U-Pool — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

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 U-C4N · Claude Skill · ★ 297

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

🔒 Is U-Pool safe to install? View the security audit →

About U-Pool

U-Pool Provider switcher for Claude Code and Codex. Keep every endpoint, API key, and model in one place. Switch the active provider with a click. Probe reachability before you start working. Python backend · Next.js UI · native OS webview — no Electron, no Node at runtime. Screenshot Why U-Pool? Switching between Anthropic, OpenRouter, DeepSeek, Azure, xAI, and custom relays usually means editing config files by hand. U-Pool turns that into a desktop app: One list of providers for Claude Code and Codex One click to make a provider live — in the config file and in the Windows environment the CLIs read Health checks that measure latency without spending tokens Atomic writes, and a backup beside every file U-Pool c

ai-toolsapi-key-managementclaude-codecodexdeepseekdesktop-appdeveloper-toolsllm-toolsnextjsopenrouter

Quick Facts

Stars297
Forks3
LanguagePython
CategoryClaude Skill
Quality Score64.6671066730939/100
Open Issues2
Last Updated2026-08-07
Created2026-07-25
Platformsbrowser, claude-code, cli, codex, python
Est. Tokens~16k

Compatible Skills

These tools work well together with U-Pool for enhanced workflows:

  • claude-overlay — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)

U-Pool alternative? Top 6 similar tools

Looking for a U-Pool alternative? If you're comparing U-Pool 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.

  • LoongPort by SailingLoong · ⭐ 138

    cc-switch 中转站的专用增强版(cc-switch for API relay providers),免去配置各种 密钥 endpoint 的烦恼。

  • code-on-incus by mensfeld · ⭐ 726

    Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops t

  • Overture by SixHq · ⭐ 630

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

  • palot by ItsWendell · ⭐ 187

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

  • mcp-gearbox by rohitsoni007 · ⭐ 62

    A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents

  • SWE-AF by Agent-Field · ⭐ 993

    Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is U-Pool?

U-Pool is Desktop provider switcher for Claude Code and Codex. Keep every endpoint, API key, and model in one place, switch the active provider in one click, and probe latency before you start. Atomic writes an. It is categorized as a Claude Skill with 297 GitHub stars.

What programming language is U-Pool written in?

U-Pool is primarily written in Python. It covers topics such as ai-tools, api-key-management, claude-code.

How do I install or use U-Pool?

You can find installation instructions and usage details in the U-Pool GitHub repository at github.com/U-C4N/U-Pool. The project has 297 stars and 3 forks, indicating an active community.

What are the best alternatives to U-Pool?

The top alternatives to U-Pool on Agent Skills Hub include LoongPort, code-on-incus, Overture. 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