media-gpt-image-prompt

media-gpt-image-prompt is a skill for Claude Code from modu-ai/moai-cowork. It costs 334 tokens per session (5,414 once invoked), scanned A, original, Apache-2.0.

An image-prompt writing tool that turns a natural-language idea into detailed prompts for GPT Image 2.5. It can also adapt the same idea for Gemini 3 Pro Image and Midjourney.

In plain words
What is it for?
Use it to prepare prompts for image generation, image editing, product shots, portraits, illustrations, and landscapes.
Why use it?
It removes the need to know each image model's prompt format or remember all the visual details to specify. It also keeps model settings separate when those settings must be chosen in the image tool.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the moai-media plugin — 17 skills, 2 agents shipped together

Good fit Use it to prepare prompts for image generation, image editing, product shots, portraits, illustrations, and landscapes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/modu-ai/moai-cowork/media-gpt-image-prompt
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.

Any agent
npx skills add modu-ai/moai-cowork --skill media-gpt-image-prompt
Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-cowork

Made for: Claude Code.

Or install moai-media, the plugin that ships this one along with the rest of its 17 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-gpt-image-prompt

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/media-gpt-image-prompt"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-gpt-image-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 334 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00334 $0.05414
Opus 5.5 $0.00134 $0.02166
Sonnet 5.5 $0.00067 $0.01083
Haiku 4.5 $0.00033 $0.00541

Measured 10d ago against content hash 086221b5e26e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

media-gpt-image-prompt 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 10d 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.

plugins/moai-media/skills/media-gpt-image-prompt/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GPT Image 2.5 Prompt Builder — 공식 가이드 8원칙 + 3-모델 동시 출력

이미지 프롬프트 빌더 (텍스트 산출 전용)

개요

GPT Image 2.5는 모델이 둘입니다.

모델 ID 성격 먼저 고르는 경우
gpt-image-2.5-flare 작은 모델, 속도 우선. 화질은 GPT Image 2와 비슷한 수준 새 워크플로에서 속도가 중요할 때, 기존 GPT Image 2 품질로 충분할 때
gpt-image-2.5-sunburst 기본 모델, 품질 우선. GPT Image 2보다 화질이 높음 품질 요구가 까다로울 때, GPT Image 2로 품질이 모자랐던 복잡한 작업

두 모델 모두 생성·편집·투명 배경을 지원하고, 정밀 편집과 피사체 보존이 좋아졌습니다. 본 스킬은 사용자 한 줄 요청을 OpenAI 공식 가이드의 프롬프팅 원칙에 맞춰 풀어 쓰고, 모델 선택과 파라미터까지 함께 권합니다.

  • 공식 원칙 기반: 결과물의 용도·구도를 먼저 정하고, 보이는 디테일을 적고, 텍스트는 따옴표로 정확히, 편집은 "바꿀 것"과 "지킬 것"을 분리합니다.
  • 3개 모델 동시 출력: GPT Image 2.5 메인 프롬프트와 함께 같은 의도를 Gemini 3 Pro Image(5-component)와 현재 Midjourney V8(기본 V8.2)의 어조로 변환합니다.
  • 프리셋 + 미세조정: 제품샷·인물·일러스트·풍경 프리셋과 프리셋별 미세조정 질문으로 디테일을 모읍니다.

프롬프트 텍스트만 산출합니다. OpenAI는 ChatGPT Images 2.5의 데스크톱 배포를 안내합니다. ChatGPT Work에서 이미지를 직접 만들 때는 media-codex-image의 현재 세션 경로를 따릅니다. Flare·Sunburst의 정확한 API 모델 ID를 지정하려면 OpenAI API 또는 지원 모델이 확인된 Higgsfield 연결을 사용합니다. 실제 생성 도구의 모델을 확인하지 못했다면 결과에 특정 API 모델 ID를 붙이지 않습니다.

트리거 키워드

GPT 이미지 프롬프트 ChatGPT 이미지 프롬프트 GPT Image 2.5 프롬프트 gpt-image-2.5 Flare Sunburst OpenAI 이미지 프롬프트 GPT 이미지 편집 프롬프트 gpt-image-2 프롬프트

워크플로우

사용자 자연어 한 줄
    ↓
[Round 1] 사용 가능한 질문 경로 — 작업 유형(생성/편집) + 프리셋 선택
    ↓
[Round 2] 사용 가능한 질문 경로 — 프리셋별 미세조정 (필요한 슬롯만)
    ↓
[Round 3] 사용 가능한 질문 경로 — 화면비 · 이미지 내 텍스트 · API 모델(필요할 때만)
    ↓
[내부] 슬롯 → 공식 원칙에 맞춘 프롬프트 (짧은 단락 또는 라벨 섹션)
    ↓
[내부] 같은 슬롯 → Gemini 5-component 변환 + MJ 키워드+파라미터 변환
    ↓
출력: 3개 모델 프롬프트 + 권장 파라미터 + 결과 검수 체크리스트 + 한국어 해설

사용자가 이미 구체적으로 적은 슬롯은 다시 묻지 않습니다. 결과를 바꾸는 정보만 확인합니다.

실행 규칙

Round 1 — 작업 유형과 프리셋 (필수)

이미 주어진 요청에서 생성인지 편집인지, 어떤 프리셋이 맞는지 확인합니다. 결과를 바꾸는 필수 정보가 비어 있으면 직접 실행에서만 현재 앱의 질문 채널을 사용합니다. 하위 에이전트에서는 질문 도구가 보여도 상위에 차단 보고를 반환하고, 직접 실행에 질문 채널이 없어도 필요한 입력을 명시한 차단 보고를 반환합니다. 편집이면 Round 2 대신 편집 워크플로우로 갑니다.

프리셋 적용 케이스 references
제품샷 (권장) 커머스 상품 사진, 패키지 컷, 보석·시계 클로즈업 presets/product-shot.md
인물·캐릭터 인물 포트레이트, 페르소나 일러스트, 광고 모델 presets/portrait.md
일러스트·아트 카드뉴스 일러스트, 책 표지, 컨셉 아트 presets/illustration.md
풍경·환경 배경 이미지, 공간 사진, 시네마틱 배경 presets/landscape.md

Read the full file on GitHub · 248 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. 10d ago Changed · +1 lines 086221b5e26e
  2. 21d ago First seen · 247 lines · 334 tokens per session scan A 00ce24ce1e36

Subscribe to this mod's changes

media-gpt-image-prompt is a skill published in the GitHub repository modu-ai/moai-cowork (308 stars, last pushed 8d ago), licensed Apache-2.0. It adds 334 tokens to every session and 5,414 once invoked, about $0.0013 per session on Opus 5.5. 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 2026-09-26.

Related

Other skills, from other repositories

market-intelligence-report

Produce a Market Intelligence Report — YouTube competitive research, channel analysis, content gap discovery, idea generation, daily scanning, and AI trend scouting — then render it as a BenAI-branded HTML dashboard in the instant-ui design language. Use this skill whenever the user says "market intelligence report"…

naveedharri/benai-skills · 193 tokens

linkedin-writer-vault

Vault-aware LinkedIn writer. Same step-by-step LinkedIn post process as linkedin-writer, but ICP, voice, and offer context come from the vault's Context/ folder instead of being bundled inside the skill. Update one file in the vault and every skill pointing to it inherits the change. TRIGGERS: LinkedIn post, LinkedIn…

naveedharri/benai-skills · 153 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

crm-prospect-mining

Mine high-value prospects from CRM pipeline stages (Lost, No Show, Churned, Stalled) by cross-referencing records with LinkedIn company data and comms history. Connects to any CRM, pulls records from target stages, filters out personal email domains, finds company LinkedIn pages via web research, bulk-scrapes company…

naveedharri/benai-skills · 222 tokens

seo-audit

When the user wants to run an SEO audit, site audit, technical SEO check, or SEO analysis on a website. Also use when the user mentions "Core Web Vitals," "page speed," "performance audit," "broken links," "missing meta tags," "crawl issues," "seomator," "@seomator/seo-audit," "structured data," "schema markup,"…

naveedharri/benai-skills · 131 tokens

seo-sitemap

Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure. Supports sitemap index files and content-type splitting. Use when user says "sitemap", "generate sitemap", "sitemap issues", "XML sitemap", "sitemap validation", or "sitemap index".

naveedharri/benai-skills · 68 tokens