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 kennethkhoocy/applied-micro-skills --skill download-gated-pdfsgit clone --depth 1 https://github.com/kennethkhoocy/applied-micro-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/kennethkhoocy/applied-micro-skills/download-gated-pdfs)<a href="https://agentmods.dev/skills/kennethkhoocy/applied-micro-skills/download-gated-pdfs"><img src="https://agentmods.dev/badge/skills/kennethkhoocy/applied-micro-skills/download-gated-pdfs/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/kennethkhoocy/applied-micro-skills/download-gated-pdfs"><img src="https://agentmods.dev/badge/skills/kennethkhoocy/applied-micro-skills/download-gated-pdfs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00137 | $0.00794 |
| Opus 5.5 | $0.00055 | $0.00318 |
| Sonnet 5.5 | $0.00027 | $0.00159 |
| Haiku 4.5 | $0.00014 | $0.00079 |
Grade A, and why
download-gated-pdfs 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use when: (1) curl/WebFetch of a .pdf URL returns HTML instead of a PDF even with a Copies of this mod
1 near-identical copy found in the catalogue:
- download-gated-pdfs — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Download bot-gated PDFs via Wayback id_
Problem
Many think-tank and publisher sites (taxpolicycenter.org, urban.org, SSRN delivery) serve an HTML bot-challenge page instead of the PDF to non-browser clients. A browser User-Agent header does not help. The downloaded "PDF" is actually HTML.
Context / Trigger Conditions
curl -o file.pdf <url>succeeds but the file starts with<!DOC- pypdf raises
invalid pdf header: b'<!DOC'orPdfStreamError: Stream has ended unexpectedly - Firecrawl
scrapereturns clean markdown for the same URL (its proxies get through), but Firecrawl does not return the binary — only parsed content
Solution
- Request the file through the Wayback Machine's raw-content (
id_) endpoint, which serves the original archived binary without rewriting:curl -sL -A "Mozilla/5.0 ... Chrome/126.0 Safari/537.36" \ "https://web.archive.org/web/<YYYY>id_/<original-pdf-url>" -o out.pdf<YYYY>is any year likely to have a snapshot (e.g. publication year); Wayback redirects to the nearest capture. Theid_suffix after the timestamp is what requests the untouched original. - Verify the download with pypdf — a bot page fails immediately:
from pypdf import PdfReader r = PdfReader("out.pdf"); print(len(r.pages), "pages") - If Wayback has no capture, fall back to: another mirror found via search (Exa/Firecrawl), or Firecrawl scrape for the parsed text when the binary is not strictly needed.
Verification
PdfReader opens the file and reports a plausible page count; first-page text matches
the expected title.
Example
Verified 2026-07-15: taxpolicycenter.org/sites/default/files/publication/165884/ssrn-id4797771.pdf
and urban.org/sites/default/files/publication/80621/2000790-...pdf both bot-gated to
direct curl (with UA), both downloaded intact via
https://web.archive.org/web/2024id_/<url> and .../web/2023id_/<url> (18 and 12 pages).
Notes
- Government data hosts (e.g.
ticdata.treasury.gov) are usually NOT gated — try direct curl first; Wayback is the fallback, not the default. - Wayback captures can be stale for frequently-revised documents; check the snapshot date if currency matters.
- See also: the
pdfskill (parsing/extraction after download) andfirecrawl:firecrawl-scrape(parsed markdown when the binary is unnecessary).
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.
- 1mo ago First seen · 64 lines · 137 tokens per session scan A 991e75d80f01
download-gated-pdfs is a skill published in the GitHub repository kennethkhoocy/applied-micro-skills (20 stars, last pushed 1mo ago), licensed MIT. It adds 137 tokens to every session and 794 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
download-fulltext-pdf
A skill for downloading a research paper's complete PDF using an identifier such as a DOI, title, or BibTeX entry.
report-helper
A Chinese-language research workflow that searches the internet and produces a formatted PDF report about a specified topic.
pdf-analyze
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
webask-results-sharing
A survey-results sharing assistant for WebAsk. It prepares reports, summaries, responses, PDF files, or Word files for other people, including public report links and reports with conclusions.
pdf-processing
Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables/formulas from PDFs (including scanned and photographed documents), OCR, combining or merging multiple PDFs, splitting, rotating, watermarking, creating new PDFs, encrypting/decrypting, and extracting…