agentic-humanizer

agentic-humanizer is a skill for Claude Code from numen-tech/slopornot. It costs 44 tokens per session (6,818 once invoked), scanned A, original, MIT.

A writing skill that rewrites AI-generated text to sound more natural in English and several other languages, with optional style and readability settings.

In plain words
What is it for?
Humanizing pasted text, matching a voice, selecting language variants, adjusting tone or length, and optionally checking readability and AI-detector scores.
Why use it?
It provides a repeatable editing process for reducing artificial-sounding wording and matching a requested language, dialect, tone, length, or reading level.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Humanizing pasted text, matching a voice, selecting language variants, adjusting tone or…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/numen-tech/slopornot/agentic-humanizer
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.

Any agent
npx skills add numen-tech/slopornot --skill agentic-humanizer
Clone the repo
git clone --depth 1 https://github.com/numen-tech/slopornot

Made for: Claude Code.

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 agentic-humanizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/numen-tech/slopornot/agentic-humanizer.svg)](https://agentmods.dev/skills/numen-tech/slopornot/agentic-humanizer)
Your own site
<a href="https://agentmods.dev/skills/numen-tech/slopornot/agentic-humanizer"><img src="https://agentmods.dev/badge/skills/numen-tech/slopornot/agentic-humanizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,818 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 $0.00044 $0.06818
Opus 5 $0.00022 $0.03409
Sonnet 5 $0.00009 $0.01364
Haiku 4.5 $0.00004 $0.00682

Measured 7d ago against content hash 2ce8b7dafca7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agentic-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 7d 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.

claude-skills/agentic-humanizer/SKILL.md · 601 lines

How it starts

The opening of the file, as written. The whole thing — 601 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Humanizer

A 5-pass AI humanizer. It always runs the core rewrite workflow; Slop or Not Pro adds measured on-device AI detector checks.

  • Without Slop or Not: runs the full rewrite workflow.
  • With Slop or Not Pro: adds on-device AI detector scoring, readability, Text Cleanup, and cleanup stats.

Slash command: /agentic-humanizer [paste text]

Inline overrides: /agentic-humanizer language=<code> variant=<spec> dialect=us|uk grade=N level=<band> tone=casual|professional|academic length=±10|exp|trim threshold=N max=N voice=off voice-skip skip-interview [paste]

language=<code> and variant=<spec> set the target language and variant (for example language=de variant=de-AT). language= without variant= uses that language's default variant from the registry (or other:<code> for an unsupported language). variant=<tag> without language= infers the base language from the variant's BCP-47 prefix (for example variant=de-AT -> language=de); if the prefix is unsupported, keep that bare prefix as the language, use the inline variant, and warn. dialect=us|uk is a legacy English alias. grade=N is English only; level=<band> (elementary|middle|high_school|college|graduate) sets the reading level for any language. See references/multilingual.md.

What this skill does

  1. Runs the built-in Claude Desktop interview (no harness detection).
  2. Handles inline overrides and unsupported profile commands before any rewrite.
  3. Resolves rewrite preferences from inline overrides, defaults, or the interview.
  4. Optionally captures a per-run writing sample and extracts a stylometric fingerprint. Voice matching does not require Slop or Not.
  5. Probes whether Slop or Not Pro is reachable via MCP.
  6. Runs the 5-pass humanization workflow:
    • Core mode logs unscored iterations.
    • Slop or Not Pro runs Text Cleanup, detection, and readability checks.
  7. Returns the final text, loop history, highest-impact edits, and, when Slop cleanup ran, a Text Cleanup summary.

Read the full file on GitHub · 601 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. 7d ago First seen · 601 lines · 44 tokens per session scan A 2ce8b7dafca7

Subscribe to this mod's changes

agentic-humanizer is a skill published in the GitHub repository numen-tech/slopornot (46 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 6,818 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

untell

Audit an AI detector and measure what its verdict is worth, using a closed-loop detector-feedback rewrite as the instrument (the "untell" skill). Use when the user wants to check whether text reads as AI-generated, find out why a detector flagged something, measure a detector's false-positive rate on human writing…

ssamba1/untell · 135 tokens

anti-slop-writing-id

Tulis teks yang menghindari semua pola penulisan AI dan terasa seperti ditulis manusia. Gunakan saat menulis artikel, esai, posting blog, konten media sosial, atau teks apa pun dalam Bahasa Indonesia yang harus terasa autentik. Aktif saat ada permintaan untuk menulis secara natural, menghindari slop AI, menghindari…

adenaufal/anti-slop-writing · 106 tokens

humanize-mba-text

A Chinese-language rewriting tool for making AI-generated text sound more natural in the style of a Chinese MBA thesis. It focuses on practical, evidence-based, academically structured writing.

stephenlzc/humanize-mba-text-skill · 108 tokens

accent-dial

Skill "accent-dial" from petar-djukic/writing-skills, covering accent dial (pre-terminal stage), usage, calibration (strategy theatre payload, 2026-08-21), sentence grain (default since gh-73) and the review gate (mandatory).

petar-djukic/writing-skills · 0 tokens

translate-polish

A Korean editing skill for making translated writing sound natural while keeping the original information and meaning unchanged.

amondnet/yoonmoon · 321 tokens

proofread

A Korean proofreading skill that corrects objective language errors such as spelling, spacing, standard-word usage, foreign-word spelling, punctuation, and clear grammatical mistakes.

amondnet/yoonmoon · 283 tokens