A text-rewriting skill that sends supplied writing to the HumanizerAI service and returns a more natural-sounding version. It supports light, medium, and aggressive rewrite levels.

Use it to rewrite text with a chosen level of editing and display the original and revised detection scores, along with remaining credits.

It changes writing that may sound machine-generated into text with a different style. The service uses credits based on the number of words.

humanize — Skill for Claude Code and Codex by humanizerai: A text-rewriting skill that sends supplied writing to the…

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/humanizerai/agent-skills/humanize

Any agent

npx skills add humanizerai/agent-skills --skill humanize

Clone the repo

git clone --depth 1 https://github.com/humanizerai/agent-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/humanizerai/agent-skills/humanize.svg)](https://agentmods.dev/skills/humanizerai/agent-skills/humanize)

Your own site

<a href="https://agentmods.dev/skills/humanizerai/agent-skills/humanize"><img src="https://agentmods.dev/badge/skills/humanizerai/agent-skills/humanize.svg" alt="Measured on agentmods" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 541 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	$0.00037	$0.00541
Opus 5	$0.00018	$0.00270
Sonnet 5	$0.00007	$0.00108
Haiku 4.5	$0.00004	$0.00054

Measured 4d ago against content hash 61115d7795d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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/humanize/SKILL.md · 92 lines

What it actually says

Humanize AI Text

Transform AI-generated content into natural, human-like writing using the HumanizerAI API.

How It Works

When the user invokes /humanize, you should:

Parse $ARGUMENTS for text and optional --intensity flag
Call the HumanizerAI API to humanize the text
Present the humanized text with before/after scores
Show remaining credits

Parsing Arguments

The user may provide:

Just text: /humanize [their text]
With intensity: /humanize --intensity aggressive [their text]

Default intensity is medium.

Intensity Levels

Value	Name	Description	Best For
`light`	Light	Subtle changes, preserves style	Already-edited text, low AI scores
`medium`	Medium	Balanced rewrites (default)	Most use cases
`aggressive`	Bypass	Maximum bypass mode	High AI scores, strict detectors

API Call

Make a POST request to https://humanizerai.com/api/v1/humanize:

Authorization: Bearer $HUMANIZERAI_API_KEY
Content-Type: application/json

{
  "text": "<user's text>",
  "intensity": "medium"
}

Response Format

Present results like this:

## Humanization Complete

**Score:** X → Y (improvement)
**Words Processed:** N
**Credits Remaining:** X

---
### Humanized Text

[The humanized text]

---

[Recommendation based on final score]

Credit Usage

1 word = 1 credit
Detection is free
Check credits at https://humanizerai.com/dashboard

Error Handling

Insufficient Credits

If the user doesn't have enough credits:

Show how many credits are needed vs available
Direct them to https://humanizerai.com/dashboard to top up

Invalid API Key

Check HUMANIZERAI_API_KEY environment variable
Direct to https://humanizerai.com to get a key

Rate Limit

If rate limited, suggest waiting or upgrading to Business plan.

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.

4d ago First seen · 92 lines · 37 tokens per session scan A 61115d7795d7

Subscribe to this mod's changes

humanize is a skill published in the GitHub repository humanizerai/agent-skills (42 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 541 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.

Writing and docs agent ai claude-code codex dete humanizer

humanize