5dive — security grade CAUTION, quality 67/100

Security audit verdict: CAUTION · quality 67/100

Flagged: sudo usage, privileged Docker. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by 5dive-ai · Codex Skill · ★ 60

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

🔒 Is 5dive safe to install? View the security audit →

About 5dive

5dive: run a company of AI agents on a server you own Spin up named agents, each with its own model, memory, and role. Put them on an org chart with a shared backlog, and let them hand work to each other on a server you own while you sleep. They ping your phone over Telegram only when a human has to decide. Works with claude, codex, grok, antigravity. We run our own company on this: a team of AI agents that assign each other work, report up an org chart, and escalate to a human only when they're stuck. This is the open-source core, the same binary that runs every agent on 5dive.com. MIT, no open-core split. Run it yourself, or skip the ops with the managed VM. Already use Claude Code, Codex, Grok, Antigravity, or opencode? Install the skill and run your whole agent company in plain English — crea

agent-loopsagent-orchestrationagent-runtimeagent-to-agentai-agentsai-companyai-teamai-workforceautonomous-agentsclaude-code

Quick Facts

Stars60
Forks10
LanguageShell
CategoryCodex Skill
LicenseMIT
Quality Score66.6352761339446/100
Open Issues20
Last Updated2026-09-20
Created2026-05-15
Platformsclaude-code, cli, codex
Est. Tokens~14k

Compatible Skills

These tools work well together with 5dive for enhanced workflows:

  • Clawdboss — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • plugin — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)

5dive alternative? Top 6 similar tools

Looking for a 5dive alternative? If you're comparing 5dive 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.

  • markus by markus-global · ⭐ 194

    The all-in-one AI workforce platform, to build AI agent teams. You are the boss.

  • platform by agynio · ⭐ 232

    Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops

  • open-tag by fancyboi999 · ⭐ 167

    Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agen

  • captain-claw by kstevica · ⭐ 163

    Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic

  • manor-ai by manor-os · ⭐ 153

    Source-available, self-hosted AI agent workspace for small businesses and lean teams — with BYOK, workflows, t

  • CoordClaw by CoordClaw · ⭐ 130

    CoordClaw: a multi-agent system that runs AI like a one-person company. Built on management & organizational t

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Shell Agent Tools

Frequently Asked Questions

What is 5dive?

5dive is Run a company of AI agents on a server you own. Spin up named agents (claude, codex, pi…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a human . It is categorized as a Codex Skill with 60 GitHub stars.

What programming language is 5dive written in?

5dive is primarily written in Shell. It covers topics such as agent-loops, agent-orchestration, agent-runtime.

How do I install or use 5dive?

You can find installation instructions and usage details in the 5dive GitHub repository at github.com/5dive-ai/5dive. The project has 60 stars and 10 forks, indicating an active community.

What license does 5dive use?

5dive is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to 5dive?

The top alternatives to 5dive on Agent Skills Hub include markus, platform, open-tag. 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