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.
git 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/plugins/modu-ai/moai-cowork/moai-media)<a href="https://agentmods.dev/plugins/modu-ai/moai-cowork/moai-media"><img src="https://agentmods.dev/badge/plugins/modu-ai/moai-cowork/moai-media.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
moai-media 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 4d 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.
What it actually says
{
"name": "moai-media",
"displayName": "🎬 미디어 크리에이터",
"version": "1.3.0",
"description": "미디어 생성 전담 AI 코워커 — 이미지·영상·오디오 생성(media-* 13종) 스킬. Higgsfield 이미지·영상·3D·설명영상·제품촬영·캐릭터 일관성(Soul/Element), ElevenLabs TTS/보이스클로닝, GPT-image-2·Gemini 3·Midjourney v8 프롬프트 빌더, codex/NotebookLM 연동까지 멀티모달 생성 도구 모음. 자연어 요청 시 매칭 스킬이 자동 호출됩니다. 이런 분께 추천: 콘텐츠 크리에이터·마케터·디자이너·1인 브랜드.",
"author": {
"name": "모두의 AI",
"email": "[email protected]"
},
"license": "Apache-2.0",
"userConfig": {
"ELEVENLABS_API_KEY": {
"type": "string",
"title": "ElevenLabs API 키",
"description": "elevenlabs.io/app/settings/api-keys 에서 발급합니다.",
"sensitive": true
}
}
}
What it installs
The manifest is a name and a version. 14 skills, 2 agents travel with it, and installing the plugin installs all of them — 3,695 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill media-audio-gen A 99 tokens
- Skill media-higgsfield-explainer A 236 tokens
- Skill media-gemini-3-image-prompt A 307 tokens
- Skill media-gpt-image-2-prompt A 278 tokens
- Skill media-higgsfield-identity A 255 tokens
- Skill media-notebooklm-slide-prompt A 329 tokens
- Skill media-higgsfield-video A 242 tokens
- Skill media-midjourney-v8-prompt A 353 tokens
- Skill media-higgsfield-image A 256 tokens
- Skill media-higgsfield-product A 286 tokens
- Skill media-higgsfield-assets A 293 tokens
- Skill media-higgsfield-core A 197 tokens
- Skill media-asset-production A 67 tokens
- Skill media-codex-image B 259 tokens
- Agent media-producer A 117 tokens
- Agent media-brand-auditor A 121 tokens
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.
- 4d ago First seen · 20 lines scan A 6a0183ba13cd
moai-media is a plugin published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 4d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
content
A modular content engine, one skill per job: /research a topic, turn it into a /linkedin post and a /newsletter in Ben's voice, then generate on-brand /visual graphics to match.
fakoli-speak
Multi-provider text-to-speech with owned playback, opt-in autospeak, and local cost estimates.
excalidraw-diagram
Generate and modify Excalidraw diagrams from natural language descriptions and code analysis.
imagine-mcp
Image/video understanding & generation across Gemini, OpenAI, Grok.
app-icon-generator
Generate app icon assets for iOS, macOS, Android, and web from a source image using ImageMagick.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.