automation

Codex Workflow

A swarm orchestration system in Codex, drastically reduce overall token usage.
332 stars27 forksPythonUpdated 8/13/2026100% free · open source
What it does

Codex_workflow is a swarm orchestration system that helps reduce overall token usage in Codex by managing and optimizing AI workflows

When to use it
  • When you need to automate repetitive AI tasks in Codex
  • When you want to minimize token usage while running multiple AI workflows
  • When you need to integrate Codex with other tools and services in your workflow
Ready-to-paste prompt
Run a sample workflow using `python workflow.py --task sentiment-analysis --num-tokens 100`
Heads up: Make sure you have a valid Codex API key and have installed the required Python dependencies, including `transformers` and `torch`, before running Codex_workflow
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/codex-workflow && curl -fsSL https://workflowstacks.com/api/skills/codex-workflow/claude-skill -o ~/.claude/skills/codex-workflow/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Codex Workflow works
Codeflow
Free to inspect

Codex Workflow is a medium Python project (~6k lines across 19 code files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit this month, no license file, has a test suite.

Size
Medium codebase
~6k lines · 19 code files · 50 min skim
Setup
Some technical setup
Comfortable with a terminal? 20–40 min. Otherwise ask a dev.
Runs on
Python
No API keys detected
Python 100%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    codex_workflow/runtime/__init__.py
    Inside codex_workflow/ — the main logic begins here
What's in each folder
codex_workflow/Core code — the actual logic45 files
docs/Documentation4 files
light_benchmark/Folder6 files
scripts/Helper scripts3 files
.github/CI / automation (GitHub Actions)1 files
READMEHas testsDocumentedCI checksNo licenseUpdated this month
Quick Actions
Details
Creator
viettran-edgeAI
Language
Python
Category
automation
Published
7/23/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.