Flagged: reads sensitive env vars. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by ruvnet · Claude Skill · ★ 510
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is open-claude-code safe to install? View the security audit →
Open Claude Code Open Source Claude Code CLI — Reverse Engineered & Rebuilt A fully functional open source implementation of Anthropic's Claude Code CLI, built from decompiled source intelligence using ruDevolution. Automated Nightly Releases — Open Claude Code automatically detects new Claude Code releases, runs 903+ tests to verify zero regressions, and publishes verified builds with AI-powered discovery analysis. See Releases pi.ruv.io ⚡ Quick Start bash Run instantly (no install) npx @ruvn
| Stars | 510 |
| Forks | 165 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 70.5735009047346/100 |
| Open Issues | 7 |
| Last Updated | 2026-10-03 |
| Created | 2025-02-24 |
| Platforms | claude-code, cli, node |
| Est. Tokens | ~15k |
Looking for a open-claude-code alternative? If you're comparing open-claude-code with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Automate Ghidra reverse engineering from the command line — headless analysis, decompilation, and structured J
Supports GPT Image 2, Seedance & ComfyUI, with a 1,400+ prompt library, carefully crafted hooks and a multi-ta
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou
A curated list of Plugins that let you extend Claude Code with custom commands, agents, hooks, and MCP servers
MCP server for Apple Developer Documentation - Search iOS/macOS/SwiftUI/UIKit docs, WWDC videos, Swift/Objecti
A Model Context Protocol (MCP) server that enables secure interaction with MySQL databases
Explore other popular claude skill tools:
open-claude-code is Nightly Claude Code CLI Decompile — Reverse Engineered & Rebuilt. It is categorized as a Claude Skill with 510 GitHub stars.
open-claude-code is primarily written in JavaScript. It covers topics such as claude-code, clean-room, clean-room-reimplementation.
You can find installation instructions and usage details in the open-claude-code GitHub repository at github.com/ruvnet/open-claude-code. The project has 510 stars and 165 forks, indicating an active community.
open-claude-code is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to open-claude-code on Agent Skills Hub include ghidra-cli, MeiGen-AI-Design-MCP, vllm-mlx. 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: