compozy — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

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 compozy · Codex Skill · ★ 2.8k

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

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

About compozy

CompozyOS The system around the agent, already built. An operating system for AI agents. Anyone can prompt an agent. Making agents work continuously is still an engineering project: loops, triggers, cron, memory, permissions, approvals, observability, and the glue scripts that hold them together. CompozyOS turns that entire agent stack into one product, a complete environment to create, automate, and supervise agent work with the agent CLIs you already use (Claude Code, OpenClaw, and Hermes). Built fi

Quick Facts

Stars2,751
Forks177
LanguageGo
CategoryCodex Skill
LicenseMIT
Quality Score59.8187701443518/100
Open Issues12
Last Updated2026-09-15
Created2026-03-28
Platformsbrowser, claude-code, cli, codex, gemini, go
Est. Tokens~18k

Compatible Skills

These tools work well together with compozy for enhanced workflows:

  • comanda — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • quint-code — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • haft — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • subtask — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)
  • shaping-skills — semantic(0.24)+complementary+similar_pop+shared_platform (48%)

compozy alternative? Top 6 similar tools

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

  • refly by refly-ai · ⭐ 7.5k

    The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex

  • Claude-to-IM-skill by op7418 · ⭐ 2.9k

    Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark

  • skillshare by runkids · ⭐ 2.6k

    📚 Sync skills across all AI CLI tools with one command and simplify team sharing. Supporting Codex, Claude Co

  • agent-skill-creator by FrancyJGLisboa · ⭐ 2.4k

    Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery,

  • learning-opportunities by DrCatHicks · ⭐ 2.4k

    A Claude or Codex skill for deliberate skill development during AI-assisted coding

  • pi-skills by badlogic · ⭐ 2.3k

    Skills for pi coding agent (compatible with Claude Code and Codex CLI)

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Go Agent Tools

Frequently Asked Questions

What is compozy?

compozy is An operating system for AI agents. Plug in the agent CLIs you already use (Claude Code, Codex, Gemini CLI, Cursor) and they become a team: they split the work, hand tasks to each other, run automated . It is categorized as a Codex Skill with 2.8k GitHub stars.

What programming language is compozy written in?

compozy is primarily written in Go.

How do I install or use compozy?

You can find installation instructions and usage details in the compozy GitHub repository at github.com/compozy/compozy. The project has 2.8k stars and 177 forks, indicating an active community.

What license does compozy use?

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

What are the best alternatives to compozy?

The top alternatives to compozy on Agent Skills Hub include refly, Claude-to-IM-skill, skillshare. 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