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 mrpulor-gh/nuphus --skill tools-internalgit clone --depth 1 https://github.com/mrpulor-gh/nuphusWrote 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/mrpulor-gh/nuphus/tools-internal)<a href="https://agentmods.dev/skills/mrpulor-gh/nuphus/tools-internal"><img src="https://agentmods.dev/badge/skills/mrpulor-gh/nuphus/tools-internal/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/mrpulor-gh/nuphus/tools-internal"><img src="https://agentmods.dev/badge/skills/mrpulor-gh/nuphus/tools-internal.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.02972 |
| Opus 5.5 | $0.00000 | $0.01189 |
| Sonnet 5.5 | $0.00000 | $0.00594 |
| Haiku 4.5 | $0.00000 | $0.00297 |
Grade A, and why
tools-internal 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 24d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
内置工具参数手册
Nuphus 工具页 24 个内部机制命令。仅注册 invoke_handler，不注册为 agent 工具（LLM 不可经 execute_tool 调用）；用户经工具页手动使用。 本手册供 Agent 感知能力与引导用户，非用户文档。
能力总览（24）
| 分类 | 命令 | 输入 → 输出 |
|---|---|---|
pdf_merge |
N 个 PDF → 1 个 | |
pdf_compress |
PDF → PDF（prune 未引用对象） | |
pdf_page_count |
PDF → 页数 | |
pdf_extract_text |
PDF → 文本（逐页，默认上限 200 页） | |
pdf_images_to_pdf |
N 图 → PDF（每图一页） | |
pdf_extract_pages |
PDF+页码 → 新 PDF | |
pdf_rotate |
PDF → PDF（90/180/270） | |
| 图像 | image_compress |
图→图（限宽高+质量） |
| 图像 | image_convert |
图→图（按扩展名推断格式） |
| 图像 | image_resize |
图→图（contain 保比例，不放大） |
| 图像 | image_info |
图→宽高/大小/格式 |
| 图像 | image_stitch |
N 图→长图（horizontal/vertical） |
| 图像 | image_compress_batch |
N 图→目录（原名-out.扩展名） |
| 图像 | image_convert_batch |
N 图→目录（目标格式） |
| 图像 | image_resize_batch |
N 图→目录（目标宽高 contain） |
| 视频 | video_compress |
视频→视频（libx264 重编码） |
| 视频 | video_extract_frames |
视频→目录（frame_%04d.jpg） |
| 视频 | video_info |
视频→时长/编码/分辨率（ffprobe） |
| 视频 | video_to_gif |
视频→GIF（palettegen+paletteuse） |
| 视频 | video_cut |
视频→片段（-ss 快速 seek + -c copy） |
| 音频 | video_extract_audio |
视频/音频→音频（wav/mp3） |
| 音频 | audio_convert |
音频/视频→音频（mp3/wav/m4a/flac） |
| 音频 | voice_clone |
参考音频+文本→克隆语音（走云端） |
| 文档 | doc_extract_text |
docx/pptx/xls/ods/odt/odp/pdf→文本 |
关键参数
PDF（src-tauri/src/commands/tools/pdf.rs，lopdf）
pdf_merge(input_paths: Vec<String>, output_path)— 多文件合并；输出扩展名必须 .pdf；单文件 ≤500MBpdf_compress(input_path, output_path)— 清理未引用对象后重写pdf_page_count(path)— 返回 pagespdf_extract_text(path, max_pages: Option<u32>)— 逐页--- Page N ---分隔pdf_images_to_pdf(input_paths, output_path)— 图片白名单 png/jpg/jpeg/bmp/gif/webp；单图像素 ≤5000 万pdf_extract_pages(input_path, pages: Vec<u32>, output_path)— 1-based，越界报错pdf_rotate(input_path, output_path, degrees: u32, pages: Option<Vec<u32>>)— degrees 仅 90/180/270
图像（image.rs，image crate）
image_compress(input, output, max_width: Option<u32>, max_height: Option<u32>, quality: Option<u8>)— JPEG quality 默认 82；PNG Best+Adaptiveimage_convert(input, output)— 输出格式随扩展名（png/jpg/jpeg/bmp/gif/webp）image_resize(input, output, width: u32, height: u32)— contain，不放大image_info(path)— 宽高/大小/格式image_stitch(input_paths, output, direction: Option<String>)— horizontal 默认/verticalimage_compress_batch(input_paths, output_dir, max_width?, max_height?, quality?)— 输出原名-out.扩展名image_convert_batch(input_paths, output_dir, format: String)— 目标 png/jpg/jpeg/bmp/gif/webp；jpeg→jpgimage_resize_batch(input_paths, output_dir, width: u32, height: u32)— contain 保比例，不放大；输出原名-out.扩展名
What ships with it
1 file 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.
- 24d ago Changed · +32 lines 563b984fd832
- 1mo ago Changed · +2 lines f154141803d7
- 1mo ago First seen · 84 lines · 0 tokens per session scan A a4c50f30cb88
tools-internal is a skill published in the GitHub repository mrpulor-gh/nuphus (89 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,972 tokens. 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 2026-09-03.
Other skills, from other repositories
chinese-video-transcribe-pdf
A workflow that turns Chinese-language videos, with or without subtitles, into structured text and a Chinese PDF report. It can use videos from sources such as YouTube or local MP4 files.
aos-agent-skill-document
A document-publishing workflow for planning, creating, converting, checking, and preparing reports, proposals, manuals, white papers, and brand documents for release.
报销助理
An expense assistant that reads invoice images, PDFs, and travel receipts, checks them against expense rules, and creates expense forms. OCR means reading printed text from an image automatically.
Генерация PDF из Markdown с точным академическим форматированием через Pandoc и LaTeX
A document workflow that turns Markdown text into PDF files using Pandoc and a custom LaTeX template. It applies specified academic page settings such as 14-point text, 1.5 line spacing, and A4 paper.
paper-to-xhs
Convert an academic paper, PDF, DOI, arXiv page, or publisher link into a Chinese Xiaohongshu paper note in the user's established voice, including a detailed verification layer, a self-contained sub-1000-character publishable post with functional emoji, topics, and 4–6 screenshot-led portrait images. Use for…
paper-to-dialogue-video
A workflow for turning an academic paper or PDF into a source-checked Chinese two-host podcast and video package.