project-os-for-codex — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

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 herry2059 · MCP Server · ★ 101

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

🔒 Is project-os-for-codex safe to install? View the security audit →

About project-os-for-codex

🚦 Project OS for Codex The open-source control plane for Codex projects: visible progress, resumable context, safe handoffs, and reusable knowledge. Independent open-source project. Not affiliated with or endorsed by OpenAI. Built for Codex. Connect through MCP, keep project truth in Git, and make every handoff resumable. <img src="https://img.shields.io/github/contributors/herry2059/project-os-for-codex?style=for-the-b

agent-handoffai-agentsai-codingai-project-managementcodexcodex-clicontext-engineeringdeveloper-toolsgitknowledge-base

Quick Facts

Stars101
Forks5
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score65.4862827649433/100
Last Updated2026-07-14
Created2026-07-09
Platformscli, codex, mcp, node
Est. Tokens~18k

Compatible Skills

These tools work well together with project-os-for-codex for enhanced workflows:

  • clickup-cli — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • ai-agent-automation — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • veritas-kanban — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)

project-os-for-codex alternative? Top 6 similar tools

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

  • mcp-fusion by vinkius-labs · ⭐ 204

    MCP Fusion - The framework for AI-native MCP servers.

  • ai-agent-automation by vmDeshpande · ⭐ 178

    Modular AI agent workflow automation platform with schedulers, tools, and observability. https://vmdeshpande.g

  • claude-emporium by Vvkmnn · ⭐ 84

    🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace

  • vibe-check-mcp-server by PV-Bhat · ⭐ 502

    Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineeri

  • daymon by daymonio · ⭐ 368

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

  • orchestkit by yonatangross · ⭐ 278

    The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is project-os-for-codex?

project-os-for-codex is Open-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.. It is categorized as a MCP Server with 101 GitHub stars.

What programming language is project-os-for-codex written in?

project-os-for-codex is primarily written in TypeScript. It covers topics such as agent-handoff, ai-agents, ai-coding.

How do I install or use project-os-for-codex?

You can find installation instructions and usage details in the project-os-for-codex GitHub repository at github.com/herry2059/project-os-for-codex. The project has 101 stars and 5 forks, indicating an active community.

What license does project-os-for-codex use?

project-os-for-codex is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to project-os-for-codex?

The top alternatives to project-os-for-codex on Agent Skills Hub include mcp-fusion, ai-agent-automation, claude-emporium. 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 MCP Server tools