notchi — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 sk-ruban · Claude Skill · ★ 1.0k

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

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

About notchi

Notchi A macOS notch companion that reacts to Claude Code and Codex activity in real-time. https://github.com/user-attachments/assets/e417bd40-cae8-47c0-998a-905166cf3513 What it does Reacts to Claude Code and Codex events in real-time (thinking, working, permission requests, compaction, errors, completions) Analyzes prompt sentiment via Anthropic or OpenAI APIs to show emotions (happy, elated, sad, neutral, sob) Click to expand and see session time and usage quota Supports multiple concurrent sessions, each with its own mascot from the Claude or Codex sprite family Sound effects for events with support for importable custom sounds (optional, auto-muted when terminal is focused) Auto-updates via Sparkle Requirements macOS 15.0+ (Sequoia) MacBook with notch Claude Code and/or Codex installed Install Download from the latest GitHub Release Open the DMG and drag Notchi to Applications Launch Notchi — it auto-installs Claude Code and Codex hooks on first launch (whichever are present) If you use Claude Code, a macOS keychain popup will appear asking to access its cached OAuth token (used for API usage stats).

claude-codecodexswift

Quick Facts

Stars1,030
Forks76
LanguageSwift
CategoryClaude Skill
LicenseGPL-3.0
Quality Score67.3884088260487/100
Open Issues24
Last Updated2026-09-21
Created2026-01-30
Platformsclaude-code, codex
Est. Tokens~15k

notchi alternative? Top 6 similar tools

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

  • cocoindex-code by cocoindex-io · ⭐ 2.7k

    A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficie

  • pilot-shell by maxritter · ⭐ 2.1k

    Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software

  • apple-docs-mcp by kimsungwhee · ⭐ 1.4k

    MCP server for Apple Developer Documentation - Search iOS/macOS/SwiftUI/UIKit docs, WWDC videos, Swift/Objecti

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

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

  • swift-ios-skills by dpearson2699 · ⭐ 996

    Agent Skills for iOS 26+, Swift 6.3, SwiftUI, and modern Apple frameworks

  • codexia by milisp · ⭐ 915

    Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is notchi?

notchi is notch app for claude code & codex. It is categorized as a Claude Skill with 1.0k GitHub stars.

What programming language is notchi written in?

notchi is primarily written in Swift. It covers topics such as claude-code, codex, swift.

How do I install or use notchi?

You can find installation instructions and usage details in the notchi GitHub repository at github.com/sk-ruban/notchi. The project has 1.0k stars and 76 forks, indicating an active community.

What license does notchi use?

notchi is released under the GPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to notchi?

The top alternatives to notchi on Agent Skills Hub include cocoindex-code, pilot-shell, apple-docs-mcp. 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 Claude Skill tools