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 znlgis/opengis-skills --skill minerugit clone --depth 1 https://github.com/znlgis/opengis-skillsWrote 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/znlgis/opengis-skills/mineru)<a href="https://agentmods.dev/skills/znlgis/opengis-skills/mineru"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/mineru/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/znlgis/opengis-skills/mineru"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/mineru.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 | $0.00115 | $0.04717 |
| Opus 5.5 | $0.00046 | $0.01887 |
| Sonnet 5.5 | $0.00023 | $0.00943 |
| Haiku 4.5 | $0.00012 | $0.00472 |
Grade B, and why
mineru scanned grade B with 2 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 2d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST http://127.0.0.1:<port>/v1/parse/jobs -H 'Content-Type: application/json' -d '{"upload_id":"...","tier":"standard"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:<port>/v1/health How it starts
The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目地址: https://github.com/opendatalab/MinerU
官方文档: https://opendatalab.github.io/MinerU/
PyPI:
mineru(4.0.12,截至 2026-10;4.x 与 3.x 的命令行入口不同,见下文)许可证: AGPL-3.0
概述
MinerU 把 PDF、扫描件、图片与多种办公文档解析成结构化 Markdown / JSON,输出保留版面顺序、公式、表格与图片资源,可直接喂给 RAG 检索、翻译流水线或人工复核。
- 多档质量:
flash/basic/standard/advanced四档,按"速度 ↔ 精度 ↔ 硬件"取舍,而不是按旧版 backend 名字猜 - 两个入口:
mineru(库式、带缓存与续读协议)与mineru-kit(无状态、一次到底) - 本地文档库:解析结果落库,用
doc:.../page:N定位符续读,不必反复整篇重解析 - 可编程:Python
DoclibClient与 V1 HTTP API;另有 WebUI 与服务模式 - 后端自动选择:小模型走 ONNX/Torch,VLM 走 llama.cpp / vLLM / LMDeploy,按本机依赖与设备自动挑
- 容器化:官方 Dockerfile 面向 Linux + NVIDIA(Windows 走 WSL2)
环境准备
前置条件
| 项 | 要求 |
|---|---|
| Python | >=3.10,<3.15(推荐 3.12) |
| 操作系统 | Linux / macOS / Windows;Docker 路径只覆盖 Linux + NVIDIA GPU |
| 硬件 | CPU 可跑(ONNX 小模型 + llama.cpp Vulkan);NVIDIA GPU 装 mineru[full] 吞吐最好 |
| 磁盘 | 模型权重与文档库需要额外空间,默认在 ~/.mineru/models |
方式一:uv 虚拟环境(官方推荐)
pip install uv
uv venv .mineru --python 3.12
# Linux/macOS
source .mineru/bin/activate
# Windows (PowerShell)
.\ .mineru\Scripts\Activate.ps1
uv pip install -U "mineru>=4.0,<5"
方式二:普通 pip(已有环境时)
python -m pip install -U "mineru>=4.0,<5"
需要最好吞吐时装 extras:
# NVIDIA GPU 推荐:自带匹配的 torch 与推理引擎
uv pip install -U "mineru[full]>=4.0,<5"
# 只补 torch 侧
uv pip install -U "mineru[torch]>=4.0,<5"
Windows 上 GPU 版 torch 需要单独装;macOS 默认安装即为最佳吞吐,不需要
[full]。
方式三:Docker(Linux + NVIDIA)
# 在仓库根目录(含 4.0 Dockerfile)执行
docker build -t mineru:4 -f docker/global/Dockerfile .
镜像基于 vLLM 0.21.0、默认 CUDA 13.0;构建期会显式选 Torch 小模型与 vLLM 权重(可在无 GPU 的构建机上准备),运行期固定 MINERU_MODEL_SMALL_BACKEND=torch、MINERU_MODEL_VLM_ENGINE=vllm。国内版 Dockerfile 走 ModelScope,global 版走 Hugging Face。
验证
mineru version --json # 4.x 的版本查询;老 CLI 用 mineru --version
mineru --help # 查看当前安装支持的子命令
mineru-kit parse --help # 无状态入口
命令行入口
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.
- 2d ago First seen · 347 lines · 115 tokens per session scan B 3e0ffb70002b
mineru is a skill published in the GitHub repository znlgis/opengis-skills (76 stars, last pushed 2d ago), licensed MIT. It adds 115 tokens to every session and 4,717 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-28.
Other skills, from other repositories
ade
Parse documents and extract schema-shaped data with the ADE (Agentic Document Extraction) v2 APIs through the ade CLI. A local job-item store makes every run idempotent, resumable, and citable — repeat runs are free, interrupted runs resume, and every answer can cite element ids with visual evidence.
paddleocr-doc-parsing
A document-parsing tool configuration for extracting structured Markdown or JSON from complex PDFs and document images, including tables, formulas, charts, and multi-column pages.
paddleocr-text-recognition
An optical character recognition tool configuration for extracting text from images, photos, scans, screenshots, and scanned PDFs. OCR means converting text visible in an image into machine-readable text.
document-processing
Use when the deliverable is a document's bytes or its literal content — text/tables out of PDFs, AcroForm fill and flatten, page merge/split, PDF/DOCX from templates, OCR of image-only scans. NOT schema-typed fields pulled from text (that is structured-extraction), NOT signature routing (e-signature) or spreadsheet…
larksnap-fetch
A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.
kreuzberg
Extract text, tables, metadata, and images from 91+ document formats (PDF, Office, images, HTML, email, archives, academic) using Kreuzberg. Use when writing code that calls Kreuzberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output…