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 Tuminha/dental-ai-skills --skill dental-paper-fetchgit clone --depth 1 https://github.com/Tuminha/dental-ai-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/tuminha/dental-ai-skills/dental-paper-fetch)<a href="https://agentmods.dev/skills/tuminha/dental-ai-skills/dental-paper-fetch"><img src="https://agentmods.dev/badge/skills/tuminha/dental-ai-skills/dental-paper-fetch/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/tuminha/dental-ai-skills/dental-paper-fetch"><img src="https://agentmods.dev/badge/skills/tuminha/dental-ai-skills/dental-paper-fetch.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 | $0.00154 | $0.07472 |
| Opus 5.5 | $0.00062 | $0.02989 |
| Sonnet 5.5 | $0.00031 | $0.01494 |
| Haiku 4.5 | $0.00015 | $0.00747 |
Grade A, and why
dental-paper-fetch scanned grade A with 1 finding 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 29d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `curl` | Optional | Used once per link when a server fails Python's certificate check, with certificate checking on. `/usr/bin/curl` on macOS completes a chain that leaves out an intermediate certificate. Without curl, How it starts
The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dental Paper Fetch: Free Full-Text PDFs and Figures
Skill protocol version: 2026.09.30
When to use
Use this skill when an answer depends on something the abstract does not give: methods, full results, tables, figures, flow charts, limitations, funding and disclosure statements, supplementary numbers. Do not answer those from the abstract when a free full text exists.
Five skills in this repository have a "Full text first" step that names this skill:
research-critic, before appraising a single paper.clinical-evidence-revieweranddental-evidence-retriever, for each key study.dental-statistical-forensics, before auditing the numbers of a paper.dental-author-disclosures, to read the paper's own funding and disclosure statements.
This skill downloads and files papers. It does not appraise them.
Requirements
| Item | Needed? | Detail |
|---|---|---|
| Python 3.10 or newer | Yes | Standard library only. Nothing to install with pip. |
| A runtime that runs scripts and reaches the internet | Yes | Claude Code, Codex or a terminal. In a chat-only runtime, ask the user for a PDF they may lawfully share. |
poppler (pdftotext, pdfimages, pdftoppm, pdfinfo) |
Optional | Needed by import, and for figures from PDFs that are not in PubMed Central. Package poppler in Homebrew, poppler-utils in Debian and Ubuntu. Without it, get saves the PDF, takes no figures from it and prints the install command once per run. Each poppler call has a time limit of 120 seconds. |
curl |
Optional | Used once per link when a server fails Python's certificate check, with certificate checking on. /usr/bin/curl on macOS completes a chain that leaves out an intermediate certificate. Without curl, those links are reported as OPEN_MANUALLY with the certificate reason. A curl exit that is not a certificate failure is not reported as one: a time limit gives "did not answer in time", an HTTP error gives the block wording. |
PAPERS_DIR |
Optional | Folder for everything the tool saves. Default: ./papers under the current directory. The tool prints one line when it creates the folder. On an external drive (/Volumes/<name>/...), every command that touches the folder first checks that the drive is connected; if not, it prints The drive <name> is not connected. Connect it or set PAPERS_DIR. and exits with 1, so nothing is ever written to a plain folder under /Volumes. |
CORE_API_KEY |
Optional | API key for CORE, registered at https://core.ac.uk/services/api. Sent in the Authorization header of requests to api.core.ac.uk. Those requests never follow a redirect to another host. Without it the tool skips CORE. |
PAPER_FETCH_EMAIL |
Optional | A contact address. Sent to PubMed (E-utilities email parameter), OpenAlex and Crossref (mailto parameter). Sent to no other service. Leave it unset to send no address. |
What ships with it
2 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.
- 29d ago First seen · 414 lines · 154 tokens per session scan A dd7267268bb6
dental-paper-fetch is a skill published in the GitHub repository Tuminha/dental-ai-skills (7 stars, last pushed 7d ago), licensed MIT. It adds 154 tokens to every session and 7,472 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.
Other skills, from other repositories
markitdown
Converts 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.
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.
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…
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.
open-notebook
Organizes research with the self-hosted Open Notebook alternative to NotebookLM. Supports source ingestion (PDFs, web pages, audio, video, and Office documents), cited document chat, text and vector search, notes, custom transformations, and multi-speaker podcasts. Use when automating Open Notebook through its REST…
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…