audit

A command that checks text for signs it may have been written by AI without rewriting it. It combines an automated scan, when available, with a manual review described by a Russian-language writing skill.

In plain words
What is it for?
Use it to audit pasted text or a file, review detected markers and false positives, prioritize changes, and receive a scanner verdict with recommendations.
Why use it?
It helps identify wording patterns that can make text appear machine-written while preserving the original text for later editing.

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/audit
Clone the repo
git clone --depth 1 https://github.com/ilyautov/humanizer-ru
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 304 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 $0.00022 $0.00304
Opus 5 $0.00011 $0.00152
Sonnet 5 $0.00004 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured 3d ago against content hash 6e0b8d998d7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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 3d 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/audit.md · 29 lines

What it actually says

Используй скилл humanizer-ru в режиме «Аудит»: покажи маркеры, ничего не переписывай.

Вход: $ARGUMENTS

  • Если это путь к файлу: работай с файлом; если текст, сохрани его во временный файл для сканера.
  • Если вход пустой: попроси текст или путь.

Порядок по скиллу: сначала машинная половина. Запусти детерминированный сканер, если доступен python3 с razdel и pymorphy3:

python3 <папка скилла>/scripts/scan.py <файл>

Если зависимостей нет: предложи pip-однострочник и проведи аудит вручную по каталогу маркеров. Аудит обязан состояться при любом раскладе.

Поверх отчёта сканера добавь суждение: отметь ложные срабатывания (жанр, формальный регистр, осмысленные триады), расставь приоритеты правок от самых выдающих к косметике. В конце дай вердикт по шкале сканера и 3-5 главных рекомендаций.

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. 3d ago First seen · 29 lines · 22 tokens per session scan A 6e0b8d998d7b

Subscribe to this mod's changes

audit is a command published in the GitHub repository ilyautov/humanizer-ru (269 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 304 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.