agentmods.dev

humanizer-ru

humanizer-ru is a skill for Claude Code, Codex from ivklgn/ai-kit. It costs 183 tokens per session (18,397 once invoked), scanned A, original, MIT.

A Russian-language editing guide for making text sound more natural and less machine-generated. It changes wording and rhythm while keeping the original facts and meaning.

In plain words
What is it for?
It helps revise Russian articles, posts and other prose into clearer, more individual-sounding writing without adding unsupported details.
Why use it?
It removes repetitive, formulaic and overly formal patterns that can make Russian writing feel artificial. It does not allow invented experiences, people, events or results.

Skill for Claude CodeCodex

Part of the ai-kit plugin — 21 skills, 15 commands, 30 agents, 1 MCP server shipped together

not rated 12 today A scan 183 tokens original MIT
View the source file ivklgn/ai-kit
Install

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.

agentmods
npx agentmods add skills/ivklgn/ai-kit/humanizer-ru
Any agent
npx skills add ivklgn/ai-kit --skill humanizer-ru
Clone the repo
git clone --depth 1 https://github.com/ivklgn/ai-kit

Made for: Claude Code, Codex.

Or install ai-kit, the plugin that ships this one along with the rest of its 21 skills, 15 commands, 30 agents, 1 MCP server.

Wrote 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.

agentmods badge for humanizer-ru

README.md
[![agentmods](https://agentmods.dev/badge/skills/ivklgn/ai-kit/humanizer-ru.svg)](https://agentmods.dev/skills/ivklgn/ai-kit/humanizer-ru)
Your own site
<a href="https://agentmods.dev/skills/ivklgn/ai-kit/humanizer-ru"><img src="https://agentmods.dev/badge/skills/ivklgn/ai-kit/humanizer-ru.svg" alt="Measured on agentmods" height="20"></a>
Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,397 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00183 $0.18397
Opus 5 $0.00092 $0.09198
Sonnet 5 $0.00037 $0.03679
Haiku 4.5 $0.00018 $0.01840

Measured 5d ago against content hash 5f9bc2fca646, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

humanizer-ru 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 5d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/humanizer_metrics/__init__.py, scripts/humanizer_metrics/burstiness.py, scripts/humanizer_metrics/markers.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/ai-kit/skills/humanizer-ru/SKILL.md · 536 lines

How it starts

The opening of the file, as written. The whole thing — 536 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Humanizer-RU v3.12

Ты редактор. Превращаешь стерильный AI-текст в живую русскую речь. Не просто убираешь маркеры нейросети, а возвращаешь в текст автора: с мнением, ритмом, характером.

Хороший русский текст неровный. Спотыкается, перебивает сам себя, ускоряется и замедляется. AI-текст гладкий и никакой, как музак в лифте.

Фундаментальный принцип: статистическое отклонение

LLM выбирает статистически наиболее вероятное продолжение текста. Результат стремится к самому типичному варианту, применимому к наибольшему числу случаев.

Очеловечивание = намеренное отклонение от статистической нормы. Каждый выбор слова, каждый поворот фразы, каждый ритмический сбой - это выбор МЕНЕЕ вероятного, но БОЛЕЕ характерного варианта. AI пишет «Это имеет важное значение». Человек пишет «Это меняет всё» или «Ну и что?» - зависит от автора. Оба варианта менее вероятны статистически, но оба несут характер.

Держи этот принцип в голове при каждом решении: «AI выбрал бы самый типичный вариант. Какой вариант выбрал бы ЭТОТ конкретный автор?»

Два ключевых наблюдения о русском AI-тексте:

  • LLM предпочитает существительные глаголам. Noun/verb ~3:1 у AI, ~2:1 у людей. Instruction tuning усиливает перекос. Люди заякоривают язык в глаголах (время, вид, наклонение), AI - в noun phrases.
  • LLM обрабатывает русский через English-biased representations. Кальки с английского в AI-русском - не случайные ошибки, а артефакт архитектуры. Translationese неизбежен. Это объясняет, ПОЧЕМУ паттерны 7 (кальки) и 8 («является») так устойчивы.

Что именно ловят детекторы (2025-2026)

Детекторы (GPTZero, Originality.ai, DivEye, RuBERT) измеряют три вещи:

  1. Perplexity (предсказуемость). Насколько каждое следующее слово предсказуемо. AI-текст имеет низкую perplexity: каждое слово «ожидаемо». Человеческий текст дёргается: предсказуемое слово, неожиданное, снова предсказуемое.

  2. Burstiness (всплески). Вариативность структуры по документу. AI пишет равномерно: все предложения ~одной длины, ~одной сложности. Человек чередует: длинное сложное, короткое рубленое, вопрос, снова длинное.

Read the full file on GitHub · 536 lines

Files

What ships with it

8 files beside SKILL.md 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.

Changes

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.

  1. 5d ago First seen · 536 lines · 183 tokens per session scan A 5f9bc2fca646

Subscribe to this mod's changes

humanizer-ru is a skill published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed today), licensed MIT. It adds 183 tokens to every session and 18,397 once invoked, about $0.0009 per session on Opus 5. 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.

Writing and docsagentsai-agentsai-codingclaudeclaude-codecodex
Related

Other skills, from other repositories

ai-ml-development

AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.

travisjneuman/.claude · 43 tokens

authentication-patterns

OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.

travisjneuman/.claude · 28 tokens

email-systems

Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.

travisjneuman/.claude · 55 tokens

case-interview-practice

Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.

travisjneuman/.claude · 39 tokens

devops-cloud

DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.

travisjneuman/.claude · 38 tokens

finance

Financial analysis expertise for financial modeling (DCF, LBO, M&A), valuation, financial statement analysis, capital allocation, treasury management, and corporate finance decisions. Use when building financial models, analyzing statements, or making investment decisions.

travisjneuman/.claude · 48 tokens