AndyShaman/senior-fable
14 stars · Last commit 2026-07-02
Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.
README preview
<h1 align="center">Senior Fable</h1> <p align="center"> <em>The expensive model decides. The cheap models type.</em> </p> <p align="center"> <img src="https://img.shields.io/badge/Claude%20Code-plugin-111111?style=flat-square" alt="Claude Code plugin"> <img src="https://img.shields.io/github/v/release/AndyShaman/senior-fable?style=flat-square&color=111111" alt="Release"> <img src="https://img.shields.io/badge/license-MIT-111111?style=flat-square" alt="MIT license"> </p> **Senior Fable** is a Claude Code plugin that turns your top-tier model (Claude Fable 5) into a **tech lead**: it keeps decomposition, architecture, contested decisions and final synthesis — and delegates everything else to cheaper subagents. Mechanical work goes to a Sonnet **fast-worker**, long context-heavy investigations go to a read-only Opus **deep-reasoner**, and risky decisions get a second opinion from **Codex** (if installed). The result: your most expensive tokens are spent only where top-tier judgment actually matters, while routine execution and codebase digging run on models that cost a fraction. Token savings without quality loss — and often with quality *gains*, because the messy exploration stays out of the main context window. ## Why Running a frontier model on boilerplate is like having your staff engineer format JSON. Two things are wasted: