What is dym-humanizer-humanize-pasted-text?

A chat-based writing tool that rewrites pasted text to sound more like a person while keeping its meaning. It returns an initial rewrite, notes remaining machine-like patterns, and then gives a final version.

Use it on pasted drafts such as emails, articles, or other prose that you want to read more naturally.

It helps when text sounds overly artificial or formulaic. The review step makes it easier to spot wording that still needs attention.

dym-humanizer-humanize-pasted-text — Skill for Claude Code by Rheinmir

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 Rheinmir/setup --skill dym-humanizer-humanize-pasted-text

Clone the repo

git clone --depth 1 https://github.com/Rheinmir/setup

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rheinmir/setup/dym-humanizer-humanize-pasted-text/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-humanizer-humanize-pasted-text)

Your own site

<a href="https://agentmods.dev/skills/rheinmir/setup/dym-humanizer-humanize-pasted-text"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-humanizer-humanize-pasted-text/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rheinmir/setup/dym-humanizer-humanize-pasted-text"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-humanizer-humanize-pasted-text.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,250 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.

Model	Per session	Once invoked
Fable 5.1	$0.00055	$0.01250
Opus 5.5	$0.00022	$0.00500
Sonnet 5.5	$0.00011	$0.00250
Haiku 4.5	$0.00006	$0.00125

Measured yesterday against content hash ee9573ab8eae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dym-humanizer-humanize-pasted-text 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 yesterday.

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.

.overstack/doyourmagic/humanizer/skills/dym-humanizer-humanize-pasted-text/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: dym-humanizer-humanize-pasted-text — Chữa văn bản dán trực tiếp (chế độ mặc định)

Vì sao dùng: đây là đường chính. Bạn dán văn bản nghe "mùi AI", Humanizer trả lại bản viết như người viết mà không đổi nội dung.

Sinh ra cái gì: ba phần trong một lượt trả lời — bản nháp, danh sách ngắn các pattern AI còn sót, và bản cuối.

Mọi lệnh trong file này gõ trong khung chat của agent, không phải terminal.

Cách gọi

/humanizer

[dán văn bản vào đây]

Nếu cài theo đường plugin (workflow 02), gọi /humanizer:humanizer.

Hoặc nói tự nhiên, không cần slash:

Humanize đoạn này giúp tôi: [văn bản]

Cái bạn nhận lại

SKILL.md mục "How to return the result" quy định chế độ mặc định (văn bản dán) trả về ba phần:

Bản nháp — lượt viết lại đầu tiên, không coi cấu trúc gốc là bất biến.
Phần soi lại — danh sách ngắn chỗ nào vẫn còn nghe máy.
Bản cuối — bản đã viết lại sau khi soi.

Thấy đủ ba phần nghĩa là skill đã chạy đúng quy trình. Chỉ nhận được một khối văn bản trơn thì hoặc agent đang chạy chế độ khác (xem 04), hoặc skill chưa được nạp.

Quy trình bên trong (4 bước, trích `SKILL.md` → "Rewrite process")

Đọc nguồn và đánh dấu từng pattern AI.
Viết nháp. Đọc to lên. Soi nhịp câu, chi tiết, động từ đơn giản (is, has), mức trang trọng.
Tự hỏi hai câu: "Chỗ nào vẫn nghe như AI?" và "Bản viết lại có thêm hay mất fact, tên, số, ngày, trích dẫn, citation, thứ hạng nào không?" Thêm hoặc mất đều tính là lỗi.
Viết bản cuối theo ý, không vá từng cụm bị gắn cờ.

Khớp giọng của bạn

Đưa mẫu văn của chính bạn thì kết quả bám giọng đó thay vì luật style mặc định:

/humanizer

Đây là mẫu văn của tôi để khớp giọng:
[dán 2-3 đoạn bạn tự viết]

Giờ humanize đoạn này:
[dán văn bản AI]

Mẫu văn đè lên luật style, kể cả luật gạch ngang §14 ("Em and en dashes"). Nguyên văn trong SKILL.md: "A writing sample takes priority over these style rules. If the sample uses em dashes, keep them at about the same rate. Do not apply §14 as a ban."

Read the full file on GitHub · 99 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.

yesterday First seen · 99 lines · 0 tokens per session scan A ee9573ab8eae

Subscribe to this mod's changes

dym-humanizer-humanize-pasted-text is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 55 tokens to every session and 1,250 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Writing and docs

dym-humanizer-humanize-pasted-text next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dym-humanizer-humanize-pasted-textRheinmir/setup	Skill	11	20d ago	MIT	A	55	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code