CodexFlow — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

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 lulu-sk · Codex Skill · ★ 83

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

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

About CodexFlow

CodexFlow A "Unified Workbench" crafted for AI Coding Agents — switch between Codex / Claude / Gemini (and custom engines) in one click, organize sessions and history by project directories, run parallel tasks with Git Worktree, browse and resume conversations with Markdown rendering, and provide a graphical input box for CLI with support for pasting images / dragging files / @project files / full-screen input for efficient prompting. Platform Recommendation: Windows 11 + WSL

aianthropicantigravityantigravity-cliclaudeclaude-codecodexcodex-clicodex-cli-guicodex-cli-ui

Quick Facts

Stars83
Forks7
LanguageTypeScript
CategoryCodex Skill
LicenseApache-2.0
Quality Score68.3191122165569/100
Open Issues2
Last Updated2026-08-07
Created2025-10-11
Platformsclaude-code, cli, codex, gemini, node
Est. Tokens~18k

Compatible Skills

These tools work well together with CodexFlow for enhanced workflows:

  • codexia — semantic(0.57)+complementary+rare_topics+same_lang+shared_platform (64%)
  • codex-mcp-server — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (61%)
  • codex-specialized-subagents — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (55%)

CodexFlow alternative? Top 6 similar tools

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

  • aisw by burakdede · ⭐ 94

    AISW | AI Switcher - Switch between multiple Claude Code, Codex CLI, Antigravity and Gemini CLI accounts in on

  • awesome-system-prompts by EliFuzz · ⭐ 250

    A collection of system prompts and tool definitions from various AI coding agents: Augment Code, Claude Code,

  • agent-network by sleep2agi · ⭐ 73

    助力搭建你的数字 AI 员工军团 — 多 Agent 一行命令组网协作。Claude Code / Claude Agent SDK / Codex / Grok Build 4 runtime + 8+ 家 LLM(A

  • agentbox by madarco · ⭐ 389

    Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud

  • gemini-for-claude-code by coffeegrind123 · ⭐ 352

    This python program allows you to use Claude Code with Google's Gemini models.

  • app by lanes-sh · ⭐ 268

    One workspace. Many agents. Your parallel AI advantage

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is CodexFlow?

CodexFlow is CodexFlow is a unified desktop workbench for AI coding agents (Codex/Claude/Gemini/Antigravity) across Windows and WSL. Organize chats by project, run parallel tasks via Git worktrees, build rich prom. It is categorized as a Codex Skill with 83 GitHub stars.

What programming language is CodexFlow written in?

CodexFlow is primarily written in TypeScript. It covers topics such as ai, anthropic, antigravity.

How do I install or use CodexFlow?

You can find installation instructions and usage details in the CodexFlow GitHub repository at github.com/lulu-sk/CodexFlow. The project has 83 stars and 7 forks, indicating an active community.

What license does CodexFlow use?

CodexFlow 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 CodexFlow?

The top alternatives to CodexFlow on Agent Skills Hub include aisw, awesome-system-prompts, agent-network. 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