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 amondnet/yoonmoonnpx agentmods add plugins/amondnet/yoonmoon/yoonmoongit clone --depth 1 https://github.com/amondnet/yoonmoonGrade A, and why
yoonmoon 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": "yoonmoon",
"version": "0.2.1",
"description": "한글 글다듬기·탐지 도구 모음 — 전과정 윤문 풀코스(polish-all), AI 글 윤문(humanize), AI 작성 판별(detect), 번역투 교정(translate-polish), 맞춤법·문법 교정(proofread), 문체·톤 변환(restyle). 내용은 보존하고 문체·리듬만 다듬으며, 11대 AI 티 분류와 한국 번역학·KatFishNet(ACL 2025) 근거를 공유한다.",
"author": {
"name": "Minsu Lee",
"email": "[email protected]",
"url": "https://github.com/amondnet"
},
"homepage": "https://github.com/amondnet/yoonmoon",
"repository": "https://github.com/amondnet/yoonmoon",
"license": "MIT",
"keywords": [
"korean",
"humanize",
"ai-detector",
"translationese",
"proofreading",
"tone",
"윤문",
"번역투",
"맞춤법",
"문체변환"
],
"skills": [
"./skills/"
]
}
What ships with it
1 file beside plugin.json 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.
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 · 29 lines scan A 9b8ba43339cd
yoonmoon is a plugin published in the GitHub repository amondnet/yoonmoon (10 stars, last pushed 11d ago), licensed MIT. 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 2026-08-31.
Other plugins, from other repositories
im-not-ai
Plugin marketplace listing 1 plugin: humanize-korean.
im-not-ai
AI가 쓴 한글 텍스트를 사람이 쓴 글처럼 윤문 — routehint 3경로(light 1콜 · standard 2콜 · heavy 3+콜). 10대 카테고리 70 AI 티 패턴 탐지·재작성.
fluent-korean
Claude Code가 유창하고 자연스러운 한국어로 응답하게 하는 출력 스타일. 코딩 지침을 유지하는 판과 유지하지 않는 판 두 가지를 제공합니다.
create-retro-game-kr-patch
레트로 게임(게임보이·NES·SNES·메가드라이브·새턴·PS1·드림캐스트·PC엔진·PC-98·게임기어 등) 한글 패치 제작 전 과정을 다루는 Agent Skill. ROM/디스크 분석부터 폰트·인코딩 설계, PoC, 추출·번역·재삽입, 빌드, 에뮬레이터 검증까지.
kr-patch
레트로 게임 한글 패치 제작 방법론 Agent Skill.
mario-montanari-skills
Le skill pubbliche di Mario Montanari per Claude Code e Claude Cowork.