sneg55/agent-starter

README preview

# agent-starter

[![License](https://img.shields.io/github/license/sneg55/agent-starter)](LICENSE)
[![CI](https://github.com/sneg55/agent-starter/actions/workflows/ci.yml/badge.svg)](https://github.com/sneg55/agent-starter/actions/workflows/ci.yml)
[![Stars](https://img.shields.io/github/stars/sneg55/agent-starter)](https://github.com/sneg55/agent-starter/stargazers)
![Claude Code](https://img.shields.io/badge/Claude%20Code-D97757?logo=claude&logoColor=fff)
![Bash](https://img.shields.io/badge/Bash-4EAA25?logo=gnubash&logoColor=fff)
![Python](https://img.shields.io/badge/Python-3776AB?logo=python&logoColor=fff)

Skills, hooks, templates, and engineering guides for bootstrapping AI-agent-friendly projects, with a per-project self-improvement loop.

## What it is

A toolkit for setting up projects that AI agents can work in safely and productively. It scaffolds new projects, retrofits existing ones, and ships enforcement hooks, drop-in configs, and engineering patterns. The differentiator is the [self-improvement loop](#the-self-improvement-loop): scaffolded projects capture signal from their own usage and turn it into better rules over time.

| Component | What it does | Where |
|-----------|--------------|-------|
| **Skills** | 8 slash commands: scaffold, adopt, commit, reflect, remember, dream | [`skills/`](skills/) |
| **Hooks** | Enforcement (lint, file-size, dangerous-command) + signal capture for the loop | [`hooks/`](hooks/) |
| **Templates** | Drop-in configs: Biome, ESLint, ruff, pyright, `CLAUDE.md`, env boundaries | [`templates/`](templates/) |

View full repository on GitHub →