,
   - what a good answer looks like (the decision to make, options on the table,
     the tradeoff axis),
   - instruction to **return a distilled answer** — the conclusion + the key
     reasoning, not a raw think-aloud dump.

3. **Relay** the subagent's answer to the user. Add your own one-line framing only
   if it helps; don't re-reason it on the cheap seat (that defeats the point).

## When NOT to use

- **Iterative, multi-round hard thinking** — a single subagent call is one-shot.
  If you need several rounds of pushing on it, launch the `fable` seat instead
  (the `fable` shell alias) and work there.
- **Mechanical / light work** — that's haiku/sonnet, not Fable. Don't burn Fable
  rates on extraction, sweeps, or drafting.
- **A whole mixed task** — use `manager` (it routes each piece, escalating to a
  Fable subagent only for the frontier parts).

## Cost note
Main seat pays only for: writing the brief + reading the distilled answer. Fable
pays only for the reasoning itself. Strictly cheaper than sitting on Fable for the
session, and you keep Fable-tier depth on the part that needs it. Pairs with
the `manager` skill and a review-loop's planning phase,
which use the same fable-subagent-from-any-seat mechanism.