AI Workflow Rules Generator CLI

Generate structured, controlled AI-assisted development workflows for your projects.

The Problem

AI coding assistants generate code fast — but without project rules they create:

• inconsistent coding styles
• duplicated implementations
• missing documentation
• unclear architectural decisions
• loss of project context between AI sessions

This CLI solves that by generating a controlled AI development environment tailored to your project.

What It Does

Run one command in your project:

ai-wrg-cli init

Answer a few questions about your stack and workflow. The tool generates:

Installation

Requirements: Python 3.10+

Recommended (Global CLI tool using pipx):

pipx install ai-wrg-cli

Standard pip:

On Windows, prefer a virtual environment so ai-wrg-cli is available without adding Python Scripts to PATH:

python -m venv .venv

# PowerShell
.\.venv\Scripts\Activate.ps1

# cmd
.\.venv\Scripts\activate.bat

# Git Bash
source .venv/Scripts/activate

pip install ai-wrg-cli
ai-wrg-cli --version

Without a venv, pip install --user may place the binary in %APPDATA%\Python\Python3x\Scripts, which often is not on PATH — then the command ai-wrg-cli will not be found until that folder is added to PATH or you use python -m / pipx instead.

From source (for development):

git clone https://github.com/karen6630/ai-wrg-cli.git
cd ai-wrg-cli
pip install -e ".[dev]"

Quick Start

# Initialize AI workflow in your project
ai-wrg-cli init

# Skip wizard and use defaults (great for CI or quick testing)
ai-wrg-cli init --non-interactive

# Generate into a specific directory
ai-wrg-cli init --output ./my-project

# List all available modules
ai-wrg-cli modules

# Check installation health
ai-wrg-cli doctor

Available Modules

Modules are combined to create your workflow. Run ai-wrg-cli modules to see all:

init asks for stack in four layers: Backend → Frontend → Database → DevOps (multi-select each).

How It Works

User Input (wizard or --non-interactive)
    │
    ▼
Configuration Model  (.ai-workflow/config.yaml)
    │
    ▼
Module Resolution    (dependency + conflict checks)
    │
    ▼
Generator Pipeline   (Cursor / Claude / Codex / Docs)
    │
    ▼
Generated Project Files

The internal configuration is the source of truth — generated files are always reproducible.

Project Structure

src/ai_rules/
├── cli/          # Typer commands + interactive wizard
├── core/         # Config model, generator pipeline, module resolver
├── generators/   # AI tool generators (cursor, claude, codex, docs)
├── modules/      # Module loader, registry
└── templates/    # Jinja2 templates

modules/          # Built-in modules (YAML metadata + rules.md)
├── core/
├── stacks/
│   ├── backend/    # python, php, node, django, fastapi, laravel
│   └── frontend/   # react, nextjs, vue
├── workflow/       # solo, team, ai-first
├── quality/        # standard, strict
└── tools/
    ├── database/   # sql, postgres, mysql, mongodb
    └── devops/     # docker, kubernetes

Adding a Custom Module

Create e.g. modules/stacks/backend/my-stack/module.yaml in your project root (or next to --output). The CLI loads built-in modules first, then overlays ./modules from the project directory so custom modules appear in ai-wrg-cli modules and the init stack wizard.

name: my-stack
version: "1.0"
category: stack
priority: 20
description: My custom stack rules
requires: []
conflicts: []
stack_layer: backend   # backend | frontend | database | devops
wizard_label: "My Stack"
wizard_default: false

Add rules.md with your rules, then:

ai-wrg-cli modules      # verify it appears
ai-wrg-cli init         # select it under the matching layer

Contributing

See CONTRIBUTING.md for setup, architecture overview, and contribution guidelines.

Maintainers: PyPI release — docs/development/release-pypi.md (canonical; also in AGENTS.md and .cursor/rules/).

License

MIT