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.
npx skills add Rheinmir/setup --skill dym-humanizer-install-claude-plugingit clone --depth 1 https://github.com/Rheinmir/setupWrote 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/skills/rheinmir/setup/dym-humanizer-install-claude-plugin)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-humanizer-install-claude-plugin"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-humanizer-install-claude-plugin/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/skills/rheinmir/setup/dym-humanizer-install-claude-plugin"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-humanizer-install-claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00050 | $0.00609 |
| Opus 5.5 | $0.00020 | $0.00244 |
| Sonnet 5.5 | $0.00010 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
dym-humanizer-install-claude-plugin 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.
What it actually says
Skill: dym-humanizer-install-claude-plugin — Cài Humanizer làm plugin Claude Code (lệnh chat)
Vì sao dùng: đường này không đụng terminal và không đẻ file nào trong repo dự án. Đổi lại nó chỉ chạy trên Claude Code.
Sinh ra cái gì: một marketplace tên humanizer và một plugin humanizer trong cấu hình Claude Code của bạn. Lệnh gọi skill thành /humanizer:humanizer.
Mọi lệnh dưới đây gõ trong khung chat của Claude Code, không phải trong terminal. Gõ chúng vào shell sẽ báo
command not found.
Yêu cầu
Claude Code 2.1.142 trở lên. Kiểm tra bằng terminal:
claude --version
Các bước
Trong chat Claude Code:
/plugin marketplace add blader/humanizer
/plugin install humanizer@humanizer
Cú pháp humanizer@humanizer là <tên plugin>@<tên marketplace>. Hai tên trùng nhau vì .claude-plugin/marketplace.json đặt name: "humanizer" và khai đúng một plugin cũng tên humanizer, source: "./".
Kiểm tra đã cài đúng
/plugin
Bảng plugin phải hiện humanizer phiên bản 2.11.2 (giá trị lấy từ .claude-plugin/plugin.json → version).
Muốn kiểm chứng manifest trước khi cài, chạy trong terminal trên một bản clone:
claude plugin validate .
Output thật khi lành:
Validating marketplace manifest: <đường-dẫn>/.claude-plugin/marketplace.json
✔ Validation passed
Gọi skill
/humanizer:humanizer
[dán văn bản vào đây]
Cài qua Skills CLI (workflow 01) thì tên ngắn hơn: /humanizer. Cách gọi bằng câu tự nhiên ("humanize đoạn này giúp tôi") hoạt động ở cả hai đường cài, vì Claude khớp theo trường description trong metadata của SKILL.md.
Chọn 01 hay 02
Chỉ chọn một. Cài cả hai thì có hai bản prompt giống hệt nhau cùng nạp, agent dễ chọn nhầm bản cũ khi bạn cập nhật một bên. Nếu lỡ cài cả hai, gỡ bên Skills CLI bằng npx skills remove humanizer --agent claude-code -y.
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 · 72 lines · 50 tokens per session scan A 555a4b9976af
dym-humanizer-install-claude-plugin is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 50 tokens to every session and 609 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.
dym-humanizer-install-claude-plugin compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-humanizer-install-claude-pluginRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 50 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 112k | today | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 2d ago | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | today | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | today | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 11d ago | MIT | A | 52 | Claude Code, Codex |