Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Rheinmir/setupnpx agentmods add skills/rheinmir/setup/dym-humanizer-install-shellWrote 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-shell)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-humanizer-install-shell"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-humanizer-install-shell/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-shell"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-humanizer-install-shell.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 | $0.00069 | $0.01225 |
| Opus 5.5 | $0.00028 | $0.00490 |
| Sonnet 5.5 | $0.00014 | $0.00245 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
dym-humanizer-install-shell scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/blader/humanizer/main/SKILL.md \ How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-humanizer-install-shell — Cài Humanizer bằng shell (Skills CLI / copy tay)
Vì sao dùng: Humanizer chỉ là một file prompt Markdown (SKILL.md). Nó không làm gì cho tới khi nằm trong thư mục skill của agent. Đây là đường cài bằng terminal, dùng được cho mọi agent hỗ trợ skill, không riêng Claude Code.
Sinh ra cái gì: một thư mục skill trong dự án hoặc ở cấp user (ví dụ .claude/skills/humanizer/), cộng skills-lock.json ở gốc dự án khi cài theo scope project.
Yêu cầu trước
- Node.js (để chạy
npx). Repo không có build step, không cópackage.json, không có dependency cần cài. - Không cần Python trừ khi bạn là người sửa chính skill này — xem
06-contributor-validate-and-release.md.
Cài cho một dự án
Chạy tại gốc dự án đích (không phải trong repo humanizer):
npx skills add blader/humanizer
Kết quả đã kiểm chứng khi cài cho Claude Code:
./.claude/skills/humanizer/
./skills-lock.json
skills-lock.json ghi lại source, sourceType và computedHash của bản đã cài.
Cài cho toàn máy (mọi dự án)
npx skills add blader/humanizer --global
-g là dạng viết tắt của --global. Bỏ cờ này thì cài ở mức project.
Chọn agent nhận skill
# một agent cụ thể
npx skills add blader/humanizer --agent claude-code
# nhiều agent
npx skills add blader/humanizer --agent claude-code cursor
# tất cả agent CLI biết
npx skills add blader/humanizer --agent '*' --skill '*' -y
Với --agent '*', CLI dựng một bản chuẩn ở .agents/skills/humanizer/ rồi symlink các thư mục agent về đó. Đã quan sát thật:
.agents/skills/humanizer/ # bản thật
.claude/skills/humanizer -> ../../.agents/skills/humanizer
agent/skills/humanizer/
Sau khi cài xong phải reload agent thì skill mới xuất hiện.
Xem và gỡ
npx skills ls # skill trong project
npx skills ls -g # skill toàn máy
npx skills ls --json # dạng máy đọc, không màu
npx skills update humanizer # cập nhật lên bản mới nhất
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 · 117 lines · 69 tokens per session scan A bb650aa00225
dym-humanizer-install-shell is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 69 tokens to every session and 1,225 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.
dym-humanizer-install-shell compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-humanizer-install-shellRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 69 | 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 |