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:
| Output | Description |
|---|---|
.cursor/rules/ |
Cursor IDE rules |
.claude/instructions.md |
Claude Code instructions |
.codex/instructions.md |
OpenAI Codex instructions |
.agents/rules/ |
Google Antigravity / Gemini workspace rules |
docs/ |
Documentation structure templates |
.ai-workflow/config.yaml |
Reproducible workflow configuration |
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:
| Category | Name | Description |
|---|---|---|
core |
core |
Base AI collaboration rules |
stack |
python, php, node, django, fastapi, laravel |
Backend languages / frameworks |
stack |
react, nextjs, vue |
Frontend |
tool |
sql, postgres, mysql, mongodb |
Database |
tool |
docker, kubernetes |
DevOps |
workflow |
solo, team, ai-first |
Workflow styles |
quality |
standard, strict |
Quality gates |
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
Metadata
Release files for ai-wrg-cli 0.2.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ai_wrg_cli-0.2.5.tar.gz | 74.0 kB | Without provenance | Details for ai_wrg_cli-0.2.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ai_wrg_cli-0.2.5-py3-none-any.whl | Python 3 | none | any | Details for ai_wrg_cli-0.2.5-py3-none-any.whl |
Total release size: 151.2 kB
Release files / ai_wrg_cli-0.2.5.tar.gz
| Download URL | ai_wrg_cli-0.2.5.tar.gz |
|---|---|
| Size | 74.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9db21b0bc216b54451e8876e83d74b200db12f842034d1afbac66fd1c92d89da
|
|
BLAKE2b-256 checksum How to use checksums |
ee3e74335592080a5a8abf59a0ad1faa46478f9f4d124f7fb64ca27a4f937482
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.2
|
Release files / ai_wrg_cli-0.2.5-py3-none-any.whl
| Download URL | ai_wrg_cli-0.2.5-py3-none-any.whl |
|---|---|
| Size | 77.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
51794f6ec881be3e6a78c110a01d6875b9b0c2fc36b5cd606bf16c347796c909
|
|
BLAKE2b-256 checksum How to use checksums |
f5e79b94aba65a51b4f0d053fde31c3e269387f06d27e46b3ecdafe1bcf64127
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.2
|
Security for ai-wrg-cli 0.2.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.