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 Aperivue/medsci-skills --skill obsidian-paper-vaultgit clone --depth 1 https://github.com/Aperivue/medsci-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/aperivue/medsci-skills/obsidian-paper-vault)<a href="https://agentmods.dev/skills/aperivue/medsci-skills/obsidian-paper-vault"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/obsidian-paper-vault/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/aperivue/medsci-skills/obsidian-paper-vault"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/obsidian-paper-vault.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 29 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00113 | $0.01885 |
| Opus 5 | $0.00056 | $0.00942 |
| Sonnet 5 | $0.00023 | $0.00377 |
| Haiku 4.5 | $0.00011 | $0.00188 |
Grade A, and why
obsidian-paper-vault 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 12d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Paper Vault
Converts a folder of research PDFs into a two-layer Obsidian vault: literature notes (one per paper, templated) and atomic concept notes (synthesized across papers).
The rules below are not style preferences. Each one is here because its absence produced a specific, silent failure — a fabricated patient count, a broken PDF link, an empty Dataview table — in a vault of 100+ papers.
Relationship to /lit-sync
Both skills write literature and concept notes into the same vault folders. They enter from opposite ends and must not overwrite each other.
/lit-sync |
obsidian-paper-vault |
|
|---|---|---|
| Input | Zotero collection / refs.bib |
a folder of PDFs |
| Note key | citekey | short descriptive title |
| Owns | manuscript/_src/refs.bib |
extracted-text cache |
Never overwrite an existing note. If a note for the paper already exists (by title, DOI,
or citekey), report it and skip. When both skills are in play, /lit-sync notes are the
bibliographic spine; this skill's notes are the read-through summaries.
Step 0: Resolve the vault layout — ask, do not assume
Establish three paths before writing anything:
- Vault root — from the user, or
$OBSIDIAN_VAULT. Never guess a home-directory path. - Literature notes folder — default
Literature/. If the vault already has a folder serving this role (02_research/논문/,Papers/,文献/), honor the existing layout rather than imposing the default. - Concept notes folder — default
Concepts/, same honor-what-exists rule.
For a vault whose structure is Korean, see references/locale/ko/note_templates.md — folder
names and note headings in Korean, opt-in.
Also confirm PyMuPDF is available: python3 -c "import fitz; print(fitz.__version__)"
(install with pip install PyMuPDF). Text extraction caches to
~/.local/cache/paper-vault-texts/ unless the user names another location.
Step 1: Pre-extract PDF text — always, for any batch
python3 scripts/extract_pdfs.py <pdf_folder> <text_cache_folder> [max_pages]
What ships with it
11 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.
- assets/example_concept_note.md 2.2 KB
- assets/example_paper_note.md 2.0 KB
- assets/example_queue.md 1.7 KB
- references/concept-extraction.md 3.6 KB
- references/locale/ko/note_templates.md 3.9 KB
- references/subagent-prompt.md 3.3 KB
- references/tag-vocabulary.md 2.2 KB
- references/templates.md 4.8 KB
- references/workflow.md 4.3 KB
- scripts/extract_pdfs.py 2.5 KB runs code
- skill.yml 2.6 KB
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.
- 12d ago First seen · 145 lines · 113 tokens per session scan A dbd654e5d3f7
obsidian-paper-vault is a skill published in the GitHub repository Aperivue/medsci-skills (292 stars, last pushed 5d ago), licensed MIT. It adds 113 tokens to every session and 1,885 once invoked, about $0.0006 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
lit-pdf-zotero
A research workflow for finding academic papers, downloading their PDFs, adding them to Zotero, and creating visual summaries. Zotero is a tool for organising references and research papers.
markitdown
Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
open-notebook
Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker…
pptx-posters
Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
liteparse
Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities…
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…