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 NulightJens/humanizer-stack --skill structural-humanizergit clone --depth 1 https://github.com/NulightJens/humanizer-stackWrote 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/nulightjens/humanizer-stack/structural-humanizer)<a href="https://agentmods.dev/skills/nulightjens/humanizer-stack/structural-humanizer"><img src="https://agentmods.dev/badge/skills/nulightjens/humanizer-stack/structural-humanizer/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/nulightjens/humanizer-stack/structural-humanizer"><img src="https://agentmods.dev/badge/skills/nulightjens/humanizer-stack/structural-humanizer.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 | $0.00188 | $0.02132 |
| Opus 5.5 | $0.00075 | $0.00853 |
| Sonnet 5.5 | $0.00038 | $0.00426 |
| Haiku 4.5 | $0.00019 | $0.00213 |
Grade A, and why
structural-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 1mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 153 lines · 188 tokens per session scan A 3e436d2c4d99
structural-humanizer is a skill published in the GitHub repository NulightJens/humanizer-stack (372 stars, last pushed 3mo ago), with no licence file. It adds 188 tokens to every session and 2,132 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
academic-humanizer
Write or rewrite academic and scholarly text so it reads as a careful researcher's work, not a chatbot's, while keeping a formal register. Use for research papers, theses and dissertations, journal articles, literature reviews, abstracts, conference papers, and grant proposals, whether you are editing existing text or…
humanizer
Write or rewrite text so it reads as natural and human, not AI-generated. Use whenever the user asks to "humanize," "de-slop," "de-AI," "make this sound human," or to edit, rewrite, or clean up existing text. Also use when the user asks Claude to write, draft, or compose an essay, article, blog post, email, or any…
legal-humanizer
Write or rewrite legal and professional drafting so it reads as careful drafting, not chatbot output, while preserving precision, defined terms, and formal structure. Use for contracts, clauses, legal memos, briefs, policies, terms of service, and demand letters, whether editing existing text or when the user asks…
post-humanizer
Write or rewrite social posts and short online content so they read like a real person wrote them, not a chatbot. Use whenever the user asks to "humanize" a post, or asks Claude to "write," "draft," "compose," or "post" a LinkedIn post, X/Twitter post or thread, blog post, newsletter section, Instagram or Facebook…
patina
Detect and rewrite AI writing patterns in Korean, English, Chinese, and Japanese text so it reads as if a human wrote it. Meaning-preservation (MPS) verified.
humanize
The laundering chain: one generative pass that moves AI-drafted prose toward human-passing on Pangram. Stages in order — filter-tells (semantic cleanup), seeded match-voice (anchored Cohere seed, iterate only while the score falls), optional burstiness, tighten-style (word recovery), optional accent-dial…