russian-style

russian-style is a skill for Claude Code from spumer/i-m-senior-developer. It costs 252 tokens per session (5,200 once invoked), scanned A, original, MIT.

A set of rules for writing and reviewing natural-sounding Russian text. It focuses on technical and workplace writing that should read like it was written by a fluent person rather than translated by AI.

In plain words
What is it for?
Use it when writing or editing Russian copy, documentation, replies, or scripts, especially when a draft sounds too formal or machine-translated.
Why use it?
It helps remove unnatural word choices, literal translations, and stiff sentence patterns. This makes Russian documentation, scripts, and user-facing text easier to read.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the clarity-language plugin — 3 skills, 1 hook shipped together

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/spumer/i-m-senior-developer/russian-style
Any agent
npx skills add spumer/i-m-senior-developer --skill russian-style
Clone the repo
git clone --depth 1 https://github.com/spumer/i-m-senior-developer

Made for: Claude Code.

Or install clarity-language, the plugin that ships this one along with the rest of its 3 skills, 1 hook.

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 russian-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/spumer/i-m-senior-developer/russian-style.svg)](https://agentmods.dev/skills/spumer/i-m-senior-developer/russian-style)
Your own site
<a href="https://agentmods.dev/skills/spumer/i-m-senior-developer/russian-style"><img src="https://agentmods.dev/badge/skills/spumer/i-m-senior-developer/russian-style.svg" alt="Measured on agentmods" height="20"></a>
Per session 252 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,200 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 5.1 $0.00252 $0.05200
Opus 5 $0.00126 $0.02600
Sonnet 5 $0.00050 $0.01040
Haiku 4.5 $0.00025 $0.00520

Measured yesterday against content hash 9153417ca22a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

russian-style 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.

plugins/clarity-language/skills/russian-style/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Russian Style — естественный русский без AI-кальки

Набор правил авторского письма на русском, выведенных из реальных правок. Цель — писать так, как говорят и пишут люди, а не так, как переводит модель с английского. Дополняет clarity-validator (он ловит смысловые синтетические паттерны) и ai-prose-detector (стиль художественной прозы). Этот скилл — про естественность формулировок в технических и рабочих текстах.

Каждое правило — нормативный guard против устойчивого класса ошибок, а не разовый вкусовой запрет.

Правило 1. Замена слова: сначала референт, потом вердикт

Решать на уровне слова — «есть русское соответствие, значит заменяй» — и есть источник худших ошибок этого правила. Порядок обязателен и обратный: сначала проверь, что читатель после замены узнаёт ту же вещь, и только потом выбирай, что делать со словом.

Наблюдённый провал прежнего порядка: в выпущенном отчёте стояло «Зелень оказалась неустойчивой». Дословно перевод верен, но существительное «зелень» не называет ни прогон, ни его итог, и владелец проекта прочёл фразу как «мигающие тесты», хотя речь была о другом — зелёный итог не воспроизвёлся, потому что проверяемое поведение не наступало вовсе. Проверка «есть ли русское слово» эту замену пропустила, потому что смотрела на слово, а не на референт.

Шаг 1. Гейт референта

Замена пригодна не потому, что она русская, а потому что читатель без английского оригинала по-прежнему опознаёт названную вещь, практику или наблюдаемое поведение. Русскость формы пригодности не доказывает.

Три теста, все обязательны:

  1. Обратный тест. Назови референт: какую вещь, практику или поведение слово называет. Если после замены референт назвать нельзя — замена не прошла.
  2. Тест диагноза. Если слово кодирует наблюдаемое поведение или режим отказа, спроси: вызовет ли новая форма то же следующее действие у читателя. flaky tests — это «то проходят, то падают без изменения кода»; «нестабильные тесты» этот признак теряет, и диагноз меняется.
  3. Тест носителя признака. Если заменяется признак термина, существительное, к которому признак относится, обязано остаться в фразе: «зелёный прогон» — да, «зелень» — нет.

Read the full file on GitHub · 322 lines

Files

What ships with it

1 file 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. yesterday Changed · +87 lines · +45 tokens per session 9153417ca22a
  2. 6d ago First seen · 235 lines · 207 tokens per session scan A ae1a2de9e3a0

Subscribe to this mod's changes

russian-style is a skill published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 4d ago), licensed MIT. It adds 252 tokens to every session and 5,200 once invoked, about $0.0013 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 2026-08-31.

Related

Other skills, from other repositories

azure-ai-translation-text-py

Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".

microsoft/skills · 60 tokens

i18n-localization

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

vudovn/ag-kit · 27 tokens

harden

Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.

fengshao1227/ccg-workflow · 62 tokens

seedance-vocab-ja

This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.

Emily2040/seedance-2.0 · 50 tokens

i18n-helper

国际化/本地化助手 — 扫描代码中的硬编码文本、生成 i18n 配置、批量翻译.

laolaoshiren/claude-code-skills-zh · 33 tokens

intlayer-preact

Integrates Intlayer internationalization with Preact applications. Use when the user asks to "setup Preact i18n", create a new translated component, use the "useIntlayer" hook in Preact, or configure providers.

aymericzip/intlayer · 52 tokens