media-codex-image

media-codex-image is a skill for Claude Code, Codex from modu-ai/moai-cowork. It costs 259 tokens per session (3,623 once invoked), scanned B, original, Apache-2.0.

A local image-generation skill that uses Codex CLI and GPT Image 2 to create images through an existing ChatGPT login. GPT Image 2 is an AI model for generating images from text instructions.

In plain words
What is it for?
It sends structured image prompts to GPT Image 2 and supports image creation with Korean text instructions and text in images.
Why use it?
It lets users generate images locally without managing an OpenAI API key, provided Codex CLI is installed and logged in.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also runs codex exec. Also seen: positional $N argument; mentions Claude Code; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is codex exec "Use \$imagegen. Generate a 1536x1024 aerial view of jeju island coastline, golden hour. quality high, save to ./public/images/jeju.png".

Part of the moai-media plugin — 14 skills, 2 agents shipped together

Good fit It sends structured image prompts to GPT Image 2 and supports image creation with Korean text instructions and text in images.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-cowork
agentmods
npx agentmods add skills/modu-ai/moai-cowork/media-codex-image

Made for: Claude Code, Codex.

Or install moai-media, the plugin that ships this one along with the rest of its 14 skills, 2 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for media-codex-image

README.md
[![agentmods](https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-codex-image/github.svg)](https://agentmods.dev/skills/modu-ai/moai-cowork/media-codex-image)
Your own site
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/media-codex-image"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-codex-image/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for media-codex-image

Your own site · 80×15
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/media-codex-image"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-codex-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 259 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,623 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Excessive Agency · line 101
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • high Excessive Agency · line 107
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • high Excessive Agency · line 114
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • high Excessive Agency · line 120
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • high Excessive Agency · line 129
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • high Agent Snooping · line 218
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00259 $0.03623
Opus 5 $0.00130 $0.01811
Sonnet 5 $0.00052 $0.00725
Haiku 4.5 $0.00026 $0.00362

Measured 7d ago against content hash 313e1354c241, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

media-codex-image scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| Trust 오류 | 프로젝트를 `~/.codex/config.toml` 신뢰 목록 추가 또는 `--skip-git-repo-check` |
plugins/moai-media/skills/media-codex-image/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

media-codex-image — codex CLI(gpt-image-2) 이미지 생성기

moai-coworker | 로컬 이미지 생성 (codex CLI OAuth, API 키 불필요)

개요

codex CLI의 내장 image_gen 도구를 호출해 gpt-image-2 모델로 이미지를 생성합니다. 핵심은 OpenAI REST API를 직접 호출하지 않고 codex exec 브릿지를 경유한다는 점 — ChatGPT OAuth 세션 토큰(~/.codex/auth.json)을 이미지 생성 서비스로 라우팅해 API 키(sk-*) 없이 ChatGPT 구독 한도로 동작합니다.

특히 본 스킬은:

  • API 키 불필요codex login 1회 OAuth로 ChatGPT 구독(Plus/Team/Enterprise) 한도 사용. OPENAI_API_KEY 관리 부담 없음.
  • 6-Block 프롬프트 연동media-gpt-image-2-prompt가 빌드한 OpenAI Cookbook 6-Block 프롬프트(Subject·Action·Scene·Composition·Lighting·Style&Text)를 그대로 codex에 전달.
  • 한국어 verbatim 보장 — 이미지 내 한글 텍스트는 따옴표·ALL CAPS·verbatim 지시로 gpt-image-2의 95%+ 텍스트 렌더링 정확도 활용.
  • media-higgsfield-image 대체 경로 — 같은 gpt-image-2를 Higgsfield MCP 경로(media-higgsfield-image)로도 호출 가능. 백엔드 선택은 환경·비용 선호에 따라.

트리거 키워드

codex 이미지 codex image gpt-image-2 생성 GPT Image 2 API 키 없이 이미지 로컬 이미지 생성 ChatGPT 구독 한도 이미지 codex exec image_gen

핵심 인사이트 — OAuth 브릿지 (왜 codex exec인가)

OpenAI의 모든 인증 경로를 테스트한 결과 (참고: wjb127/codex-image MIT):

방식 동작 비고
OPENAI_API_KEY → REST API 표준이지만 API 키 관리 부담
OAuth 토큰 → REST API 직접 401 OAuth 토큰은 세션 토큰이지 API 키가 아님
OAuth 토큰 → codex execimage_gen 본 스킬 codex exec 내부 브릿지가 OAuth를 이미지 생성 서비스로 라우팅
codex login (최초 1회)
  → OAuth 토큰이 ~/.codex/auth.json에 저장
    → codex exec가 토큰을 자동 읽기
      → 내장 image_gen 도구가 OAuth로 인증
        → gpt-image-2가 이미지 생성
          → 프로젝트 디렉토리에 저장

주의: OAuth 토큰으로 OpenAI REST API를 직접 호출하면 HTTP 401. 반드시 codex exec 브릿지를 거쳐야 합니다.

전제 — codex CLI 설치 + 로그인

요구사항 명령 비고
codex CLI npm install -g @openai/codex 이미지 생성 엔진
codex login codex login ChatGPT로 최초 1회 OAuth
# 설치·인증 확인
codex --version          # OpenAI Codex v0.1xx.x
codex login status       # "Logged in using ChatGPT"

Cowork 환경에서 Bash가 제한되면 codex CLI 호출이 차단될 수 있습니다. 이 스킬은 로컬 Claude Code(터미널) 또는 Bash 허용 Cowork 환경에서 동작합니다. Bash 제한 시 사용자에게 codex 명령어를 안내만 하고 수동 실행을 유도하세요.

Read the full file on GitHub · 239 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 239 lines · 259 tokens per session scan B 313e1354c241

Subscribe to this mod's changes

media-codex-image is a skill published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 7d ago), licensed Apache-2.0. It adds 259 tokens to every session and 3,623 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

infographic-v2

Generate professional infographics using Nano Banana MCP (Gemini AI image generation). Follows a guided flow - analyze content, suggest visualizable concepts, propose visualization approaches, then generate on-brand images. USE THIS SKILL WHEN user says "create infographic v2", "make a visual v2", "infographic-v2".…

naveedharri/benai-skills · 81 tokens

excalidraw

Create visual presentations, slide decks, and explanatory diagrams in Excalidraw. Use when user asks to create a presentation, slide deck, visual explainer, pitch deck, comparison diagram, process flow, or any multi-slide visual content. Supports two output modes — generating .excalidraw JSON files OR injecting slides…

naveedharri/benai-skills · 99 tokens

marketing-os-carousel

Build an image-first social carousel from an asset already filed in the Marketing OS, export it as a PDF, and record it back as a real channel asset. Brand palette, typography, the logo pointer and the never-black-background rule all resolve from Context/brand/brand-kit.md. Source is a filed newsletter edition…

naveedharri/benai-skills · 221 tokens

youtube-brief

Create a detailed video brief for a new YouTube video through a structured, collaborative process. This is a STEP-BY-STEP, interactive process — never output a complete brief immediately. Each step requires suggestions, user decision, then progression to the next step. USE THIS SKILL WHEN: - User wants to plan a…

naveedharri/benai-skills · 205 tokens

ads-creative

Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative fatigue, evaluates platform-native compliance, and provides production priorities. Collects brand context and creates branding.md if missing. Uses infographic-v2 for generating ad…

naveedharri/benai-skills · 88 tokens

generate-visual

Generate on-screen visuals for Ben van Sprundel's YouTube videos using Higgsfield. Same brand system as the thumbnails (charcoal + coral, dot-grid, flat-stylized icons, bold uppercase text), but optimized for in-video slides shown during a tutorial. Use when the user says generate a visual, make a slide, on-screen…

naveedharri/benai-skills · 164 tokens