media-higgsfield-identity

media-higgsfield-identity is a skill for Claude Code from modu-ai/moai-cowork. It costs 255 tokens per session (4,536 once invoked), scanned A, original, Apache-2.0.

A Higgsfield workflow for keeping a person, character, product, or other visual reference consistent across generated images. It chooses between a trained identity model and a one-image reference method.

In plain words
What is it for?
Use it to create a reusable digital likeness, keep one character consistent, place the same product in several images, or list saved identity references.
Why use it?
It helps avoid repeatedly re-creating the same subject from scratch, while making the trade-off between training time and immediate references clear.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; mentions Codex.

Part of the moai-media plugin — 14 skills, 2 agents shipped together

Good fit Use it to create a reusable digital likeness, keep one character consistent, place the same product in several images, or list saved identity references.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/modu-ai/moai-cowork/media-higgsfield-identity
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-higgsfield-identity
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 14 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-higgsfield-identity

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/media-higgsfield-identity"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/media-higgsfield-identity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 255 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,536 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00255 $0.04536
Opus 5 $0.00128 $0.02268
Sonnet 5 $0.00051 $0.00907
Haiku 4.5 $0.00026 $0.00454

Measured 8d ago against content hash 8317af412855, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

media-higgsfield-identity 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.

plugins/moai-media/skills/media-higgsfield-identity/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Higgsfield 일관성 참조 (media-higgsfield-identity)

moai-media | Soul Character · Reference Element 판정과 생성 (코어: media-higgsfield-core)

개요

"같은 인물·같은 캐릭터·같은 제품이 여러 컷에 일관되게 나오게" 하는 두 가지 수단을 다룬다. 두 수단은 대체재가 아니라 서로 다른 제약을 가진 별개 경로이며, 잘못 고르면 학습 시간과 크레딧을 버린다.

호출 계약·namespace 런타임 해석·비용 프리플라이트는 코어를 따른다:

  • 호출 계약: ../media-higgsfield-core/references/call-schema.md
  • 라이브 조회: ../media-higgsfield-core/references/catalog-protocol.md
  • 잡·비용·리드백: ../media-higgsfield-core/references/job-lifecycle.md

트리거 키워드

Soul, Soul ID, 소울, 디지털 트윈, 캐릭터 학습, 얼굴 학습, identity, 캐릭터 일관성, Element, 레퍼런스 엘리먼트, 참조 요소, 재사용 캐릭터, 같은 인물, 같은 제품

두 경로 비교 (판정의 근거)

Soul Character Reference Element
만드는 방법 5~20장 학습 (약 10분, 비차단) 이미지 1장으로 즉시 생성 (동기)
한 생성에 몇 개 1개만 여러 개 (<<<id>>> 다중 배치)
대상 사람 1인 사람·환경·소품 모두
사용 가능 모델 soul_2, soul_cinematic 전용 Nano Banana 계열·GPT Image 2·Seedream·Cinema Studio·Seedance·Kling 등
identity 충실도 높음 (전용 학습) 보통 (참조 주입)
되돌리기 학습 비용 발생 후 비용 거의 없음

상세 판정 규칙과 지원 모델 전체 목록은 references/soul-vs-elements.md.

판정 워크플로우

0단계 — 사람이 찍힌 사진인가 (경로 판정보다 먼저)

[HARD] 얼굴 동의 게이트는 Soul/Element 분기보다 앞에 있다. 사람이 찍힌 사진을 서버로 올리는 일은 어느 경로를 타든 같은 일이며, 경로는 그 뒤에 정한다.

이 순서가 뒤집히면 게이트에 구멍이 난다. Element로 확정되는 신호에는 **"가진 이미지가 1장뿐"**과 **"지금 바로·빨리"**가 들어 있다(1단계). 즉 제3자 얼굴 사진 한 장을 급히 올리는 요청이 정확히 Element로 분기하는데, 게이트가 Soul 쪽에만 있으면 그 요청은 아무 확인 없이 업로드된다. 가장 위험한 입력이 게이트를 비켜 가는 구조였다.

게이트가 걸리는 조건: 업로드할 이미지에 사람 얼굴이 있다. 사람이 아닌 대상(제품·소품·배경·로고)만 있으면 이 게이트는 지나가고 1단계로 간다.

  • [HARD] 사람 사진이 하나라도 섞였으면 media_upload 전에 멈춘다. Soul이든 Element든, 1장이든 20장이든 같다.
  • [HARD] 승인과 동의는 다른 문항이다. 아래 §게이트 1의 두 문항을 그대로 쓴다.
  • 동의를 확보하지 못했으면 업로드하지 않고 종료한다. 경로 판정으로 넘어가지 않는다.

Element 경로라고 위험이 줄지 않는다. 학습은 없지만 그 사람의 얼굴이 서버로 가고, 그 얼굴로 이미지가 생성된다. 되돌릴 수 없다는 성질은 같다.

1단계 — 경로 판정 (0단계를 통과한 뒤)

아래 신호로 경로를 가른다. 어느 쪽도 확실하지 않으면 생성하지 않고 blocker를 반환한다 — 오케스트레이터가 사용자에게 확인한다. 이 스킬은 사용자에게 직접 질문하지 않는다.

Element로 확정되는 신호 (하나라도 걸리면 Element):

  • 한 컷에 인물/대상이 2명 이상 ("나랑 친구", "두 사람이")
  • 대상이 사람이 아님 (제품·소품·배경·로고)
  • 가진 이미지가 1장뿐
  • Nano Banana·Seedream·Kling·Cinema Studio 등 soul 계열이 아닌 모델을 지목
  • "지금 바로", "빨리" 등 즉시성 요구

Read the full file on GitHub · 217 lines

Files

What ships with it

2 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. 8d ago First seen · 217 lines · 255 tokens per session scan A 8317af412855

Subscribe to this mod's changes

media-higgsfield-identity is a skill published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 255 tokens to every session and 4,536 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.

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

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…

naveedharri/benai-skills · 156 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-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"…

naveedharri/benai-skills · 88 tokens