agentbox — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 madarco · Codex Skill · ★ 476

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

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

About agentbox

AgentBox&nbsp; Run multiple agents in parallel, with a single command, on your PC, self-hosted, or in the cloud Works with iterm2 - cmux - tmux How it works 📦 Teleport - Move your project to a dedicated VM, local or in the cloud, with a single command. 🤖 Automatic - Bring all your skills, plugins, and settings for Claude Code, Codex, Open Code 🌐 A full Computer — Dedicated browser, screen sharing, persistent shells and warmed up VS Code / Cursor IDE, with each box. 💾 Checkpoints — Sub <1s startup of new boxes from a previous checkpoint, auto pause to save cost/resources when not in use. 🔒 Safe - Your git credentials are kept on your local machine, with permission requests to push to the remote repository. Full Documentation Complete setup: sh npm -g

claudeclaude-codeclicmuxcodexcodex-clicoding-agentsdeveloper-toolsdockergrok-build

Quick Facts

Stars476
Forks36
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score69.9619828333073/100
Open Issues1
Last Updated2026-09-21
Created2026-05-12
Platformsclaude-code, cli, codex, docker, node
Est. Tokens~16k

Compatible Skills

These tools work well together with agentbox for enhanced workflows:

  • simple-agent-manager — semantic(0.39)+complementary+same_lang+similar_pop+shared_platform (59%)
  • codex-collab — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)

agentbox alternative? Top 6 similar tools

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

  • agent-notifications by 777genius · ⭐ 815

    🔔 Cross-platform smart notifications for Claude/Codex (more planned). Desktop alerts, sounds, click-to-focus,

  • Codeman by Ark0N · ⭐ 764

    Self-hosted mission control for AI coding agents: run Claude Code, OpenCode, Pi, Codex, and Antigravity & Gemi

  • ai-devkit by codeaholicguy · ⭐ 1.6k

    The control plane for AI coding agents.

  • quint-code by m0n0x41d · ⭐ 1.3k

    Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p

  • code-on-incus by mensfeld · ⭐ 728

    Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops t

  • codemap by JordanCoin · ⭐ 689

    a project brain for your AI. Give LLMs instant architectural context without burning tokens

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is agentbox?

agentbox is Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud. It is categorized as a Codex Skill with 476 GitHub stars.

What programming language is agentbox written in?

agentbox is primarily written in TypeScript. It covers topics such as claude, claude-code, cli.

How do I install or use agentbox?

You can find installation instructions and usage details in the agentbox GitHub repository at github.com/madarco/agentbox. The project has 476 stars and 36 forks, indicating an active community.

What license does agentbox use?

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

What are the best alternatives to agentbox?

The top alternatives to agentbox on Agent Skills Hub include agent-notifications, Codeman, ai-devkit. 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