codex-image

codex-image is a skill for Claude Code, Codex from jh941213/codex-lattice. It costs 259 tokens per session (2,019 once invoked), scanned A, original, MIT.

An image-generation skill for the OpenAI Codex command-line tool. It can create one image or up to five images at the same time using Codex’s built-in image tool.

In plain words
What is it for?
Creating one or several PNG images from text prompts, saving them into a chosen workspace folder, and producing image variations in batches.
Why use it?
It avoids writing separate API scripts or managing a separate API key when Codex is already signed in. Parallel generation can reduce the time needed to produce several images.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/jh941213/codex-lattice/codex-image
Any agent
npx skills add jh941213/codex-lattice --skill codex-image
Clone the repo
git clone --depth 1 https://github.com/jh941213/codex-lattice

Made for: Claude Code, Codex.

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 codex-image

README.md
[![agentmods](https://agentmods.dev/badge/skills/jh941213/codex-lattice/codex-image.svg)](https://agentmods.dev/skills/jh941213/codex-lattice/codex-image)
Your own site
<a href="https://agentmods.dev/skills/jh941213/codex-lattice/codex-image"><img src="https://agentmods.dev/badge/skills/jh941213/codex-lattice/codex-image.svg" alt="Measured on agentmods" 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 2,019 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00259 $0.02019
Opus 5 $0.00130 $0.01009
Sonnet 5 $0.00052 $0.00404
Haiku 4.5 $0.00026 $0.00202

Measured 4d ago against content hash c70a75c5bddc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-image scanned grade A 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/codex_imagegen_batch.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **인증 단순화**: codex 가 ChatGPT OAuth 로 이미 로그인돼 있으면 별도 OPENAI_API_KEY · Python SDK · curl 스크립트가 모두 불필요. 단순 자연어 프롬프트 한 줄로 끝.
skills/codex-image/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Image Generation (병렬)

OpenAI Codex CLI 의 내장 image_generation 툴을 활용해 최대 5장까지 이미지를 동시에 생성하는 스킬. (codex-cli 0.128 / 2026-05 실측 기준)

왜 이 스킬인가

  • 병렬 처리: codex exec 를 백그라운드 N개로 띄우면 OpenAI 서버가 N개를 동시 처리. 5장 동시 시 직렬 대비 약 2.85배 빠름 (실측: 직렬 추정 450초 → 병렬 158초).
  • 인증 단순화: codex 가 ChatGPT OAuth 로 이미 로그인돼 있으면 별도 OPENAI_API_KEY · Python SDK · curl 스크립트가 모두 불필요. 단순 자연어 프롬프트 한 줄로 끝.
  • 워크스페이스 통합: 결과 PNG 가 지정 디렉토리에 자동 저장 (codex 가 ~/.codex/generated_images/<session>/ 에서 작업 폴더로 복사).

사전 점검

codex --version           # 0.128+ 권장
codex login status        # "Logged in using ChatGPT" 확인
codex features list | grep image_generation   # stable / true 인지 확인

미로그인 시 codex login 실행을 사용자에게 요청. 이 스킬 호출 전에 한 번만.

핵심 패턴 1 — 단일 이미지 (베이스라인)

codex exec \
  --sandbox workspace-write \
  --skip-git-repo-check \
  --cd <work_dir> \
  -o /tmp/codex-img-single.md \
  "이미지 생성 도구로 '<프롬프트>' 이미지를 생성하고 ./<출력>.png 로 저장. 파일 경로만 한 줄로 보고."
  • 평균 소요: 약 80~110초/장 (모델 응답 분산 큼)
  • 기본 해상도: 1254×1254 또는 1536×1024 — codex 가 프롬프트에 따라 자동 결정
  • 해상도 강제는 어려움. 정확한 해상도가 필요하면 gpt-image2 사용

핵심 패턴 2 — N장 병렬 (N ≤ 5)

Bash run_in_background: true 로 동일 명령을 N개 띄운다. 핵심은 출력 파일명을 다르게 하는 것.

# 한 메시지 안에서 5개 Bash 도구 호출을 동시에 실행
codex exec --sandbox workspace-write --skip-git-repo-check --cd <work_dir> \
  -o /tmp/codex-img-1.md \
  "이미지 생성 도구로 '<프롬프트1>' 이미지를 생성하고 ./<output1>.png 로 저장. 경로만 한 줄로 보고."
# ... 같은 패턴으로 2~5번째도 run_in_background: true 로 띄움

각 작업은 독립 codex 세션이므로 진정한 병렬. 완료 알림은 백그라운드 작업 통지로 자동 수신 — sleep 폴링 금지.

실측 (2026-05 기준)

동시 작업 수 가장 느린 작업 wall-clock 직렬 대비
1장 89.7초 1.00×
3장 110.9초 2.43×
5장 158.5초 2.84×

5장이 3장보다 가장 느린 작업이 ~47초 늘어남. 큐잉 흔적이지만 명확한 직렬화는 없음.

핵심 패턴 3 — N > 5 배치 처리

ChatGPT 플랜의 동시 요청 한도와 안정적 응답 시간을 고려해 5개씩 묶어 순차 배치를 권장.

# 12장 = 5 + 5 + 2 의 3배치
# 배치1: 5개 동시 → 완료 대기
# 배치2: 다음 5개 동시 → 완료 대기
# 배치3: 마지막 2개 동시

배치 헬퍼 스크립트는 scripts/codex_imagegen_batch.sh 참고.

헬퍼 스크립트

Read the full file on GitHub · 133 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 133 lines · 259 tokens per session scan A c70a75c5bddc

Subscribe to this mod's changes

codex-image is a skill published in the GitHub repository jh941213/codex-lattice (19 stars, last pushed 3mo ago), licensed MIT. It adds 259 tokens to every session and 2,019 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-cut

剪辑中文口播原素材:逐词转录、词典修字出修字表、五轮扫描找口误与重复、汇总表与重复句子表、打开 Studio 让用户复核、复盘沉淀用户偏好与词典。只产出一份已复核的删词账本,不切媒体、不做字幕、不做分镜动画。用户说剪口播、处理口误、生成口播基础素材、继续剪口播,或确认卡回传 action=returncutreview 时使用。不要用于执行物理剪切、导出剪后视频、单独安装、单独打开工作台或口播分镜成片。.

Agentchengfeng/chengfeng-videocut-skills · 154 tokens

chengfeng-check-updates

剪辑环境的唯一管理者:就绪检查(skills 是否最新 → Runtime 是否配套)、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用;业务 Skill(剪口播/字幕/画面/导出)第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

infographic-template-updater

Update template catalogs and UI prompts after adding new infographic templates (src/templates/.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.

antvis/Infographic · 43 tokens

moq

Build live video, audio, and real-time data apps with Media over QUIC (MoQ). Use when adding live streaming, conferencing, voice AI, or real-time pub/sub to an app; when integrating the @moq/ npm packages, moq- Rust crates, or the Python/Kotlin/Swift/Go/C bindings; or when running a moq-relay server or a gateway…

moq-dev/moq · 104 tokens