codex-gpt-image — 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 ningzimu · Claude Skill · ★ 56

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

🔒 Is codex-gpt-image safe to install? View the security audit →

About codex-gpt-image

Codex GPT Image Skill 一个面向 OpenClaw / Claude Code / Codex / Hermes Agent 的 生图 skill:通过 Codex OAuth / ChatGPT 登录态 调用 ,不需要 。 它读取本机 ,请求 ,并显式调用 Responses 工具,让 agent 复用已有 Codex / ChatGPT 订阅权限生成图片。 适合谁用 想在 OpenClaw / Claude Code / Codex / Hermes Agent 里直接用 生图 已经有 Codex / ChatGPT OAuth 登录态,不想再配置 OpenAI API key 想把同一套 GPT Image skill 复用到多个支持 的 agent 需要文本生图、参考图编辑、2K/4K 输出或透明背景请求 特点 OpenClaw skill / Claude Code skill / Codex skill / Hermes Agent skill Codex OAuth:读取 ,不要求 OpenAI API key 默认使用 ,支持 、、、 质量参数 支持文本生图和多参考图编辑 支持 2K/4K 合法尺寸,例如 、 支持透明背景请求自动使用 纯 Python 标准库脚本,便于在任意 agent 环境里调用 目录结构 安装 推荐使用 CLI 一次安装到当前 agent 的全局 skills 目录: 这个仓库目前只包含 一个 skill。安装完成后

agent-skillsclaude-codeclaude-code-skillcodexcodex-oauthgpt-image-2hermes-agentimage-generationopenclawopenclaw-skill

Quick Facts

Stars56
Forks2
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score64.8740634882873/100
Last Updated2026-09-10
Created2026-05-11
Platformsclaude-code, codex, python
Est. Tokens~5k

codex-gpt-image alternative? Top 6 similar tools

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

  • mcp-image by shinpr · ⭐ 161

    MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Support

  • skills by fabricioctelles · ⭐ 88

    A collection of skills for AI agents (Kiro, Cursor, Windsurf, Claude Code, and others). Each skill is a reusab

  • agent-skills by jdrhyne · ⭐ 241

    A collection of AI agent skills for Clawdbot, Claude Code, Codex

  • maestro by ReinaMacCredy · ⭐ 232

    Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f

  • open-skills by besoeasy · ⭐ 132

    Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, sear

  • kaggle-skill by shepsci · ⭐ 81

    Complete Kaggle integration plugin/skill for AI coding agents — competition reports, dataset/model downloads,

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is codex-gpt-image?

codex-gpt-image is OpenClaw/Claude Code SKILL.md for gpt-image-2 via Codex OAuth, no OPENAI_API_KEY required. It is categorized as a Claude Skill with 56 GitHub stars.

What programming language is codex-gpt-image written in?

codex-gpt-image is primarily written in Python. It covers topics such as agent-skills, claude-code, claude-code-skill.

How do I install or use codex-gpt-image?

You can find installation instructions and usage details in the codex-gpt-image GitHub repository at github.com/ningzimu/codex-gpt-image. The project has 56 stars and 2 forks, indicating an active community.

What license does codex-gpt-image use?

codex-gpt-image is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to codex-gpt-image?

The top alternatives to codex-gpt-image on Agent Skills Hub include mcp-image, skills, agent-skills. 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 Claude Skill tools