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-videogit 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-video)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/media-higgsfield-video"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-higgsfield-video/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-video"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-higgsfield-video.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 | $0.00242 | $0.02716 |
| Opus 5 | $0.00121 | $0.01358 |
| Sonnet 5 | $0.00048 | $0.00543 |
| Haiku 4.5 | $0.00024 | $0.00272 |
Grade A, and why
media-higgsfield-video 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 8d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield 영상 생성 (media-higgsfield-video)
moai-media| 라이브 카탈로그 기반 영상 생성 (코어:media-higgsfield-core)
개요
Higgsfield MCP의 영상 생성 도구를 호출하는 스킬입니다. 사용자 의도로 계열 후보를 좁힌 뒤 파라미터는 라이브 카탈로그에서 조회해 생성합니다. 이전 스킬의 하드코딩 모델·프리셋 표는 제거되었습니다 — 그 표들은 라이브 스키마와 어긋나 실패하는 호출을 낳았습니다.
핵심 설계는 코어 스킬 media-higgsfield-core에 있습니다: 호출 계약(call-schema.md), 라이브 조회(catalog-protocol.md), 공통 규칙 R1–R5(universal-rules.md), 잡·비용·리드백(job-lifecycle.md).
계열 크래프트 (references/prompt-craft/) — 계열마다 규칙이 다르다
각 파일은 벤더 공식 문서 기반이며 출처·Evidence tier를 답니다.
| 파일 | 계열 |
|---|---|
references/prompt-craft/veo.md |
Veo (오디오 문법 SFX:/Ambient noise:) |
references/prompt-craft/kling.md |
Kling (유연 프레임워크, 1차-relayed) |
references/prompt-craft/seedance.md |
Seedance (타임스탬프 unstable — 라벨 샷 리스트) |
references/prompt-craft/cinema-studio.md |
Cinema Studio (4계층 참조, enum 라이브 조회) |
references/prompt-craft/marketing-studio.md |
Marketing Studio (hook/setting↔ad_reference 상호배타) |
references/prompt-craft/wan.md |
Wan (Timestamp 멀티샷 — Seedance와 정반대) |
references/prompt-craft/gemini-omni.md |
Gemini Omni (편집은 단순 프롬프트) |
references/prompt-craft/grok.md |
Grok (오디오 문서 부재 — 지어내지 않음) |
카메라 디렉팅·Marketing Studio 슬러그 참고: references/dop-motions.md.
범용 비디오 공식은 없다 — per-family 라우팅
단일 범용 비디오 프롬프트 공식을 쓰지 않는다. 벤더마다 컨벤션이 정반대이기 때문이다: Wan은 멀티샷에 명시적 Timestamp를 처방하지만 ByteDance는 Timestamp가 Seedance를 불안정하게 만든다고 경고한다. 이 둘을 하나로 통합하는 것은 correctness 회귀다. 따라서 스킬은 대상 계열의 prompt-craft/ 파일로 per-family(계열별) 라우팅하여 그 계열의 벤더 공식 컨벤션을 적용한다.
워크플로우 (REQ-010 흐름)
1단계 — 의도 파악 → 후보 좁히기
사용자 요청에서 subject·action·scene·camera·audio·references(+각 용도)·shot count·duration 등 슬롯을 수집(→ core interview-schema.md)하고 계열 후보를 좁힙니다. 후보를 좁힐 뿐 파라미터를 단정하지 않습니다. 슬롯이 부족하면 blocker 보고를 반환하고 오케스트레이터가 확인합니다(스킬은 사용자에게 직접 질문하지 않음).
| 사용자 표현 | 후보 계열 |
|---|---|
| "사실적", "오디오 있는 영상" | Veo |
| "인물·표정·스토리보드" | Kling |
| "다이내믹 모션·멀티샷" | Seedance 또는 Wan |
| "영화 룩·모션 전이" | Cinema Studio |
| "UGC·DTC 광고 영상" | Marketing Studio |
| "이미지 편집·간단 참조" | Gemini Omni |
| "Grok 영상" | Grok |
What ships with it
9 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/dop-motions.md 3.3 KB
- references/prompt-craft/cinema-studio.md 2.1 KB
- references/prompt-craft/gemini-omni.md 1.7 KB
- references/prompt-craft/grok.md 2.1 KB
- references/prompt-craft/kling.md 2.5 KB
- references/prompt-craft/marketing-studio.md 2.4 KB
- references/prompt-craft/seedance.md 3.2 KB
- references/prompt-craft/veo.md 2.1 KB
- references/prompt-craft/wan.md 2.5 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.
- 8d ago First seen · 138 lines · 242 tokens per session scan A 4fe8c1d4fd8e
media-higgsfield-video is a skill published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 242 tokens to every session and 2,716 once invoked, about $0.0012 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"…