agentmods.dev

image-prompt

image-prompt is a skill for Claude Code, Codex from daeryundf2-prog/LAZYANTIGRAVITY. It costs 651 tokens per session (6,148 once invoked), scanned A, original, MIT.

A Korean-language skill that turns a rough image idea into a detailed prompt for gpt-image-2, OpenAI’s image-generation model.

In plain words
What is it for?
Writing image-generation prompts for photos, cinematic artwork, presentations, promotional graphics, and other visual formats.
Why use it?
It gives an incomplete visual request a consistent structure, including style, layout, colors, text, and restrictions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex; $skill-name invocation.

not rated 14repo 7d ago A scan 651 tokens original MIT

Good fit Writing image-generation prompts for photos, cinematic artwork, presentations, promotional graphics, and other visual formats.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/daeryundf2-prog/lazyantigravity/image-prompt
View source ↗ daeryundf2-prog/LAZYANTIGRAVITY
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 daeryundf2-prog/LAZYANTIGRAVITY --skill image-prompt
Clone the repo
git clone --depth 1 https://github.com/daeryundf2-prog/LAZYANTIGRAVITY

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 image-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/image-prompt/github.svg)](https://agentmods.dev/skills/daeryundf2-prog/lazyantigravity/image-prompt)
Your own site
<a href="https://agentmods.dev/skills/daeryundf2-prog/lazyantigravity/image-prompt"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/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 image-prompt

Your own site · 80×15
<a href="https://agentmods.dev/skills/daeryundf2-prog/lazyantigravity/image-prompt"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/image-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 651 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,148 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 $0.00651 $0.06148
Opus 5.5 $0.00260 $0.02459
Sonnet 5.5 $0.00130 $0.01230
Haiku 4.5 $0.00065 $0.00615

Measured 1mo ago against content hash 19389ceb1acb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_prompt.mjs), 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.

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.

shared-skills/skills/image-prompt/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🐾 공냥 프롬프트 킷 VOL.2 — gpt-image-2 프롬프트 컴파일러

거칠고 모호한 요청을 다운스트림 이미지 툴($imagegen)에 넘길 완성 한국어 프로덕션 프롬프트로 바꾼다. 이미지를 직접 생성하지는 않는다(생성·양산은 [codex-imagegen]). 깊은 내용은 필요할 때 references/를 읽는다.

워크플로우

  1. 거친 요청에서 빠진 결정(카테고리·컷타입·피사체·스타일·구도·텍스트·AR)을 추론해 채운다. 취향 디테일은 묻지 말고 결정. 묻는 건 정확한 한글 문구·브랜드명·민감 소재 정도.
  2. 카테고리/컷타입이 잡히면 references/category-patterns.md(C1~C12)를 본다. 포맷 라우팅(아래 §포맷 A/포맷 B)으로 A/B를 정한다. 무드 요청("있어보이게"·"럭셔리하게"·"영화처럼")은 references/look-presets.md에서 프리셋 1개를 골라 드롭인. 홍보판촉물·홍보이미지·브랜드 포스터 요청("홍보물 뽑아줘"·"판촉물 느낌"·"디자인 잘된 포스터")은 references/promo-router.md에서 패턴 1개를 고르고 해당 references/promo/Pn-*.md 하나만 읽어 레이아웃 골격으로 — 카드뉴스 밀도 문법으로 홍보물을 만들면 미감이 죽는다(C7 미감 라우팅 2모드). 시안 다변화·양산 컨셉·"차별화되게"·"컨셉부터" 요청은 references/concept-axes.md의 변수 축(사조 M·몸 반응 R·모순쌍 X·타이포 아트 T·컬러 번역)에서 축 1개를 골라 변주.
  3. 아래 철칙을 지켜 작성, 끝에 AR 토큰.
  4. 고가치 산출물은 응답 전 node scripts/check_prompt.mjs <file>로 검증(ok:true 확인).
  5. 생성으로 이어지면 컴파일된 프롬프트만 넘긴다(거친 원문은 안 넘김).

거친 입력 확장 예: "포스터 하나"→C3(타이틀 위계·여백·팔레트·AR), "화보 한 장"→C1 포맷 B(단독 인물 플랫 단문), "드라마 키아트"→C11(타이틀 negative space·장르 광 레시피), "귀여운 아이콘"→C9(오브젝트·재질·베벨·배경, "텍스트 없음"), "제품 소개"→C4(히어로·콜아웃·리더선), "만화 느낌"→C10(패널·거터·말풍선·선화), "발표자료/피피티"→C12(덱 DNA 블록·16:9 고정·슬라이드 타입·룩 프리셋).

출력 계약: 단일 요청 → 본문 + 끝 AR x:y만(설명 없이). 다중 → 엔트리당 Title / Category(Cn) / Cut type / Prompt. 생성 요청 → 조용히 컴파일 후 이미지 툴 호출.

철칙 — 절대 어기지 말 것

  1. 앞머리 [AR x:y SIZE wxh] 브래킷 금지. size는 API 파라미터(jsonl size)로만. 프롬프트엔 끝에 AR x:y 토큰 하나만. 슬롯 토큰 [PERSONA_LOCK] 류는 작성 단계 전용 — 최종 프롬프트에 브래킷이 잔존하면 실격(검증기 E-SLOT-LEAK).

  2. 네거티브 기본 금지 + 화이트리스트 2종. gpt-image-2는 장면 네거티브를 오히려 렌더한다 → 장면 배제는 여전히 전부 긍정형(군중→"프레임 안엔 인물 한 명, 단독", 배경→"깨끗한 단색 배경", 워터마크→"브랜드 없는 클린 마감"). 예외는 아래 두 레인뿐이며, 이는 우회가 아니라 컴플라이언스 스티어링(정책 적합성을 프롬프트에 명시)이다.

    티어 조건 허용 문구
    Tier-0 기본 항상 all-positive. 부정문 0개
    Tier-1 텍스트 렌더 가드 렌더 텍스트(따옴표 카피)가 실제로 있을 때만 화이트리스트 7종: no extra words · no duplicate text · no invented glyphs · no watermark · no logo · no extra text · verbatim, no extra characters
    Tier-2 화보 컴플라이언스 레인 명시 선언 시만(휴리스틱 승격 금지) SAFETY_ASSERT(긍정형, 피사체절) + NEGATIVE_TAIL(AR 직전 정확히 1회) 페어 — 고정 문자열, 상세 references/editorial-hwabo.md

Read the full file on GitHub · 144 lines

Files

What ships with it

51 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.

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. 1mo ago First seen · 144 lines · 651 tokens per session scan A 19389ceb1acb

Subscribe to this mod's changes

image-prompt is a skill published in the GitHub repository daeryundf2-prog/LAZYANTIGRAVITY (14 stars, last pushed 7d ago), licensed MIT. It adds 651 tokens to every session and 6,148 once invoked, about $0.0026 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 2026-08-30.

Creative and mediaData and AIPromptingTypeScriptagentic-codingai-agentautomationdeveloper-toolslazycodex
Related

Other skills, from other repositories

developing-genkit-js

Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.

google/skills · 60 tokens

ax-gen

This skill helps an LLM generate correct AxGen code using @ax-llm/ax. Use when the user asks about ax(), AxGen, generators, forward(), streamingForward(), validation, assertions, streaming assertions, field processors, step hooks, self-tuning, or structured outputs. For MCP clients, transports, prompts, resources…

ax-llm/ax · 86 tokens

ax-signature

This skill helps an LLM generate correct DSPy signature code using @ax-llm/ax. Use when the user asks about signatures, s(), f(), field types, string syntax, fluent builder API, validation constraints, or type-safe inputs/outputs.

ax-llm/ax · 57 tokens

ax-playbook

This skill helps an LLM generate correct playbook code using @ax-llm/ax. Use when the user asks about playbook(), AxPlaybook, context playbooks, evolving context, ACE / Agentic Context Engineering, agent.playbook(), or growing/applying task knowledge offline and online with evolve() and update().

ax-llm/ax · 70 tokens

ax-llm

Build or debug TypeScript LLM applications with @ax-llm/ax. Use for Ax providers, structured generation, signatures, agents and tools, memory, MCP, workflows, audio, and optimization.

ax-llm/ax · 47 tokens

ax-refine

Use this skill when writing or reviewing Ax bestOfN/refine code, reward functions, thresholds, native sample selection, serial attempts, generated advice, and attempt diagnostics.

ax-llm/ax · 38 tokens