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 virtualarchitectures/Local-Zotero-MCP --skill reading-zotero-documentsgit clone --depth 1 https://github.com/virtualarchitectures/Local-Zotero-MCPWrote 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/virtualarchitectures/local-zotero-mcp/reading-zotero-documents)<a href="https://agentmods.dev/skills/virtualarchitectures/local-zotero-mcp/reading-zotero-documents"><img src="https://agentmods.dev/badge/skills/virtualarchitectures/local-zotero-mcp/reading-zotero-documents/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/virtualarchitectures/local-zotero-mcp/reading-zotero-documents"><img src="https://agentmods.dev/badge/skills/virtualarchitectures/local-zotero-mcp/reading-zotero-documents.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 | $0.00088 | $0.00739 |
| Opus 5 | $0.00044 | $0.00369 |
| Sonnet 5 | $0.00018 | $0.00148 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade A, and why
reading-zotero-documents 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 11d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading Zotero documents
Requires the Zotero desktop app running locally with the Local API enabled (see the
searching-zotero-library skill for the setting). These tools read the resolved attachment file
directly with PyMuPDF — they work on any PDF/EPUB attachment, not just ones Zotero has indexed
for full-text search.
Workflow
- Find the attachment's item key:
get_item_children(item_key)on the parent item, and pick the child withitemType: "attachment"and a PDF/EPUBcontentType. If you already have an attachment key directly (e.g. from a prior search), skip this step. - Read it:
read_document(item_key=attachment_key) read_document(item_key=attachment_key, remove_headers_footers=True) read_document(item_key=attachment_key, start_page=21, max_pages=20) # page through a long docread_documentreturns{total_pages, start_page, end_page, text}. Defaultmax_pagesis 20 — call again with a higherstart_pageto keep reading. - To save a copy instead of reading inline, use
convert_document(item_key, output_path, output_format="txt"|"pdf").remove_headers_footersonly applies tooutput_format="txt"; PDF output always preserves the original pages as-is.
remove_headers_footers detects lines that repeat near the top/bottom of most pages (running
titles, page numbers, journal watermarks) and strips them. Turn it on when doing anything that
reads across many pages at once — quoting, summarizing, comparing — since repeated headers
otherwise pollute the extracted text. Leave it off if the user wants a faithful, unedited dump of
a page's content.
Deciding whether to read the full text at all
Read the PDF when: the user wants detailed analysis of arguments/evidence, specific quotes or figures, a methodology comparison, or the abstract genuinely doesn't answer the question.
Stay with metadata (search_items / get_item) when: the user wants a landscape overview,
is identifying themes across many papers, or is still in an early exploration phase. Reading full
text for 20+ papers back-to-back is usually the wrong call — narrow to the 3–5 most relevant
first.
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.
- 11d ago First seen · 57 lines · 88 tokens per session scan A 2fceb1eadda4
reading-zotero-documents is a skill published in the GitHub repository virtualarchitectures/Local-Zotero-MCP (0 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 739 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 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.