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 devswha/patinanpx agentmods add plugins/devswha/patina/marketplacegit clone --depth 1 https://github.com/devswha/patinaGrade A, and why
patina 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 2d 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
{
"$schema": "https://www.schemastore.org/claude-code-marketplace.json",
"name": "patina",
"description": "patina — a deterministic, auditable AI-writing humanizer for Korean, English, Chinese, and Japanese.",
"owner": {
"name": "devswha",
"url": "https://github.com/devswha"
},
"plugins": [
{
"name": "patina",
"source": "./",
"version": "7.1.0",
"description": "Strip the AI packaging, keep the meaning. Detect and rewrite AI writing patterns across KO/EN/ZH/JA with MPS/fidelity checks. Runs the root SKILL.md as the /patina skill.",
"homepage": "https://github.com/devswha/patina",
"repository": "https://github.com/devswha/patina",
"license": "MIT",
"keywords": [
"humanize",
"ai-writing",
"ai-detector",
"translationese",
"korean",
"english",
"chinese",
"japanese",
"윤문",
"번역투"
]
}
]
}
What ships with it
1 file beside marketplace.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.
- 2d ago First seen · 33 lines scan A 16d7ef2e00f8
patina is a plugin published in the GitHub repository devswha/patina (328 stars, last pushed 2d 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 2026-08-30.
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.
humanizer-zh-tw
humanizer-zh-tw 技能，可作為 Claude Code 外掛安裝。.
humanizer-zh-tw
去除文字中的 AI 生成痕跡，讓繁體中文讀起來更自然、更像真人書寫。基於 blader/humanizer，針對台灣繁體中文在地化，共 46 種模式。.
ilyautov-plugins
Plugins by Ilya Utov: humanizer-ru kills AI smell in Russian text | Плагины Ильи Утова: humanizer-ru убирает следы нейросети из русского текста.
humanizer
Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when…