explaingit

realgarit/fable-baton

Analysis updated 2026-05-18

21HTMLAudience · developerComplexity · 3/5LicenseSetup · easy

TLDR

A Claude Code plugin that turns the top AI model into a conductor, delegating routine coding work to cheaper Opus, Sonnet, and Haiku agents.

Mindmap

mindmap
  root((fable-baton))
    What it does
      Orchestrates AI models
      Routes work by tier
      Enforces delegation
    Tech stack
      Claude Code plugin
      Hooks
      Node.js
    Use cases
      Save top model quota
      Consistent session policy
      Automated delegation
    Audience
      Developers
      Claude Code users
    Setup
      Plugin marketplace install
      Setup skill
      MIT license

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Keep a premium AI model available longer in a session by routing routine edits and file reading to cheaper models.

USE CASE 2

Enforce a consistent delegation pattern across every coding session in every repository automatically.

USE CASE 3

Reduce how often a subscription plan's top-tier model quota runs out and forces a downgrade mid session.

What is it built with?

Claude CodeNode.jsHooksAnthropic API

How does it compare?

realgarit/fable-batonhurapanda/cheesjenniferzhao0531/icml2026-guide-cn
Stars212121
LanguageHTMLHTMLHTML
Setup difficultyeasyeasyeasy
Complexity3/52/52/5
Audiencedevelopergeneralresearcher

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 5min

Requires a Claude subscription or API access that includes Fable 5, otherwise it falls back to Opus.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

In plain English

fable-baton is a plugin for Claude Code, the command line coding assistant from Anthropic. It changes how work gets split up during a coding session. Instead of one AI model doing every step itself, from reading files to writing code to checking the result, the plugin turns the top model, called Fable 5, into a conductor that hands off routine work to cheaper models underneath it. The plugin sets up four roles. A scout, running on the smaller Haiku model, handles discovery work like reading files and logs and writing summaries. An executor, running on Sonnet, handles scoped implementation such as tests and routine edits. An architect, running on Opus, takes on complex implementation, deep debugging, and reviewing what the cheaper agents produced. A verifier, also on Haiku, checks that tests pass and that changes match the plan. Fable itself is meant to stay focused on judgment and planning rather than doing the hands on labor. The project uses three layers of hooks to keep this pattern in place through a session: one that loads the policy when a session starts, one that reminds the model of the delegation rules on every new prompt, and one that counts consecutive inline tool calls and nudges the model to delegate once a threshold is crossed. The author ran a small benchmark comparing sessions with the plugin on and off, and found that total dollar cost stayed about the same or sometimes rose slightly, but the top model's own share of the work and tokens dropped noticeably. The stated benefit is for people on a subscription plan where running out of access to the top model triggers an automatic downgrade mid session, since delegating cheaper work keeps that top model available longer for the judgment calls it is best suited for. Installation is done from inside a Claude Code session using plugin marketplace commands, followed by a setup step that configures the default model. It requires Claude Code with plugin support and access to Fable 5, falling back to Opus if that is unavailable. It is released under the MIT license.

Copy-paste prompts

Prompt 1
Set up fable-baton in my Claude Code environment and explain what each of the four agent tiers does.
Prompt 2
Show me how the SessionStart, UserPromptSubmit, and PostToolUse hooks work together in fable-baton.
Prompt 3
Walk me through the benchmark numbers in fable-baton's README and explain what they mean for cost versus quota.
Prompt 4
Help me adjust the FABLE_BATON_TRIPWIRE threshold and explain what tradeoff that changes.

Frequently asked questions

What is fable-baton?

A Claude Code plugin that turns the top AI model into a conductor, delegating routine coding work to cheaper Opus, Sonnet, and Haiku agents.

What language is fable-baton written in?

Mainly HTML. The stack also includes Claude Code, Node.js, Hooks.

What license does fable-baton use?

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

How hard is fable-baton to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is fable-baton for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.