ru-text — security grade SAFE, quality 74/100

Security audit verdict: SAFE · quality 74/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by talkstream · Codex Skill · ★ 221

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is ru-text safe to install? View the security audit →

About ru-text

ru-text Languages: English | Русский Russian text quality plugin for Claude Code, Codex CLI, Gemini CLI, Cursor, OpenClaw, and Notion — typography, information style, editorial standards, UX writing, and business correspondence. 1,040 independently formulated rules informed by 16 canonical Russian-language sources. All formulations are original — no verbatim quotes, full attribution. Acknowledgments This plugin exists because a handful of people decided that Russian text on the internet deserves better. They wrote the books, built the tools, maintained the guides, and set the standards that thousands of editors, writers, and designers now rely on every day. Their work fundamentally changed how Russian text is written, formatted, and read on screens. I am deeply grateful to every one of them. If this plugin saves you time, please buy their books and use their tools — they earned it. What it does ru-text gives your AI coding assistant

agent-skillsai-agentsai-text-detectionclaude-codeclaude-coworkcodex-clicursoreditorialgemini-cli-extensioninfo-style

Quick Facts

Stars221
Forks22
LanguageShell
CategoryCodex Skill
LicenseMIT
Quality Score73.5465305428078/100
Last Updated2026-08-28
Created2026-03-28
Platformsclaude-code, cli, codex, gemini
Est. Tokens~13k

Compatible Skills

These tools work well together with ru-text for enhanced workflows:

ru-text alternative? Top 6 similar tools

Looking for a ru-text alternative? If you're comparing ru-text with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • humanizer-ru by ilyautov · ⭐ 374

    humanizer-ru: очеловечить русский AI-текст для Claude Code, Cursor, Codex и других AI-агентов. 64 признака ней

  • humanizer-ru by smixs · ⭐ 143

    Skill для AI-агентов (Claude Code, Codex, OpenClaw, Hermes): убирает 37 признаков AI-генерации из русского тек

  • humanizer-ru by Vladimir-Human · ⭐ 126

    Проверяемая гигиена вставки из чата для русского текста

  • agent-skills by jdrhyne · ⭐ 241

    A collection of AI agent skills for Clawdbot, Claude Code, Codex

  • Claude-Skills by borghei · ⭐ 805

    372 AI skills, 76 expert agents, and 867 stdlib Python tools for every team: engineering, PM, marketing, C-lev

  • ai-maestro by 23blocks-OS · ⭐ 791

    AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Shell Agent Tools

Frequently Asked Questions

What is ru-text?

ru-text is 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.. It is categorized as a Codex Skill with 221 GitHub stars.

What programming language is ru-text written in?

ru-text is primarily written in Shell. It covers topics such as agent-skills, ai-agents, ai-text-detection.

How do I install or use ru-text?

You can find installation instructions and usage details in the ru-text GitHub repository at github.com/talkstream/ru-text. The project has 221 stars and 22 forks, indicating an active community.

What license does ru-text use?

ru-text is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to ru-text?

The top alternatives to ru-text on Agent Skills Hub include humanizer-ru, humanizer-ru, humanizer-ru. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools