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 Tano73/agent-skills --skill mineru-pdf-to-mdgit clone --depth 1 https://github.com/Tano73/agent-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/tano73/agent-skills/mineru-pdf-to-md)<a href="https://agentmods.dev/skills/tano73/agent-skills/mineru-pdf-to-md"><img src="https://agentmods.dev/badge/skills/tano73/agent-skills/mineru-pdf-to-md/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/tano73/agent-skills/mineru-pdf-to-md"><img src="https://agentmods.dev/badge/skills/tano73/agent-skills/mineru-pdf-to-md.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 | $0.00274 | $0.03228 |
| Opus 5.5 | $0.00110 | $0.01291 |
| Sonnet 5.5 | $0.00055 | $0.00646 |
| Haiku 4.5 | $0.00027 | $0.00323 |
Grade A, and why
mineru-pdf-to-md 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.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MinerU PDF → Markdown
MinerU converte documenti a layout complesso in Markdown pulito. Il suo modello di punta è MinerU2.5-Pro-2604-1.2B, un VLM che legge la pagina come immagine e ne ricostruisce la struttura: ordine di lettura, tabelle in HTML, formule in LaTeX, figure ritagliate su file.
Questo lo rende adatto dove un estrattore di testo tradizionale fallisce — PDF a due colonne, scansioni, paper scientifici, capitolati con tabelle annidate — ma comporta un vincolo concreto: il VLM ha bisogno di una GPU o di un server remoto. Il primo compito della skill è quindi capire dove può girare, non lanciare subito la conversione.
Script:
$HOME/.agents/skills/mineru-pdf-to-md/scripts/mineru_env.py— diagnosi ambiente e installazione$HOME/.agents/skills/mineru-pdf-to-md/scripts/mineru_convert.py— conversione, normalizzazione output, report qualità
Fase 0 — Diagnosi dell'ambiente
Esegui sempre questo comando prima di qualsiasi conversione. È veloce e determina tutto il resto:
python3 $HOME/.agents/skills/mineru-pdf-to-md/scripts/mineru_env.py check
Lo script rileva GPU CUDA, Apple Silicon, un eventuale server VLM (variabili d'ambiente
MINERU_SERVER_URL o MINERU_VLM_SERVER_URL) e la presenza di mineru, poi raccomanda un backend.
| Situazione rilevata | Backend scelto | Usa MinerU2.5-Pro? |
|---|---|---|
| Server OpenAI-compatibile raggiungibile | vlm-http-client |
Sì, in remoto |
| GPU CUDA ≥ 8 GB VRAM o Apple Silicon | hybrid-auto-engine |
Sì, in locale |
| Solo CPU, nessun server | pipeline |
No |
Il caso CPU va dichiarato all'utente
Se la raccomandazione è pipeline, la conversione funzionerà comunque — MinerU ha una pipeline
classica (layout detection + OCR) che gira bene su CPU — ma MinerU2.5-Pro non viene usato, e
tabelle e formule risultano sensibilmente più deboli. Siccome l'utente ha probabilmente chiesto
proprio quel modello, non silenziare la differenza: spiega il fallback e presenta le alternative
reali (procedere con pipeline, puntare a un server remoto con --server-url, oppure forzare
vlm-auto-engine su CPU, che usa davvero MinerU2.5-Pro ma impiega diversi minuti a pagina).
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 · 229 lines · 274 tokens per session scan A c6a9b2128f5c
mineru-pdf-to-md is a skill published in the GitHub repository Tano73/agent-skills (2 stars, last pushed 23d ago), licensed MIT. It adds 274 tokens to every session and 3,228 once invoked, about $0.0011 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 2026-09-04.
Other skills, from other repositories
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
pptx-posters
Creates and audits editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Used when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
nature-paper-trans
A workflow for translating selected pages or a complete English research-paper PDF into a simplified-Chinese, image-based PDF. bioRxiv is not mentioned in the provided details; the workflow applies to research-paper PDFs generally.
nature-paper2word
A document conversion workflow that turns an academic Markdown manuscript into a Word .docx file. It supports specified academic formatting, equations, tables, references, cross-references, and export checks.
extracting-lab-tables
Detects and extracts tabular laboratory panels from PDFs, scans, and images into structured rows ready for OpenMed and FHIR. Use when the user has a CBC, CMP, lipid panel, or other lab report as a scanned image / PDF / spreadsheet and needs the test name, value, unit, reference range, and abnormal flag as clean rows.…
figures
Makes publication-quality plots from data with matplotlib, learning curves, scaling laws, benchmark and ablation comparisons, Pareto trade-offs, heatmaps and confusion matrices, sized for the page, vector, with uncertainty shown. Use whenever results are plotted, charted or visualized for a paper, report or answer, or…