Why it is worth attention

It enables multi-model orchestration within Codex, allowing users to bring in external models like Claude Fable 5 for distinct planning and review roles, with automated workflow gating and potential parallel execution for faster results.

Who it is for

Developers using Codex who want stronger planning before code generation
Teams seeking to leverage different AI models for specialized roles in a single workflow
Users looking to reduce premium-model API limits by offloading work to cheaper executors

Use cases

Creating a plan with Claude Fable 5, reviewing with GPT-5.6 Sol, then implementing with Luna
Running parallel executor tasks to speed up implementation of independent subtasks
Setting up a repeatable workflow that automatically applies model roles to new Codex tasks

Strengths

Modular role separation (Planner, Advisor, Executor) with clear safety gates and a 5-review limit
Ability to bring external models like Claude Fable 5 into Codex without extra API keys
Potential up to 2x faster execution through parallel executors and 40% less premium-model limit usage

Considerations

Codex remains the root orchestrator; the plugin cannot override Codex's permissions or delegation decisions
Requires compatible models and providers; Fable 5 is the only bundled cross-provider model
Performance and speed gains depend on the task, models, context, and retries; not guaranteed

README quick start

Codex Orchestration

Bring models like Claude Fable 5 and Claude Opus 5 into Codex, give each model a role, and let Codex coordinate the work.

What is it?

Codex Orchestration adds four simple roles to a Codex task:

Planner creates the plan and improves it after feedback. It is optional; when omitted, your current Codex model plans.
Advisor reviews the plan, finds important gaps, and approves it when it is ready. It is optional.
Designer turns approved requirements into a bounded visual, UX, interaction, information-architecture, or design-system handoff. It is optional.
Executor implements the approved plan. It is required for setup.

The model selected for the Codex task remains in charge. It passes work between the roles, checks every result, and gives you the final answer.

How it works

                         YOUR TASK
                             |
                             v
                  CODEX COORDINATES THE WORK
                             |
                             v
               PLANNER CREATES THE FIRST PLAN
              Fable 5, another model, or Codex
                             |
                             v
                    ADVISOR REVIEWS IT
                       finds real gaps
                             |
                   needs work? -- yes --+
                             |            |
                            no            v
                             |      PLANNER IMPROVES IT
                             |            |
                             +, advisor: , designer: , executor:

Omit planner to use the current Codex model as Planner.
Omit advisor when you do not want plan review.
Omit designer when you do not need a separate design handoff.
executor is required.
Planner and Advisor must use different configured model routes so the review is independent.

Role labels are literal. A model after planner: plans; a model after advisor: reviews; a model after designer: designs; a model after executor: implements. Codex must never move a model to a different role because that model was used differently in an older plugin version. If you omit Designer, the workflow has no Designer. If you specify Planner and Executor but omit Advisor, the workflow has no Advisor.

When every requested route is ready in the current task, the plugin c

Description

Bring any model to Codex, assign them any role, use them in /goal or any workflow.

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo

Featured

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents

2,390

slvDev

Featured

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models

1,960

littledivy

Featured

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning

1,482