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-coworker)<a href="https://agentmods.dev/plugins/modu-ai/moai-cowork/moai-coworker"><img src="https://agentmods.dev/badge/plugins/modu-ai/moai-cowork/moai-coworker/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/plugins/modu-ai/moai-cowork/moai-coworker"><img src="https://agentmods.dev/badge/plugins/modu-ai/moai-cowork/moai-coworker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
moai-coworker 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 6d 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-coworker",
"displayName": "🧑💼 코워커",
"version": "1.2.0",
"description": "실무 범용 코어 AI 코워커 — 브랜드·제안서·보고·협상·프로세스 등 비즈니스 실무 + 라이프스타일·자기계발(목표·습관·회고·여행·웰니스·행사기획) 스킬 32종. 전문 영역은 전문가 플러그인(작가·스토리·마케터·미디어·셀러·사무관·데이터 애널리스트·법무·재무·인사·튜터·CS·컨설턴트·커리어코치)으로 분리되었으며, 코워커는 범용 비즈니스 코어와 생활 도메인을 담당합니다. 자연어 요청 시 매칭 스킬이 자동 호출됩니다. 이런 분께 추천: 1인 사업자·스타트업 운영자.",
"author": {
"name": "모두의 AI",
"email": "[email protected]"
},
"keywords": [
"moai",
"cowork",
"coworker",
"korean",
"all-in-one",
"통합",
"비즈니스",
"라이프스타일",
"자기계발"
],
"license": "Apache-2.0",
"mcpServers": "./.mcp.json",
"userConfig": {
"DART_API_KEY": {
"type": "string",
"title": "OpenDART 인증키",
"description": "opendart.fss.or.kr 회원가입 후 인증키 신청 — 이메일로 즉시 발급되는 40자 키입니다. 하루 20,000건 무료.",
"sensitive": true
}
}
}
What it installs
The manifest is a name and a version. 32 skills travel with it, and installing the plugin installs all of them — 5,174 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ai-slop-reviewer A 263 tokens
- Skill collab-sales-playbook A 179 tokens
- Skill collab-pm-report A 205 tokens
- Skill meta-skill-builder A 157 tokens
- Skill meta-skill-tester A 191 tokens
- Skill ai-diagnostic A 151 tokens
- Skill collab-exec-summary A 340 tokens
- Skill collab-proposal A 312 tokens
- Skill collab-process A 97 tokens
- Skill collab-vendor A 93 tokens
- Skill personal-wellness A 102 tokens
- Skill collab-status-report A 93 tokens
- Skill meta-feedback A 125 tokens
- Skill personal-event A 90 tokens
- Skill personal-travel A 217 tokens
- Skill meta-skill-template A 108 tokens
- Skill collab-brand-identity A 283 tokens
- Skill collab-conflict A 126 tokens
- Skill collab-feedback-loop A 127 tokens
- Skill collab-meeting A 125 tokens
- Skill collab-negotiation A 132 tokens
- Skill collab-report-speak A 123 tokens
- Skill collab-ux-design A 235 tokens
- Skill collab-productivity-report A 118 tokens
- Skill collab-roadmap A 224 tokens
- Skill collab-spec A 180 tokens
- Skill collab-ux-research A 230 tokens
- Skill personal-self-care A 116 tokens
- Skill productivity-goal A 122 tokens
- Skill productivity-habit A 116 tokens
- Skill productivity-retro A 119 tokens
- Skill ai-prompting-basics A 75 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.
- 6d ago Changed · +8 lines f5cfb19e1626
- 11d ago First seen · 24 lines scan A 7c979c2d4728
moai-coworker is a plugin published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 7d 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 2026-08-30.
Other plugins, from other repositories
agentic-os
Set up an agentic OS — inside an Obsidian vault (command-center dashboard + bundled plugins) or as a standalone Next.js web dashboard with live MCP integrations and optional Railway deploy. Includes /os-mcp to self-host the Relay MCP server.
gws
Operate across all Google Workspace services using the gws CLI — 100 skills, 15 slash commands, 11 role-based agents, and 44 automation recipes covering email, calendar, drive, docs, sheets, slides, tasks, chat, meet, forms, classroom, keep, people, events, admin reports, model armor, and apps script.
evernote
Evernote integration - notes, notebooks, and research management.
toggl
Toggl time tracking - manage time entries and generate reports.
better-email-mcp
Email management via IMAP/SMTP — multi-account.
better-notion-mcp
Markdown-first Notion API integration — 8 composite tools, 95% coverage.