humanize

A command for rewriting Russian AI-generated text to sound more natural, using the full editing process from the `humanizer-ru` skill. It can accept text directly or read it from a file.

In plain words
What is it for?
Use it to humanise Russian text, diagnose passages that need editing, rewrite them in a consistent voice, and briefly report what changed.
Why use it?
It helps remove artificial-sounding wording while preserving the original facts and checking the result through several editing passes.

Command

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 commands/ilyautov/humanizer-ru/humanize
Clone the repo
git clone --depth 1 https://github.com/ilyautov/humanizer-ru
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 257 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 $0.00023 $0.00257
Opus 5 $0.00012 $0.00129
Sonnet 5 $0.00005 $0.00051
Haiku 4.5 $0.00002 $0.00026

Measured 2d ago against content hash 719611b55979, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

humanize 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.

commands/humanize.md · 22 lines

What it actually says

Используй скилл humanizer-ru в режиме «Полное редактирование».

Вход: $ARGUMENTS

  • Если это путь к файлу: прочитай файл и работай с его содержимым.
  • Если это текст: работай с ним напрямую.
  • Если вход пустой: попроси пользователя дать текст или путь к файлу и спроси про целевой голос (кто автор, какой жанр).

Пройди все 5 шагов скилла, начиная с первого: диагностика со светофорной разметкой абзацев (зелёные не трогать!), калибровка голоса, переписывание по разметке с контрастным вычитанием, quad-pass аудит. Помни про Факт-замок: факты исходника неприкосновенны, выдумывать конкретику запрещено.

Выведи: переписанный текст, затем коротко (3-5 пунктов) что именно было исправлено и почему.

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. 2d ago First seen · 22 lines · 23 tokens per session scan A 719611b55979

Subscribe to this mod's changes

humanize is a command published in the GitHub repository ilyautov/humanizer-ru (269 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 257 once invoked, about $0.0001 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.