agentmods.dev

GPTHuman-humanizer

GPTHuman-humanizer is a skill for Claude Code, Codex from GPTHuman-ai/mcp-server. It costs 27 tokens per session (531 once invoked), scanned A, original, Apache-2.0.

A text-rewriting tool that turns AI-generated writing into more natural-sounding prose. It can target different reading levels and rewrite styles, and can return information about AI-detector results.

In plain words
What is it for?
Use it to revise AI-written articles, messages, and other drafts into professional, balanced, enhanced, or level-specific versions.
Why use it?
It helps when a draft sounds artificial or needs a different tone, though the text must meet the tool’s length limits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo 2d ago A scan 27 tokens original Apache-2.0

Good fit Use it to revise AI-written articles, messages, and other drafts into professional, balanced, enhanced, or level-specific versions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gpthuman-ai/mcp-server/gpthuman-mcp
View source ↗ GPTHuman-ai/mcp-server
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 GPTHuman-ai/mcp-server --skill gpthuman-mcp
Clone the repo
git clone --depth 1 https://github.com/GPTHuman-ai/mcp-server

Made for: Claude Code, Codex.

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 GPTHuman-humanizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpthuman-ai/mcp-server/gpthuman-mcp/github.svg)](https://agentmods.dev/skills/gpthuman-ai/mcp-server/gpthuman-mcp)
Your own site
<a href="https://agentmods.dev/skills/gpthuman-ai/mcp-server/gpthuman-mcp"><img src="https://agentmods.dev/badge/skills/gpthuman-ai/mcp-server/gpthuman-mcp/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 GPTHuman-humanizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpthuman-ai/mcp-server/gpthuman-mcp"><img src="https://agentmods.dev/badge/skills/gpthuman-ai/mcp-server/gpthuman-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 531 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 $0.00027 $0.00531
Opus 5 $0.00014 $0.00266
Sonnet 5 $0.00005 $0.00106
Haiku 4.5 $0.00003 $0.00053

Measured 9d ago against content hash e76ede08d08c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

GPTHuman-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 9d 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.

skills/GPTHuman-MCP/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GPTHuman Text Humanizer

This skill enables you to use the humanize_text tool provided by the GPTHuman MCP server to rewrite AI-generated text into natural, human-sounding prose with AI-detector metadata.

When to Use

Use this skill when the user asks you to:

  • "Humanize" a piece of text
  • Rewrite AI-generated content to sound more human
  • Make text bypass AI detectors or improve its human score
  • Adjust the tone of an AI-generated draft to sound more natural

How to Use

If the GPTHuman MCP server is connected, you will have access to the humanize_text tool.

Call the humanize_text tool with the following parameters:

  • text (required): The text you want to humanize. Note: The text must be at least 300 characters and at most 2,000 words.
  • tone (optional): The target reading level / tone. Valid options are Standard, HighSchool, College, PhD. Defaults to College.
  • mode (optional): The rewrite strategy. Valid options are Professional, Balanced, Enhanced. Defaults to Balanced.

Steps

  1. Verify Text Length: Ensure the text provided by the user is at least 300 characters long. If it's too short, inform the user that GPTHuman requires a minimum of 300 characters for optimal results.
  2. Determine Tone and Mode: If the user hasn't specified a tone or mode, use your best judgment based on the context, or use the defaults (College and Balanced).
  3. Execute the Tool: Call humanize_text with the appropriate arguments.
  4. Present the Results: Provide the humanized text to the user. You should also briefly mention the key metadata returned by the tool (such as the AI-detector Human Score, Similarity, and Credit Usage).

Example Scenarios

  • Scenario 1: The user says "Humanize this generated blog intro in College tone using Balanced mode."

    • Action: Call humanize_text with the user's text, tone="College", and mode="Balanced".

  • Scenario 2: The user asks "Rewrite this product description in Professional mode."

    • Action: Call humanize_text with the user's text and mode="Professional".

Read the full file on GitHub · 41 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. 9d ago First seen · 41 lines · 27 tokens per session scan A e76ede08d08c

Subscribe to this mod's changes

GPTHuman-humanizer is a skill published in the GitHub repository GPTHuman-ai/mcp-server (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 531 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 2026-08-31.

Writing and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens