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 crealwork/ai-marketing-kit --skill image-gengit clone --depth 1 https://github.com/crealwork/ai-marketing-kitWrote 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/crealwork/ai-marketing-kit/image-gen)<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/image-gen"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/image-gen/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/crealwork/ai-marketing-kit/image-gen"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/image-gen.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 | $0.00113 | $0.01522 |
| Opus 5 | $0.00056 | $0.00761 |
| Sonnet 5 | $0.00023 | $0.00304 |
| Haiku 4.5 | $0.00011 | $0.00152 |
Grade A, and why
image-gen 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(`encoding='utf-8-sig'`). 다운로드는 Python `urllib.request.urlretrieve` How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Gen
마케팅 이미지·AI 영상 생성의 단일 창구. 모든 생성은 Higgsfield CLI 경유 — 모델 카탈로그(gpt_image_2, FLUX 계열, 시네마틱/영상 모델)를 한 계정으로 쓴다. 기본 이미지 모델은 gpt_image_2 (텍스트/워드마크 재현 강함).
Hard rules
- Higgsfield가 유일한 생성 경로. 직접 API 호출은 힉스필드가 불가능한 환경에서만 (부록), 그것도 유저에게 알리고.
- 생성 전 계정 확인 필수:
higgsfield account status— 계정 이메일과 크레딧을 확인하고 시작한다. 잘못된 계정의 지출은 되돌릴 수 없다. - 기본 모델 = gpt_image_2. 다른 모델(FLUX 등)은 유저 지정 또는 스타일 특성상
필요할 때 —
higgsfield model list --image로 카탈로그 확인. 실패 시 다른 모델로 말없이 전환 금지 — 보고하고 유저가 결정. - 변형은 기본 복수 생성: 용도당 최소 3개 (구도/톤/컨셉 다르게). 광고 소재는 A/B 전제 — 4개+ (훅 축 × 비주얼 축). 1장 생성은 이 스킬 위반.
- 생성 후 눈으로 검증: 각 결과를 READ — 이미지 속 텍스트는 글자 단위로, 손가락/로고 왜곡, 브랜드 컬러. 텍스트가 핵심인 이미지는 텍스트를 굽지 말고 HTML/PIL 오버레이가 기본. (예외: 유튜브 썸네일은 thumbnail-maker 룰대로 문구 포함 통생성이 기본 — gpt_image_2가 텍스트 렌더에 강해서.)
- 실존 인물은 유저 제공 사진 기반(
--image레퍼런스)만 — 얼굴을 지어내지 않는다. - Windows에서 CLI는 전체 경로로:
%APPDATA%\npm\higgsfield.cmd.
Setup (1회)
npm i -g @higgsfield/cli # Node 필요
higgsfield auth login # 브라우저 로그인
higgsfield account status # VERIFY: 이메일 + 크레딧
higgsfield model list --image # 카탈로그 확인 (gpt_image_2 포함)
생성
# 텍스트 → 이미지
higgsfield generate create gpt_image_2 \
--prompt "<장면 서술>" --aspect_ratio 16:9 --quality high --resolution 2k \
--wait --json
# 이미지 입력 (실물 사진/디자인 레퍼런스 — 목업 합성, 인물 유지)
higgsfield generate create gpt_image_2 --image ./reference.png \
--prompt "<이 이미지를 정확히 유지한 채 ...>" --aspect_ratio 9:16 \
--quality high --resolution 2k --wait --json
- 결과 파싱: 출력은 pretty-print JSON —
result_url키를 믿지 말고 stdout 전체를json.loads후 재귀로 이미지 URL을 전부 수집, 입력 레퍼런스가 올라간 호스트를 제외한 URL이 결과물. 파일로 저장한 출력은 BOM이 붙는다 (encoding='utf-8-sig'). 다운로드는 Pythonurllib.request.urlretrieve(Windows curl 인코딩 함정 회피). - 일시적 502 → 1회만 재시도. 반복 실패는 보고.
- 레퍼런스 충실도가 중요한 합성은 프롬프트에 "reproduce EXACTLY as provided, same layout/text/colors, no redesign" 를 명시 — 그래도 잔글씨는 근사치임을 유저에게 고지 (정본은 원본 파일).
- AI 영상 클립:
higgsfield model list --video로 모델 확인 후 동일 패턴 — 편집/합성 파이프라인은 ad-video·hyperframes가 소유.
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.
- 9d ago First seen · 90 lines · 113 tokens per session scan A 70fe8487ea9e
image-gen is a skill published in the GitHub repository crealwork/ai-marketing-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 1,522 once invoked, about $0.0006 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.
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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.