claude-skill

vnx-orchestration

Name: vnx-orchestration
Author: Vinix24

Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality gates, and full provenance.

62 stars8 forksPythonUpdated 10/23/2026100% free · open source

What it does

Vnx-orchestration provides governance-first orchestration for Claude Code, Codex, and Gemini CLI, enabling features like parallel workers, receipts, quality gates, and full provenance for AI workflows

When to use it

•When you need to manage complex AI workflows involving multiple tools like Claude Code, Codex, and Gemini CLI
•When you require full provenance and quality gates for your AI workflows
•When you want to leverage parallel workers to speed up your AI workflow execution

Ready-to-paste prompt

Create a new workflow that uses Claude Code to generate text, then uses Codex to fine-tune the model: `vnx-orchestration create-workflow my-workflow --steps claude-code,codex`

Heads up: Make sure you have the necessary API keys and credentials for Claude Code, Codex, and Gemini CLI configured in the `config.json` file before running the orchestrator

Saves to your device

Use with Claude

New

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

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/vnx-orchestration && curl -fsSL https://workflowstacks.com/api/skills/vnx-orchestration/claude-skill -o ~/.claude/skills/vnx-orchestration/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 vnx-orchestration works

Codeflow

Free to inspect

Vnx-orchestration is a very large Python project (~454k lines across 1209 code files, plus 1597 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size

Very large codebase

~454k lines · 1209 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Python

No API keys detected

Python 93%Shell 4%TypeScript 2%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
CLAUDE.md
The instructions the AI actually follows
3
bin/vnx
Where the program starts running
4
pyproject.toml
Dependencies and the commands it exposes
5
skills/README.md
Inside skills/ — an example of what the AI is told to do

What's in each folder

skills/Prompts, skills & agent definitions88 files

agents/Prompts, skills & agent definitions23 files

lib/Core code — the actual logic2 files

packages/Sub-packages / plugins159 files

bin/Command-line entry points1 files

docs/Documentation234 files

templates/Templates25 files

samples/Examples you can copy5 files

READMEHas testsDocumentedCI checksExamples includedMIT licenseUpdated this month