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 bahayonghang/my-ai-cli-toolkit --skill humanizer-papergit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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/bahayonghang/my-ai-cli-toolkit/humanizer-paper)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/humanizer-paper"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/humanizer-paper.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.01961 |
| Opus 5 | $0.00044 | $0.00981 |
| Sonnet 5 | $0.00018 | $0.00392 |
| Haiku 4.5 | $0.00009 | $0.00196 |
Grade A, and why
humanizer-paper 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer (Academic): register-aware AI-tell removal
Polish an academic draft so it reads like a careful human author and conforms
to its register's norms. Two modes: English journal articles (en-journal) and
Chinese doctoral dissertations (zh-dissertation).
The analysis kernel is the "Signs of AI writing" taxonomy from
Wikipedia
(WikiProject AI Cleanup), re-gated for academic register: several general-prose
defaults are backwards in a journal or dissertation, so each tell is kept,
calibrated, or disabled rather than applied blindly. The heavy content lives in
references/; this file is the router and the behavioral rules.
In the
pythoncommand below,<skill-dir>is this skill's base directory, announced when the skill loads. Substitute that literal path; it is not an environment variable. The bundled script self-locates, so only the path needs to resolve.
诚信边界 (behavioral hard rule)
This skill polishes the author's own draft for clarity and for compliance with academic norms. It is not a detector-evasion tool.
- The legitimate, transferable techniques here — varying cadence, calibrating hedging, tightening argumentation, enforcing terminology consistency, protecting citations — apply only to text the author actually wrote or substantively authored.
- If the request is framed as "rewrite this generated text so it passes Turnitin / 知网 AIGC / an AI detector", refuse that framing. Redirect to the legitimate goal: improving real originality (add real data and citations, deepen analysis, fix norms). High AIGC rate is treated by many institutions as academic misconduct; do not position this skill as a way around that.
When to use
- Polish an English journal/conference manuscript or section to remove AI tells while keeping formal register, hedging, and section-appropriate passive.
- Polish a Chinese 学位论文 (摘要/引言/方法/结果/讨论/结论/致谢) for AI tells and GB punctuation, terminology unification, and AIGC quantitative self-check.
- Norm-check a draft (
--check-only) and report mechanical tells without rewriting.
What ships with it
8 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.
- 8d ago First seen · 170 lines · 88 tokens per session scan A e8fed56eac28
humanizer-paper is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 1,961 once invoked, about $0.0004 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.
Other skills, from other repositories
aaai-submission
Use when auditing an AAAI main technical track submission for OpenReview readiness, double-blind anonymity, page limits, reproducibility checklist, supplementary material, author limits, multiple-submission policy, and AAAI AI-use policy compliance.
acl-author-response
Use when drafting an ACL author response inside an ACL Rolling Review cycle on OpenReview, covering the response window before meta-review, reviewer discussion dynamics, score-change strategy, flagging review issues to the area chair, anonymity rules, and deciding between responding now versus revising for a later ARR…
acl-camera-ready
Use when preparing an accepted ACL main-conference or Findings paper for camera-ready, covering the extra content page, de-anonymization and acknowledgements, AI-assistance disclosure, keeping the Limitations section, ACL Anthology metadata and CC BY 4.0 publication, meta-review-driven edits, and presentation-mode…
acl-submission
Use when auditing an ACL submission before an ACL Rolling Review cycle deadline, covering long/short paper page budgets, the mandatory Limitations section, Responsible NLP checklist, anonymized PDFs and supplements, preprint declarations, dual-submission rules, resubmission linking, and ARR desk-reject triggers on…
acl-topic-selection
Use when deciding whether a project fits ACL versus EMNLP, NAACL, EACL, TACL, Computational Linguistics, COLM, or an ML venue, covering contribution typing for NLP work, long-versus-short paper choice, the annual theme track, Findings-tier expectations, and sharpening the computational-linguistics framing before…
acl-workflow
Use when planning an ACL project calendar across ACL Rolling Review cycles, covering cycle selection against conference commitment windows, backward planning from an ARR deadline, the review-response-meta-review timeline, commitment decisions, resubmission loops to later cycles, and camera-ready through ACL Anthology…