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 talkstream/ru-textnpx agentmods add plugins/talkstream/ru-text/marketplacegit clone --depth 1 https://github.com/talkstream/ru-textGrade A, and why
ru-text 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
{
"name": "ru-text",
"metadata": {
"description": "Russian text quality for AI agents — neuroslop cleanup, typography, information style, editorial standards, UX writing, business correspondence. Scores text 0–10. 2,000+ linguistic atoms.",
"version": "2.7.0"
},
"owner": {
"name": "Arseniy Kamyshev",
"email": "[email protected]",
"url": "https://t.me/nafigator"
},
"plugins": [
{
"name": "ru-text",
"displayName": "ru-text",
"source": "./",
"version": "2.7.0",
"description": "Russian text quality for AI agents — neuroslop cleanup, typography, information style, editorial standards, UX writing, business correspondence. Scores text 0–10. 2,000+ linguistic atoms.",
"category": "productivity",
"homepage": "https://github.com/talkstream/ru-text",
"tags": [
"russian",
"neuroslop",
"ai-text-detection",
"typography",
"editorial",
"ux-writing",
"text-quality"
]
}
]
}
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 8a66da599427
ru-text is a plugin published in the GitHub repository talkstream/ru-text (222 stars, last pushed 4d 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
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-ru
Install Humanizer RU as a Claude plugin. | Установка Humanizer RU как плагина Claude.
humanizer-ru
Читает русскоязычный текст, находит следы машинной генерации и по явной просьбе переписывает его естественным языком. | Reads Russian text, finds traces of machine generation and, on explicit request, rewrites it to sound natural.
practicaltypography
Plugin marketplace listing 1 plugin: practicaltypography.
practicaltypography
A typography skill that audits and produces publication-quality text for blogs, docs, slides, and any content — distilled from Butterick's Practical Typography.
animalz-plugins
Plugin marketplace listing 7 plugins: structured-article-writer, copywriting-coach, blog-style-guide-creator, design-reference, session-saver.