by JasonSTong · Codex Skill · ★ 106
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Local-first visual theme editor and hot-reload theme manager for Codex Desktop on macOS.
| Stars | 106 |
| Forks | 2 |
| Language | JavaScript |
| Category | Codex Skill |
| Quality Score | 54.0431458849492/100 |
| Last Updated | 2026-07-24 |
| Created | 2026-07-16 |
| Platforms | codex, node |
| Est. Tokens | ~13k |
These tools work well together with codex-theme-studio for enhanced workflows:
Looking for a codex-theme-studio alternative? If you're comparing codex-theme-studio 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.
Named CODEX_HOME profiles and ChatGPT Desktop windows with separate local state, without copying tokens
给 Codex Desktop 一键换肤：OpenAI Codex/ChatGPT 桌面端主题工具，CDP 注入零修改应用，Miku/原神/鸣潮/火影/恋与深空 9 预设+自定义图片取色 | One-click them
Cross-platform desktop notifications for Claude Code, Codex, and Gemini CLI. Install via Homebrew, npm, or scr
One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local
AI-powered annotations for localhost development. Create visual feedback on your apps and let AI coding agents
CodeWhisper: AI-Powered End-to-End Task Implementation & blazingly fast Codebase-to-LLM Context Bridge
Explore other popular codex skill tools:
codex-theme-studio is Local-first visual theme editor and hot-reload theme manager for Codex Desktop on macOS.. It is categorized as a Codex Skill with 106 GitHub stars.
codex-theme-studio is primarily written in JavaScript. It covers topics such as cdp, codex, codex-desktop.
You can find installation instructions and usage details in the codex-theme-studio GitHub repository at github.com/JasonSTong/codex-theme-studio. The project has 106 stars and 2 forks, indicating an active community.
The top alternatives to codex-theme-studio on Agent Skills Hub include codex-profiles, heige-codex-skin-studio, code-notify. 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: