agentpet — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

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 ntd4996 · Codex Skill · ★ 348

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

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

About agentpet

If AgentPet helps your workflow, please give it a star — it really helps! English · Tiếng Việt · 简体中文 · 日本語 Run several coding agents at once (Claude Code, Codex, ...) and AgentPet tells you, at a glance, which one is working, which one is done, and which one is waiting for your input, so you stop tab-hunting across terminals. A little pet floats on your desktop and reacts to it all. Why Running multiple agents in parallel means constantly switching windows to check who needs you. AgentPet surfaces that in two places: Menu bar monitor for the details: every running agent, its state, wha

ai-agentsclaude-codecodexdesktop-petdeveloper-toolsmacosmenubarproductivityswiftswiftui

Quick Facts

Stars348
Forks57
LanguageSwift
CategoryCodex Skill
LicenseMIT
Quality Score72.5906326339833/100
Open Issues1
Last Updated2026-09-07
Created2026-05-31
Platformsclaude-code, cli, codex, gemini
Est. Tokens~16k

Compatible Skills

These tools work well together with agentpet for enhanced workflows:

  • claude-pets — semantic(0.44)+complementary+rare_topics+similar_pop+shared_platform (60%)
  • Claude-Usage-Monitor — semantic(0.45)+complementary+rare_topics+similar_pop+shared_platform (55%)

agentpet alternative? Top 6 similar tools

Looking for a agentpet alternative? If you're comparing agentpet 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.

  • MioIsland by MioMioOS · ⭐ 544

    macOS Dynamic Island for AI coding agents. Monitor, approve, and jump to Claude Code sessions from the notch.

  • CodeIsland by xmqywx · ⭐ 172

    macOS Dynamic Island for AI coding agents. Monitor, approve, and jump to Claude Code sessions from the notch.

  • vibe-island-updates by edwluo · ⭐ 93

    Vibe Island releases & update feed — download the latest DMG of the macOS notch panel for 25 AI coding agents

  • agent-deck by asheshgoplani · ⭐ 935

    Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

  • claude-code-apple-skills by rshankras · ⭐ 606

    Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation,

  • daymon by daymonio · ⭐ 365

    Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is agentpet?

agentpet is A desktop pet for macOS & Windows that monitors your AI coding agents (Claude Code, Codex, Cursor, Gemini...) in real time, and grows as you code, feed it tokens, level it up, climb the leaderboard.. It is categorized as a Codex Skill with 348 GitHub stars.

What programming language is agentpet written in?

agentpet is primarily written in Swift. It covers topics such as ai-agents, claude-code, codex.

How do I install or use agentpet?

You can find installation instructions and usage details in the agentpet GitHub repository at github.com/ntd4996/agentpet. The project has 348 stars and 57 forks, indicating an active community.

What license does agentpet use?

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

What are the best alternatives to agentpet?

The top alternatives to agentpet on Agent Skills Hub include MioIsland, CodeIsland, vibe-island-updates. 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