What is paper-fetcher-vp?

A skill for identifying, downloading, checking, renaming, and filing academic research papers as official PDF files. It can use a screenshot, title, URL, or excerpt as the starting clue.

Use it to fetch papers from sources such as arXiv, OpenReview, publishers, or project pages, classify them by research area, and report the identifier needed to add them to Zotero.

It reduces the risk of saving the wrong paper, an unofficial copy, or a file in the wrong research category. It also keeps paper files and their metadata organised for a knowledge base.

paper-fetcher-vp — Skill for Codex by VectorPeak

Install

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.

Any agent

npx skills add VectorPeak/vectorpeak-agent-skills --skill paper-fetcher-vp

Clone the repo

git clone --depth 1 https://github.com/VectorPeak/vectorpeak-agent-skills

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/paper-fetcher-vp/github.svg)](https://agentmods.dev/skills/vectorpeak/vectorpeak-agent-skills/paper-fetcher-vp)

Your own site

<a href="https://agentmods.dev/skills/vectorpeak/vectorpeak-agent-skills/paper-fetcher-vp"><img src="https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/paper-fetcher-vp/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vectorpeak/vectorpeak-agent-skills/paper-fetcher-vp"><img src="https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/paper-fetcher-vp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,391 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00089	$0.01391
Opus 5	$0.00044	$0.00696
Sonnet 5	$0.00018	$0.00278
Haiku 4.5	$0.00009	$0.00139

Measured 10d ago against content hash 3b387468e7da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

paper-fetcher-vp 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/paper_postprocess.py, tests/test_paper_postprocess.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

knowledge-skills/paper-fetcher-vp/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper Fetcher

When To Use

Use this skill when the user wants to identify, fetch, verify, rename, and store an academic paper PDF from a screenshot, title, URL, project page, or excerpt. Also use it when the user asks for the Zotero Add Item by Identifier value for a paper.

Do not use this skill for generated reading notes, summaries, synthesis pages, Zotero database editing, paywall bypasses, or non-official mirror collection unless the user explicitly asks for a separate downstream task.

Default Vault Contract

For this local LLM_wiki vault, default paper storage is the numbered raw research taxonomy under:

E:\LLM_wiki\LLM_wiki\01.raw\08.Research

Use the mapped field folder when the user does not provide a destination:

Field	PDF destination
`Agent`	`01.raw\08.Research\00.Agent`
`RAG`	`01.raw\08.Research\01.RAG`
`SFT`	`01.raw\08.Research\02.PostTraining\SFT`
`RL`	`01.raw\08.Research\02.PostTraining\RL`
`Training_Systems` or legacy `DL_Frameworks`	`01.raw\08.Research\03.Training_Systems`
`Personal`	`01.raw\08.Research\04.Personal`
`Other`	`01.raw\08.Research\05.Other`

Treat PDFs, .metadata.json sidecars, optional BibTeX sidecars, and raw paper metadata saved here as 01.raw source material. Default sidecars go into 01.raw\08.Research\_metadata. If --target-dir is supplied, treat it as the exact PDF destination directory and put sidecars in <target-dir>\_metadata.

Do not create generated notes, summaries, outlines, or wiki-ready interpretations inside 01.raw\08.Research; those belong later in 02.wiki or another user-specified notes destination.

Core Workflow

Extract title, authors, visible IDs, source URL, project URL, and candidate PDF URL from the user input.
Search online when needed and verify the strongest official match.
Prefer official sources in this order: arXiv, OpenReview, official publisher pages, official project pages, then GitHub READMEs that link to the paper.
Identify the best Zotero identifier: prefer arXiv ID, then DOI; if neither exists, report not available and include another source ID such as OpenReview ID.
Download the official PDF into a temporary path or the matching field folder under 01.raw\08.Research.
Read enough of the paper to choose exactly one field: RAG, Agent, SFT, RL, Training_Systems, Personal, or Other.
Choose a specific filename prefix with --name-prefix when possible, such as Survey, Benchmark, RepoContext, QLoRA, DPO, PPO, GRPO, DistributedTraining, LLMTraining, or PrivacyDeletion.
Run scripts/paper_postprocess.py to verify %PDF-, rename the PDF as {name-prefix}_{paper title}.pdf, write metadata, and report Zotero status.
Do not generate .bib files unless explicitly requested.

Read the full file on GitHub · 109 lines

Files

What ships with it

7 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.

Changes

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.

10d ago First seen · 109 lines · 89 tokens per session scan A 3b387468e7da

Subscribe to this mod's changes

paper-fetcher-vp is a skill published in the GitHub repository VectorPeak/vectorpeak-agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,391 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.

Documents PDF Research agent-skills ai-agents codex developer-tools knowledge-management

paper-summarizer

Agents should invoke this skill for academic or technical papers, arXiv/PubMed/IEEE/ACM links, PDFs, methodology review, limitations, practical implications, or extracting findings for engineering decisions.

waybarrios/opencode-power-pack · 46 tokens

okf

Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…

scaccogatto/okf-skills · 127 tokens

wechat-article-ingest

A tool that converts public WeChat Official Account articles, or PDF copies of them, into Markdown notes. It can also extract the article's main viewpoints and create linked questions for further thinking.

chubbyguan/chubbyskills · 39 tokens

deck-ai

Generate modern presentation decks (PDF) from markdown content. Local open-source alternative to Gamma — uses Slidev for layouts and Unsplash for imagery. Invoke when the user asks to "make a deck", "build slides from this", or "turn this into a presentation".

assafkip/kipi-system · 57 tokens

call-prep

Call preparation: research, CRM, talking points, PDF.

aAAaqwq/AGI-Super-Team · 0 tokens

pdf

Inspect, extract, assemble, generate, render, OCR, and validate PDF files with local tools while treating active content and external services as explicit security boundaries.

holon-run/holon · 33 tokens