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 modu-ai/moai-cowork --skill media-higgsfield-imagegit clone --depth 1 https://github.com/modu-ai/moai-coworkWrote 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/modu-ai/moai-cowork/media-higgsfield-image)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/media-higgsfield-image"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-higgsfield-image/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/modu-ai/moai-cowork/media-higgsfield-image"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-higgsfield-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00256 | $0.02476 |
| Opus 5 | $0.00128 | $0.01238 |
| Sonnet 5 | $0.00051 | $0.00495 |
| Haiku 4.5 | $0.00026 | $0.00248 |
Grade A, and why
media-higgsfield-image 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 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.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield 이미지 생성 (media-higgsfield-image)
moai-media| 라이브 카탈로그 기반 이미지 생성 (코어:media-higgsfield-core)
개요
Higgsfield MCP의 이미지 생성 도구를 호출하는 스킬입니다. 사용자 자연어 요청에서 의도를 추출하고, 계열 크래프트로 후보를 좁힌 뒤, 파라미터는 라이브 카탈로그에서 조회해 생성합니다. 이전 스킬이 갖고 있던 하드코딩 모델 표·파라미터 표는 제거되었습니다 — 그 표들은 라이브 스키마와 어긋나 실패하는 호출을 낳았습니다.
핵심 설계는 코어 스킬 media-higgsfield-core에 있습니다:
- 호출 계약:
../media-higgsfield-core/references/call-schema.md - 라이브 조회 프로토콜:
../media-higgsfield-core/references/catalog-protocol.md - 공통 규칙 R1–R5:
../media-higgsfield-core/references/universal-rules.md - 잡·비용·리드백:
../media-higgsfield-core/references/job-lifecycle.md
트리거 키워드
Higgsfield 이미지, Soul, Nano Banana, Nano Banana Pro, GPT Image, Seedream, FLUX, Recraft, Marketing Studio, DTC 광고 이미지, AI 이미지 생성, 시네마틱 이미지, 캐릭터 일관성
계열 크래프트 (references/prompt-craft/)
각 파일은 벤더 공식 문서 기반이며 출처·Evidence tier를 답니다. 파라미터가 아니라 프롬프트 크래프트만 다룹니다.
| 파일 | 계열 |
|---|---|
references/prompt-craft/soul.md |
Soul (공식 프롬프트 공식 부재 → R1–R5 폴백) |
references/prompt-craft/nano-banana.md |
Nano Banana (Google 5-part 공식) |
references/prompt-craft/openai.md |
GPT Image (openai_hazel 매핑은 unverified) |
references/prompt-craft/seedream.md |
Seedream (ByteDance 5원칙) |
references/prompt-craft/flux.md |
FLUX (어순 load-bearing, 부정 프롬프트 없음) |
references/prompt-craft/recraft.md |
Recraft (global-to-local, 벡터/로고) |
references/prompt-craft/marketing-studio.md |
Marketing Studio / DTC Ads (style 선택 워크플로) |
워크플로우 (REQ-010 흐름)
1단계 — 의도 파악 → 후보 좁히기
사용자 요청에서 subject·용도·톤·리터럴 텍스트 등 슬롯을 수집(→ core interview-schema.md)하고, 계열 크래프트로 후보 모델을 좁힙니다. 이 단계는 후보를 좁힐 뿐 파라미터를 단정하지 않습니다. 슬롯이 부족하면 스킬은 blocker 보고를 반환하고, 오케스트레이터가 사용자에게 확인합니다(스킬은 사용자에게 직접 질문하지 않음).
후보 좁히기 힌트(파라미터가 아니라 계열 선택 힌트):
| 사용자 표현 | 후보 계열 |
|---|---|
| "글자 정확하게", "포스터", "카드뉴스" | GPT Image 또는 Nano Banana Pro |
| "시네마틱", "인물 디테일", "캐릭터 일관성" | Soul |
| "사진처럼", "사실적", "제품 샷" | FLUX |
| "예술적", "독특한 톤" | Seedream |
| "로고", "아이콘", "벡터" | Recraft |
| "DTC 광고", "제품 광고 포맷" | Marketing Studio (ms_image) |
What ships with it
7 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.
- references/prompt-craft/flux.md 2.6 KB
- references/prompt-craft/marketing-studio.md 2.0 KB
- references/prompt-craft/nano-banana.md 2.4 KB
- references/prompt-craft/openai.md 2.4 KB
- references/prompt-craft/recraft.md 2.3 KB
- references/prompt-craft/seedream.md 2.2 KB
- references/prompt-craft/soul.md 3.3 KB
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 · 137 lines · 256 tokens per session scan A 1d070697e032
media-higgsfield-image is a skill published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 256 tokens to every session and 2,476 once invoked, about $0.0013 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 2026-09-03.
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"…
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…
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…
operator
Build and schedule a personalized Operator prompt that runs a Baalda vault as a second brain on a recurring cadence. Run it from inside the vault: it reads Context/ and CLAUDE.md first to infer org, team, brand voice and paths, then asks only the gaps (cadence, connectors, DM recipient, budgets, signature), writes the…
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…
seo-hreflang
Hreflang and international SEO audit, validation, and generation. Detects common mistakes, validates language/region codes, and generates correct hreflang implementations for HTML, HTTP headers, and XML sitemaps. Use when user says "hreflang", "i18n SEO", "international SEO", "multi-language", "multi-region"…