UniCli — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

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 yucchiy · Agent Tool · ★ 251

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

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

About UniCli

UniCli A command-line interface for controlling Unity Editor from the terminal. UniCli lets you compile scripts, run tests, manage packages, inspect GameObjects, and more — all without leaving your terminal. Designed to work with AI coding agents such as Claude Code, UniCli gives AI the ability to interact with Unity Editor directly through structured CLI commands with JSON output. 80+ built-in commands: compile, test, build, inspect GameObjects, manage scenes/prefabs/packages, and more Dynamic C# execution: run arbitrary C# code in Unity via Extensible: add custom commands with a single C# class AI-agent ready: structured JSON output, Claude Code plugin, and Agent Skills support Cross-platform: NativeAOT binaries for macOS (arm64/x64), Linux (x64), and Windows (x64) Table of Contents Getting Started Requirements CLI Unity Package Quick Usage CLI Usage Project Discovery Executing Commands Parameter syntax Common options Examples [Dynamic Code Execution

ai-agentscommand-lineunity

Quick Facts

Stars251
Forks26
LanguageC#
CategoryAgent Tool
LicenseMIT
Quality Score71.0181597801091/100
Open Issues7
Last Updated2026-09-04
Created2026-02-11
Platformscli, dotnet
Est. Tokens~27k

UniCli alternative? Top 6 similar tools

Looking for a UniCli alternative? If you're comparing UniCli with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • mcp-cli by apify · ⭐ 459

    mcpc is a CLI client for MCP. It supports persistent sessions, stdio/HTTP, OAuth 2.1, JSON output for code mod

  • runprompt by chr15m · ⭐ 443

    Run LLM prompts from your shell

  • notion-cli-agent by Balneario-de-Cofrentes · ⭐ 88

    Notion CLI with AI agent support. Smart queries, Obsidian sync, batch ops, backups, validation and more.

  • cheatengine-mcp-bridge by miscusi-peek · ⭐ 1.2k

    Connect Cursor, Copilot & Claude AI directly to Cheat Engine via MCP. Automate reverse engineering, pointer sc

  • MCPJungle by mcpjungle · ⭐ 1.2k

    One place to manage & connect to all your MCP servers

  • claude-codex-settings by fcakyon · ⭐ 1.2k

    Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular C# Agent Tools

Frequently Asked Questions

What is UniCli?

UniCli is A CLI tool to control Unity Editor - enabling both humans and AI agents to run compilations, tests, and editor commands from the terminal.. It is categorized as a Agent Tool with 251 GitHub stars.

What programming language is UniCli written in?

UniCli is primarily written in C#. It covers topics such as ai-agents, command-line, unity.

How do I install or use UniCli?

You can find installation instructions and usage details in the UniCli GitHub repository at github.com/yucchiy/UniCli. The project has 251 stars and 26 forks, indicating an active community.

What license does UniCli use?

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

What are the best alternatives to UniCli?

The top alternatives to UniCli on Agent Skills Hub include mcp-cli, runprompt, notion-cli-agent. 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 Agent Tool tools