CatDesk — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

Flagged: opens a tunnel service. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Xeift · Codex Skill · ★ 167

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

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

About CatDesk

CatDesk An open-source tool that turns ChatGPT Web into a coding agent. No reverse engineering, no API, no Codex. A ChatGPT Plus subscription is enough. CatDesk in ChatGPT Web Disclaimer This is an independent open-source project and is not affiliated with or endorsed by OpenAI. I built it as a personal tool and decided to open-source it. Some features are still buggy and may cause unexpected behavior. Use it at your own risk. I am not responsible for any loss caused by this tool. It is strongly recommended to run it inside a VM or container. Why CatDesk? Codex has a very generous weekly quota (2x usage + reset usage frequently) compared to Antigravity and Claude Code (3 Opus prompts then 5h quota is gone lol), that's why I love OpenAI so much. Codex reset usage frequently🙏 However, the quota runs out very quickly if you work on a large project. I used up my Codex quota on the first day after it reset Then you need to wait another 7 days. What are you going to do for the rest of the week? Here's the solution: most people with a Plus subscription do not use

Quick Facts

Stars167
Forks40
LanguageRust
CategoryCodex Skill
LicenseMIT
Quality Score64.2521188799852/100
Open Issues4
Last Updated2026-09-25
Created2026-03-18
Platformscodex, rust
Est. Tokens~26k

Compatible Skills

These tools work well together with CatDesk for enhanced workflows:

  • revula — semantic(0.31)+complementary+similar_pop (46%)

CatDesk alternative? Top 5 similar tools

Looking for a CatDesk alternative? If you're comparing CatDesk with other codex skill tools, these 5 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • ai-maestro by 23blocks-OS · ⭐ 820

    AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen

  • upskill by huggingface · ⭐ 750

    Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex

  • skills by wlzh · ⭐ 675

    开源了Codex Skills等集合,大部分是自己实际需要搞得,需要的自取。欢迎star

  • solana-dev-skill by solana-foundation · ⭐ 572

    Skills for agentic development on Solana

  • theorist by blader · ⭐ 191

    A Codex/Claude skill that maintains per-repo operating theory documents.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is CatDesk?

CatDesk is An open-source tool that lets you use ChatGPT Chat as a local coding agent. No reverse engineering, no API, no Codex, no Work mode. A ChatGPT Plus subscription is enough.. It is categorized as a Codex Skill with 167 GitHub stars.

What programming language is CatDesk written in?

CatDesk is primarily written in Rust.

How do I install or use CatDesk?

You can find installation instructions and usage details in the CatDesk GitHub repository at github.com/Xeift/CatDesk. The project has 167 stars and 40 forks, indicating an active community.

What license does CatDesk use?

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

What are the best alternatives to CatDesk?

The top alternatives to CatDesk on Agent Skills Hub include ai-maestro, upskill, skills. 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 Codex Skill tools