by YunTaiHua · Codex Skill · ★ 58
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Illusion-Agent: Where fantasy meets functionality — an AI agent platform for terminal, browser, any model, any OS.
| Stars | 58 |
| Forks | 8 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 58.6294602812054/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-14 |
| Created | 2026-04-06 |
| Platforms | browser, claude-code, codex, gemini, python |
| Est. Tokens | ~13k |
Looking for a illusion-agent alternative? If you're comparing illusion-agent with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
MCP-X 是一个**企业级 AI 中台**，集成了 AI 对话、文案生成、视频生成、图片生成、前端应用构建、MCP市场、Agent智能体等多种创作工具，为企业和开发者提供一站式的 AIGC 工作台解决方案。
开源OpenClaw中文文档站，OpenClaw中文指南，支持小龙虾 AI 智能体安装部署、消息渠道接入、Agent 架构、Skills 技能配置、模型提供商、CLI 命令参考、网关运维、安全沙箱等全方位文档。覆盖 Wh
助力搭建你的数字 AI 员工军团 — 多 Agent 一行命令组网协作。Claude Code / Claude Agent SDK / Codex / Grok Build 4 runtime + 8+ 家 LLM（A
轻量级的clawdbot/openclaw，支持飞书，钉钉，QQ和企业微信
Bridgic is the next-generation agent development framework for building intelligent systems.
Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, sear
Explore other popular codex skill tools:
illusion-agent is Illusion-Agent: Where fantasy meets functionality — an AI agent platform for terminal, browser, any model, any OS.. It is categorized as a Codex Skill with 58 GitHub stars.
illusion-agent is primarily written in Python. It covers topics such as agent, ai, claude.
You can find installation instructions and usage details in the illusion-agent GitHub repository at github.com/YunTaiHua/illusion-agent. The project has 58 stars and 8 forks, indicating an active community.
illusion-agent is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to illusion-agent on Agent Skills Hub include MCP-X-web, openclaw-guide, agent-network. 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: