No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is maggy safe to install? View the security audit →
Maggy From Claude Bootstrap to autonomous AI engineering. This project started as Claude Bootstrap — an opinionated set of skills, hooks, and rules for Claude Code. Over time it grew into something much bigger: a multi-model routing system, a persistent memory layer, an intent-tracking code graph, container-based orchestration, and a full engineering command center. The bootstrap scaffolding is still here, but the future of this project is Maggy — an autonomous engineering system that routes work across AI models, learns from outcomes, and manages the full development lifecycle. 62 skills, TDD enforcement via Stop hooks, agent teams, persistent memory (Mnemos), intent tracking (iCPG), and multi-model AI command center. Works with Claude Code, Kimi CLI, and OpenAI Codex CLI. Quick Start Claude will validate tools, ask about your stack, create the repo structure, copy skills/rules/hooks, and spawn an agent team. Maggy — Autonomous Engineering System Maggy is the core of this project. It routes tasks across models, tracks performance, learns from outcomes, and manages the full development lifecycle from a local dashboard or CLI REPL.
| Stars | 707 |
| Forks | 57 |
| Language | Python |
| Category | AI Skill |
| License | MIT |
| Quality Score | 64.7246304118577/100 |
| Last Updated | 2026-09-24 |
| Created | 2025-12-26 |
| Platforms | claude-code, python |
| Est. Tokens | ~14k |
These tools work well together with maggy for enhanced workflows:
Looking for a maggy alternative? If you're comparing maggy with other ai skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Release channel for TheAuditor — see blog.theauditortool.com
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
Universal development automation for ANY project. Claude Code implements features, runs tests, creates PRs aut
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Explore other popular ai skill tools:
maggy is What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center. It is categorized as a AI Skill with 707 GitHub stars.
maggy is primarily written in Python. It covers topics such as ai-coding, claude, claude-code.
You can find installation instructions and usage details in the maggy GitHub repository at github.com/alinaqi/maggy. The project has 707 stars and 57 forks, indicating an active community.
maggy is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to maggy on Agent Skills Hub include Overture, Auditor, orchestkit. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: