humanize

humanize is a command for Claude Code from felvieira/claude-skills-fv. It costs 52 tokens per session (1,898 once invoked), scanned A, original, Apache-2.0.

A text-editing command that rewrites documents and other published prose to remove common signs of machine-written text. It applies a defined style checklist and adds a more natural voice.

In plain words
What is it for?
Use it on product requirements, user documentation, copy, changelogs, release notes, articles, landing pages, and other text before publication.
Why use it?
It helps make public writing sound less formulaic and easier for people to read. It is meant for prose rather than source code or short technical comments.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the dev-team-kit-fv plugin — 72 skills, 45 commands, 16 agents, 5 hooks shipped together

Good fit Use it on product requirements, user documentation, copy, changelogs, release notes, articles, landing pages, and other text before publication.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/felvieira/claude-skills-fv/humanize
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.

Clone the repo
git clone --depth 1 https://github.com/felvieira/claude-skills-fv

Made for: Claude Code.

Or install dev-team-kit-fv, the plugin that ships this one along with the rest of its 72 skills, 45 commands, 16 agents, 5 hooks.

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 humanize

README.md
[![agentmods](https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/humanize/github.svg)](https://agentmods.dev/commands/felvieira/claude-skills-fv/humanize)
Your own site
<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/humanize"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/humanize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for humanize

Your own site · 80×15
<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/humanize"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/humanize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,898 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00052 $0.01898
Opus 5 $0.00026 $0.00949
Sonnet 5 $0.00010 $0.00380
Haiku 4.5 $0.00005 $0.00190

Measured 12d ago against content hash d03371e1f1d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 12d 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 · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/humanize — Remove AI Writing Patterns

Objetivo: reescrever texto para soar natural e humano, removendo os 29 padrões catalogados em policies/anti-ai-writing.md. Baseado em blader/humanizer + Wikipedia: Signs of AI writing.

Quando usar:

  • antes de publicar PRD no tracker (/to-prd)
  • ao finalizar docs de usuário (skill 10)
  • ao revisar copy antes de publicar (skill 13)
  • ao revisar artigo/blog (skill 14, skill 41)
  • ao revisar página de vendas/ads (skill 50)
  • em todo texto final que vai pro ar: landing page, app, blog, README público
  • ao revisar qualquer prosa que humanos vão ler

Quando NÃO usar:

  • código-fonte (não é prosa)
  • comentários técnicos curtos (overhead desproporcional)
  • conteúdo em idioma diferente do input (skill processa no idioma do texto)

Skill ativada: Documenter (skill 10) em modo "anti-AI editor".

Processo

Passo 1 — Detectar input

# Argumento é path de arquivo?
test -f "$1" && cat "$1"   # lê arquivo
# Sem argumento: texto veio inline na conversa

Se nenhum input detectado: pedir ao usuário o texto ou path.

Passo 2 — Voice calibration (opcional)

Se o usuário forneceu amostra de escrita própria (inline ou path):

  1. Ler a amostra antes de qualquer reescrita
  2. Notar: comprimento de frases, nível de vocabulário, início de parágrafos, pontuação, vícios de linguagem, como trata transições
  3. Usar esses padrões na reescrita — não apenas remover AI-isms, mas substituir com os padrões da amostra

Se sem amostra: usar voz padrão (natural, variada, opinativa).

Passo 3 — Draft rewrite

Aplicar todas as 5 categorias de policies/anti-ai-writing.md:

  1. Conteúdo (padrões 1-6): significado inflado, notabilidade, -ing superficial, linguagem promocional, atribuições vagas, seções formulaicas
  2. Linguagem (padrões 7-13): vocabulário AI, copula avoidance, paralelismos negativos, regra dos três, synonym cycling, falsos ranges, passiva sem sujeito
  3. Estilo (padrões 14-19): em dash, negrito, listas com cabeçalho inline, title case, emojis, curly quotes
  4. Comunicação (padrões 20-22): artefatos de chatbot, disclaimers de cutoff, sycofância
  5. Enchimento (padrões 23-29): frases de enchimento, hedging, conclusões genéricas, hifenização excessiva, autoridade persuasiva, signposting, headers com aquecimento

Read the full file on GitHub · 141 lines

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. 12d ago First seen · 141 lines · 52 tokens per session scan A d03371e1f1d3

Subscribe to this mod's changes

humanize is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,898 once invoked, about $0.0003 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.