Fable Advisor: Multi-Model Orchestration for Claude Code

RepositoryDannyMac180/fable-advisorTool

Fable Advisor is a Claude Code plugin implementing an architect pattern where Fable 5.1 handles planning, specifications, and reviews, while GPT-5.6 Luna and Sol generate the actual code.

Key points

  1. Architect Pattern: Fable 5.1 runs the primary session, handling requirements, task decomposition, specifications, and verification.
  2. Dedicated implementation lanes: Routine coding routes to GPT-5.6 Luna (codex-implementer), while complex edge cases route to GPT-5.6 Sol (sol-implementer).
  3. Dynamic reasoning effort: Each task specification defines reasoning effort levels from 'low' to 'ultra' based on complexity.
  4. Cross-vendor review: A clean-context Fable 5.1 subagent validates all accumulated changes before completion.
  5. Token efficiency: High-tier models produce architecture and judgment while external subagents handle the high-volume typing.

Why it matters

Single-agent coding setups often suffer from context bloat and high costs. Fable Advisor demonstrates how multi-vendor workflows can split responsibilities, leveraging separate model families for implementation and critical review.

Analysis

The project solves common trade-offs in agentic coding by separating the architect role from typing code. Fable 5.1 governs specs and final quality gates, while GPT-5.6 models handle execution via the Codex CLI. Its six-part spec contract enables context-free delegation, keeping implementation lanes lean and deterministic. With over 1,000 GitHub stars and an MIT licence, the project presents a well-structured orchestration skill designed specifically for developers using Claude Code alongside OpenAI Codex integrations.

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Repository:chhoumann/t3-pstack

    t3-pstack: Multi-Model Orchestration for Coding Agents

    t3-pstack adapts Lauren Tan's pstack and Michael Denyer's pstack-claude for T3 Code, dispatching subagents, review panels, and fan-outs across Claude, GPT, and Grok via T3's MCP tools.

    172starsJavaScript

    AI & LLMs· Tool

  • Repository:chaseai-yt/claudex-loop

    claudex-loop: Adversarial Plan Hardening for Claude Code and OpenAI Codex

    claudex-loop is a Claude Code skill and plugin that hardens development plans before any code is written. By placing Claude and OpenAI Codex into an adversarial cycle, competing models inspect and challenge specifications to prevent architectural flaws.

    1.6kstars

    AI & LLMs· Tool

  • Repository:promptadvisers/claudex

    claudex: Autonomous Claude and Codex review loop for software planning

    claudex links Claude Code and Codex into an automated terminal loop. Claude creates development plans from short prompts, while Codex reviews them across multiple rounds covering architecture, security, and operations before Claude revises.

    119starsShell

    AI & LLMs· Tool

  • Repository:smarzban/pi-review-panel

    pi-review-panel: Multi-Model Code Review Panel for Pi Coding Agents

    pi-review-panel is a TypeScript extension for Pi coding agents that coordinates multi-model code reviews across pinned Git snapshots. It explicitly avoids automated merge verdicts, focusing instead on structured, actionable findings.

    16starsTypeScript

    AI & LLMs· Tool

  • Repository:DanMcInerney/orchflows

    orchflows: Reusable AI Agent Workflows Defined in Markdown

    orchflows is a Python utility for designing and orchestrating reusable multi-agent workflows within subagent-capable environments like Claude Code or Codex.

    119starsPython

    AI & LLMs· Tool

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.