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.
npx skills add joonlab/joonlab-claudecode-setting-for-share --skill openai-gpt-image-2git clone --depth 1 https://github.com/joonlab/joonlab-claudecode-setting-for-shareWrote 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.
[](https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/openai-gpt-image-2)<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/openai-gpt-image-2"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/openai-gpt-image-2/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.
<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/openai-gpt-image-2"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/openai-gpt-image-2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00179 | $0.02752 |
| Opus 5 | $0.00089 | $0.01376 |
| Sonnet 5 | $0.00036 | $0.00550 |
| Haiku 4.5 | $0.00018 | $0.00275 |
Grade A, and why
openai-gpt-image-2 scanned grade A with 0 findings 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAI gpt-image-2
OpenAI의 SOTA 이미지 모델 gpt-image-2로 이미지 생성 및 편집을 수행합니다.
- 모델 ID:
gpt-image-2(스냅샷:gpt-image-2-2026-04-21) - 인증:
OPENAI_API_KEY환경변수 (스크립트가 매 실행 시 동적으로 읽음) - 기본값:
quality=high,size=auto,format=png, 저장 위치~/Downloads/
Quick Start
# 1) 기본 생성 (텍스트 → 이미지, quality=high가 기본)
uv run ~/.claude/skills/openai-gpt-image-2/scripts/generate_image.py \
"Photorealistic portrait of an elderly sailor on a small fishing boat at dawn"
# 2) 출력 경로/해상도 명시
uv run ~/.claude/skills/openai-gpt-image-2/scripts/generate_image.py \
"K-pop concert poster, neon, vertical" \
-o ~/Downloads/poster.png \
--size 1024x1536
# 3) 이미지 편집 (참조 이미지 + 프롬프트, 최대 16장)
uv run ~/.claude/skills/openai-gpt-image-2/scripts/generate_image.py \
"Combine these four items into a cohesive gift basket on a white background" \
-i body-lotion.png -i soap.png -i incense-kit.png -i bath-bomb.png \
-o ~/Downloads/basket.png
# 4) 마스크 인페인팅
uv run ~/.claude/skills/openai-gpt-image-2/scripts/generate_image.py \
"Replace the masked region with a window overlooking the ocean" \
-i room.png --mask room_mask.png
워크플로우 (11-slot + 점진 quality)
1단계 — 11-slot prompt contract 채우기
복잡한 비주얼(포스터, 인포그래픽, 슬라이드, 광고, UI mockup, 텍스트 포함 이미지)은 11개 slot 전부 채워서 작성:
[Purpose] [Core brief] [Required elements] [Context] [Style]
[Composition] [Light/material/color] [Layout] [Text rules]
[Constraints] [Output]
상세 정의/카테고리별 우선순위/Cookbook 튜닝 규칙은 references/prompt-contract.md 참고. 카테고리별(infographic/slide/product/UI/character) 사전 채워둔 패턴은 references/use-cases.md 참고.
빠른 초안용은 3-slot: [Subject] + [Context] + [Style]만으로 시작 가능.
2단계 — 사이즈 사전 검증 (선택, 비표준 사이즈일 때만)
비표준 --size WxH를 쓸 거면 호출 전에 검증:
uv run scripts/check_size.py --size 1920x1080
uv run scripts/check_size.py --suggest-presets # 8개 프리셋 표
정사각/HD/2K 프리셋만 쓸 때는 생략 가능. auto는 항상 안전.
3단계 — 점진 quality (low → high)
기본은 high($0.21/장)지만 탐색 단계는 --quality low($0.006/장, 35배 저렴)로 시작 → 구도/구성 검증 → 만족 시 high로 재실행. 텍스트가 많거나 세밀한 인포그래픽/UI는 처음부터 high.
What ships with it
5 files 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.
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.
- 11d ago First seen · 196 lines · 179 tokens per session scan A 70b60ff8cb85
openai-gpt-image-2 is a skill published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 1mo ago), licensed MIT. It adds 179 tokens to every session and 2,752 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
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…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.