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.
git clone --depth 1 https://github.com/Aboudjem/humanizer-skillWrote 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.
[](https://agentmods.dev/plugins/aboudjem/humanizer-skill/humanizer-skill)<a href="https://agentmods.dev/plugins/aboudjem/humanizer-skill/humanizer-skill"><img src="https://agentmods.dev/badge/plugins/aboudjem/humanizer-skill/humanizer-skill/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.
<a href="https://agentmods.dev/plugins/aboudjem/humanizer-skill/humanizer-skill"><img src="https://agentmods.dev/badge/plugins/aboudjem/humanizer-skill/humanizer-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 1mo 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.
What it actually says
{
"name": "humanizer",
"version": "0.7.1",
"description": "Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when editing a Markdown file in place. Triggers on phrases like \"humanize this\", \"make this sound less AI\", \"make this sound human\", \"remove AI tells\", \"does this read like ChatGPT\", and \"rewrite so it does not sound AI-generated\". Pure Markdown, zero dependencies, no network calls.",
"author": {
"name": "Adam Boudjemaa",
"email": "[email protected]"
},
"license": "MIT",
"keywords": [
"claude-code",
"claude-code-plugin",
"humanizer",
"ai-writing",
"writing-tools",
"ai-detection",
"burstiness",
"voice-profiles",
"text-rewriting",
"content-quality"
],
"skills": "./skills/"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 139 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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.
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.
- 1mo ago Changed 3af15760045f
- 1mo ago First seen · 24 lines scan A 97cf7a0067a8
humanizer is a plugin published in the GitHub repository Aboudjem/humanizer-skill (290 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
patina
Detect and rewrite AI writing patterns in Korean, English, Chinese, and Japanese so text reads as if a human wrote it. Meaning-preservation (MPS) verified, audit-friendly. The root SKILL.md is loaded as the /patina skill.
untell
Humanize AI-generated text via a closed-loop, detector-feedback rewrite. Optimizes against GPTZero, ZeroGPT, Originality.ai and other Turnitin-class checkers while preserving meaning, citations and facts. Research/defensive tool.
signs-of-ai
Measure a text for the signs of AI writing and read back the evidence — offline, EN/ES, with the tool's own false-positive rate attached.
humanizer-ko
A Korean-language editing tool that finds writing patterns associated with AI-generated text and rewrites the prose to sound more natural.
anti-ai-tell
Cross-media discipline so prose AND design don't read as AI-generated. Generation-time rules, a mechanical linter for prose + visual tells, a style fingerprint that injects a chosen point of view, a population-level sameness detector, and hooks that lint-on-write and ask for a style anchor when one is missing.
humanizer-de
Deutscher Stil-Editor für Claude Code/Codex: misst Register und Rhythmus, redigiert proportional auf ein Zielprofil, gleicht erkennbare Faktenanker konservativ ab und auditiert/entfernt KI-Schreibmuster. German AI Text Humanizer / deutscher Humanizer Skill. Supports Claude Code and Codex. 72 Muster in 10 Kategorien…