explaingit

tomascupr/sous-chef

Analysis updated 2026-05-18

65ShellAudience · developerComplexity · 3/5LicenseSetup · moderate

TLDR

A Claude Code plugin where one AI model plans and reviews coding tasks while a second model, like Codex CLI or GLM, does the actual implementation.

Mindmap

mindmap
  root((sous-chef))
    What it does
      Plans tasks
      Reviews diffs
      Delegates coding work
    Tech stack
      Claude Code
      Codex CLI
      GLM
    Use cases
      Automated implementation
      Loop until tests pass
      Second opinion review
    Audience
      Developers
      AI tool builders
    Setup
      Codex CLI required
      ChatGPT subscription

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

Automate multi-step coding tasks where one model plans and reviews while another writes the code.

USE CASE 2

Keep a goal-shaped task looping until tests pass, with an independent model judging each attempt.

USE CASE 3

Get a second AI model's code review before merging a change.

What is it built with?

ShellClaude CodeCodex CLIGLM

How does it compare?

tomascupr/sous-chefnikvpn-iran/nikvpn-codespacefilipedeschamps/dotfiles
Stars656567
LanguageShellShellShell
Last pushed2025-04-23
MaintenanceStale
Setup difficultymoderateeasymoderate
Complexity3/52/52/5
Audiencedevelopergeneraldeveloper

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

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires Codex CLI 0.134 or higher, signed in with a ChatGPT subscription.

Use, modify, and distribute freely, including for commercial projects, as long as you keep the copyright notice (MIT license).

In plain English

sous-chef is a Claude Code plugin that splits coding work between two AI models, the way a kitchen splits work between a head chef and a line cook. One model, the head chef, plans the task, writes out what needs to be done, and reviews every change line by line. Another model, the worker, does the actual implementation and has no say in what ships. The plugin is built around Claude models for planning and review, while Codex CLI (a separate coding tool made by OpenAI) or GLM models handle the implementation. The plugin offers two main commands. The first, called serve, is for tasks that are clearly scoped: it writes a ticket describing the work, sends it to the implementer, reviews the resulting change, fixes any problems found, and verifies the result, all within a limited number of implementation runs. The second, called simmer, is meant for open-ended goals, such as making all the tests pass. It repeats the implement-and-check cycle until the goal is met, with limits on how many attempts it will make and a check for when no more progress is happening. There are also more manual commands for people who want finer control: one to write a ticket and run a single implementation pass, one to run a review without making any changes, one to turn confirmed review findings into a scoped fix, and one for first-time setup, which checks that Codex CLI is installed and logged in. To use the plugin, a person needs Codex CLI version 0.134 or higher, signed in with a ChatGPT subscription rather than a separate API key. Installation happens through the Claude Code plugin marketplace command, followed by a one-time setup command run inside the target repository. The project explains its design choices by pointing to specific incidents, including a case where a polling loop against a background job used up a large share of a weekly usage quota without producing results, and a test run where several AI-generated reviews turned out to be wrong. The license is MIT, so the code can be used, modified, and shared freely, including in commercial projects.

Copy-paste prompts

Prompt 1
Set up sous-chef in my repo and walk me through the mise setup command.
Prompt 2
Use sous-chef's serve command to implement this ticket end to end and review the diff before it ships.
Prompt 3
Run sous-chef's simmer command to keep looping on this failing test suite until it's green.
Prompt 4
Explain the difference between sous-chef's serve and simmer commands so I know which one to use.

Frequently asked questions

What is sous-chef?

A Claude Code plugin where one AI model plans and reviews coding tasks while a second model, like Codex CLI or GLM, does the actual implementation.

What language is sous-chef written in?

Mainly Shell. The stack also includes Shell, Claude Code, Codex CLI.

What license does sous-chef use?

Use, modify, and distribute freely, including for commercial projects, as long as you keep the copyright notice (MIT license).

How hard is sous-chef to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is sous-chef for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.