A text-editing guide for making English or Russian writing sound less like it was generated by AI. It detects the language unless the requested language is specified.

Use it when you want text humanized, made more natural, or stripped of obvious AI patterns. It accepts pasted text, a file path, or the current selection.

It helps remove recurring machine-written patterns while following separate rules for English and Russian. It is meant for rewriting supplied text, not for creating unrelated content.

humanizer — Skill for Claude Code by DmitriyYukhanov: A text-editing guide for making English or Russian writing…

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/dmitriyyukhanov/claude-plugins/humanizer

Any agent

npx skills add DmitriyYukhanov/claude-plugins --skill humanizer

Clone the repo

git clone --depth 1 https://github.com/DmitriyYukhanov/claude-plugins

Made for: Claude Code.

Or install humanizer, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dmitriyyukhanov/claude-plugins/humanizer.svg)](https://agentmods.dev/skills/dmitriyyukhanov/claude-plugins/humanizer)

Your own site

<a href="https://agentmods.dev/skills/dmitriyyukhanov/claude-plugins/humanizer"><img src="https://agentmods.dev/badge/skills/dmitriyyukhanov/claude-plugins/humanizer.svg" alt="Measured on agentmods" height="20"></a>

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,311 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.

Model	Per session	Once invoked
Fable 5.1	$0.00105	$0.01311
Opus 5	$0.00053	$0.00656
Sonnet 5	$0.00021	$0.00262
Haiku 4.5	$0.00011	$0.00131

Measured 6d ago against content hash 214f4df6a830, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

humanizer 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 6d 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/humanizer/skills/humanizer/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Humanizer (EN + RU auto-routing)

Remove AI-generation patterns from text. This skill bundles two MIT-licensed upstream rulesets and routes the input to the right one based on language.

This file is a router. The actual humanization rules live in references/humanizer-en.md and references/humanizer-ru.md and are authoritative. Do not paraphrase, summarise, or "improve" them — load and follow.

Process

Step 1 — Receive input

Accept the text to humanize as: a pasted block, a file path (use Read), or the current selection. If the input is unclear, ask the user once.

Step 2 — Honour explicit override

Scan the user's request (case-insensitive) for an explicit language directive:

EN override — the request contains any of: as english, english only, humanize in english, на английском, обработай как английский.
RU override — the request contains any of: as russian, russian only, humanize in russian, на русском, обработай как русский.

If an override is present, skip step 3 and jump to step 4 with the chosen language.

Step 3 — Detect language

Count letters in the input (ignore digits, punctuation, whitespace):

cyr = number of letters matching [А-Яа-яЁё]
lat = number of letters matching [A-Za-z]
total = cyr + lat

Decide:

total < 20 (input too short to classify reliably) → use AskUserQuestion with options "English", "Russian".
cyr / total >= 0.6 → Russian.
cyr / total <= 0.1 → English.
Otherwise (mixed, Cyrillic ratio between 10 % and 60 % exclusive) → use AskUserQuestion with options "Apply Russian rules", "Apply English rules", "Run both passes (RU then EN)".

Step 4 — Load the chosen ruleset

For English: Read references/humanizer-en.md
For Russian: Read references/humanizer-ru.md
For "both passes": load both. Execute RU first, then EN on the RU output.

The loaded file is authoritative. Treat its instructions as if they were yours.

Step 4b — Russian only: resolve the ruleset's own file paths

Read the full file on GitHub · 128 lines

Files

What ships with it

13 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.

6d ago First seen · 128 lines · 105 tokens per session scan A 214f4df6a830

Subscribe to this mod's changes

humanizer is a skill published in the GitHub repository DmitriyYukhanov/claude-plugins (7 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 1,311 once invoked, about $0.0005 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.

Writing and docs ai anthropic claude claude-code claude-code-marketplace claude-code-plugin

top-design

Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…

wondelai/skills · 113 tokens

design-everyday-things

Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…

wondelai/skills · 132 tokens

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

create-app

Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…

wondelai/skills · 217 tokens

create-business

Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…

wondelai/skills · 211 tokens

clean-architecture

Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…