ungate — security grade SAFE, quality 76/100

Security audit verdict: SAFE · quality 76/100

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 →

by orchidfiles · Claude Skill · ★ 167

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is ungate safe to install? View the security audit →

About ungate

Ungate A Cursor-first extension for using Claude, ChatGPT, and MiniMax subscriptions in Cursor instead of paying for API tokens. How it works Ungate lets you use Claude, ChatGPT, and MiniMax in Cursor through account subscriptions instead of direct API token billing. Claude and ChatGPT authenticate via OAuth; MiniMax uses provider API credentials. Cursor allows a custom OpenAI Base URL. Ungate listens on that URL and translates requests to the target provider API, including streaming, tool calls, and vision where supported. The extension manages the tunnel that makes the proxy reachable to Cursor's backend and shows its settings in a Webview panel. From there you configure providers, copy the public proxy URL, and copy the proxy API key that Cursor uses to authenticate to your local proxy. The status bar item shows separate API and

anthropicchatgptclaudeclaude-codecursorcursor-extensioncursor-idegptminimaxopenai

Quick Facts

Stars167
Forks19
LanguageTypeScript
CategoryClaude Skill
LicenseMIT
Quality Score76.2472371052153/100
Open Issues10
Last Updated2026-09-11
Created2026-03-31
Platformsclaude-code, node
Est. Tokens~15k

ungate alternative? Top 6 similar tools

Looking for a ungate alternative? If you're comparing ungate 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.

  • repopack-py by abinthomasonline · ⭐ 121

    Python version of 📦 repopack (https://github.com/yamadashy/repopack) by yamadashy (https://github.com/yamadas

  • ha-claude by Bobsilvio · ⭐ 81

    Home Assistant add-on: Claude Code, OpenAI/GPT, Gemini

  • wcgw by rusiaaman · ⭐ 674

    Shell and coding agent on mcp clients

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • notion-mcp-server by awkoy · ⭐ 171

    Notion MCP server for Claude, Cursor, ChatGPT & Claude Desktop. Connect AI agents to Notion via Model Context

  • quanta-quest by quanta-quest · ⭐ 104

    AI-powered universal search for all your personal data, tailored just for you. Goal:The world's first product

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is ungate?

ungate is Use your Claude and ChatGPT subscriptions in Cursor instead of paying for API tokens.. It is categorized as a Claude Skill with 167 GitHub stars.

What programming language is ungate written in?

ungate is primarily written in TypeScript. It covers topics such as anthropic, chatgpt, claude.

How do I install or use ungate?

You can find installation instructions and usage details in the ungate GitHub repository at github.com/orchidfiles/ungate. The project has 167 stars and 19 forks, indicating an active community.

What license does ungate use?

ungate is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to ungate?

The top alternatives to ungate on Agent Skills Hub include repopack-py, ha-claude, wcgw. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Claude Skill tools