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.
/plugin marketplace add modu-ai/moai-coworknpx agentmods add plugins/modu-ai/moai-cowork/moai-pmgit 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-pm)<a href="https://agentmods.dev/plugins/modu-ai/moai-cowork/moai-pm"><img src="https://agentmods.dev/badge/plugins/modu-ai/moai-cowork/moai-pm.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
moai-pm 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 yesterday.
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-pm",
"displayName": "🚀 PM",
"version": "1.6.1",
"description": "프로젝트 초기화 허브 AI 코워커 — /project로 진입합니다. Claude Cowork 프로젝트 초기화(전 코워커 지침 설정 + .claude/agents/ 커스텀 에이전트 + AGENTS.md 워크플로우 생성 + 재귀적 자가 개선)를 담당하며 AI 코워커 플러그인 패밀리의 진입을 라우팅합니다. 비개발자도 자연어 한마디로 프로젝트를 시작할 수 있습니다. 이런 분께 추천: 비개발자·프로젝트 시작자.",
"author": {
"name": "모두의 AI",
"email": "[email protected]"
},
"keywords": [
"moai",
"pm",
"project",
"허브",
"라우터",
"초기화"
],
"license": "Apache-2.0"
}
What it installs
The manifest is a name and a version. 1 skill, 1 command travel with it, and installing the plugin installs all of them — 522 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday First seen · 20 lines scan A df3cff500c22
moai-pm is a plugin published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 2d 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
foundation
revenantworks-foundation — ten standalone wrights for building, auditing, and maintaining skills, prompts, messages, agent specs, standing Claude configuration, research docs, eval suites, brand identity, token budgets, and multi-agent fan-out dispatch.
claudit
Audit and optimize your Claude Code configuration. Caches current Claude Code ecosystem knowledge so any subsequent agent task — building a skill, configuring an MCP, authoring CLAUDE.md — can read it instead of re-fetching docs.
gamedev
revenantworks-gamedev — game-development skills on the -smith motif. First member: pixelsmith, art direction for pixel art that must read at several zoom scales at once.
brevity
Claude Code says less, and says it straight. Short replies, no jargon, no preamble. Applies ASD-STE100 Simplified Technical English to long replies.
local-ai
From nothing to a working AI setup you own. Scans the machine for models that fit, installs and wires up the right app with consent at every download, shares it over a private URL, and rents a cloud GPU when a model is too big. Needs shell access.
desktop-notification
Alert you when Claude Code needs input — an audible terminal bell, an OSC 9 terminal notification, and an OS-native toast (macOS/Linux) on permission and idle prompts.