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 ericjypark · Codex Skill · ★ 341
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codex-island safe to install? View the security audit →
CodexIsland Your AI usage limits, living in your notch. CodexIsland is a native macOS overlay that turns the MacBook notch into a Dynamic-Island-style live activity for Claude Code and Codex usage limits. It sits quietly over the notch, peeks on hover with the 5-hour headline, and expands on click to show both providers' 5-hour and weekly windows with reset timing, chart controls, and a swipeable Cost screen that estimates dollar spend and token throughput from your local session logs. https://github.com/user-attachments/assets/195beeff-0f70-4d6b-8f3d-9f31d9c0b989 The app is free, open source, unsigned, and local-first. It reads credentials already written by Claude Code / Claude Desktop and Codex, then calls only the providers' own usage endpoints. What it does Two providers, four windows. Claude 5h + 7d and Codex 5h + 7d live in one panel. Notch-native overlay. The compact state is a black pill aligned to the physical notch, drawn with continuous (squircle) corners that match the hardware. On non-notched Macs it falls back to a 200 x 28 menu-bar pill. Hover to peek. The silhouette widens just enough to show each visible provider's 5-hour percentage and reset headline.
| Stars | 341 |
| Forks | 49 |
| Language | Swift |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 75.7665191443571/100 |
| Open Issues | 22 |
| Last Updated | 2026-09-17 |
| Created | 2026-04-29 |
| Platforms | claude-code, codex |
| Est. Tokens | ~18k |
These tools work well together with codex-island for enhanced workflows:
Looking for a codex-island alternative? If you're comparing codex-island 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.
macOS Dynamic Island for AI coding agents. Monitor, approve, and jump to Claude Code sessions from the notch.
macOS Dynamic Island for AI coding agents. Monitor, approve, and jump to Claude Code sessions from the notch.
Vibe Island — macOS notch panel for 25 AI coding agents: Claude Code, Codex, Cursor, Gemini CLI & more. Monito
Vibe Island releases & update feed — download the latest DMG of the macOS notch panel for 25 AI coding agents
Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across
🔔 Cross-platform smart notifications plugin for Claude Code. 6 types. Click-to-focus (many terminal). 1 line
Explore other popular codex skill tools:
codex-island is CodexIsland - AI usage limits in your MacBook notch. It is categorized as a Codex Skill with 341 GitHub stars.
codex-island is primarily written in Swift. It covers topics such as claude, claude-code, codex.
You can find installation instructions and usage details in the codex-island GitHub repository at github.com/ericjypark/codex-island. The project has 341 stars and 49 forks, indicating an active community.
codex-island is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to codex-island on Agent Skills Hub include MioIsland, CodeIsland, vibe-island. 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: