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 HK-hub/AgentSkills --skill paper-fetchgit clone --depth 1 https://github.com/HK-hub/AgentSkillsWrote 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/hk-hub/agentskills/paper-fetch)<a href="https://agentmods.dev/skills/hk-hub/agentskills/paper-fetch"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/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/hk-hub/agentskills/paper-fetch"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/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 | $0.00162 | $0.05848 |
| Opus 5 | $0.00081 | $0.02924 |
| Sonnet 5 | $0.00032 | $0.01170 |
| Haiku 4.5 | $0.00016 | $0.00585 |
Grade A, and why
paper-fetch scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Some publishers (e.g. `science.org`) sit behind Cloudflare, which answers a plain HTTP client with a `403`/`429` or a "Just a moment…" JS-challenge page instead of the PDF — so the default `urllib` download can't get thr This is a copy
100% identical to paper-fetch — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-fetch
Fetch the PDF for a paper given a DOI (or title). Tries multiple sources in priority order and stops at the first hit.
Resolution order
- Unpaywall —
https://api.unpaywall.org/v2/{doi}?email=$UNPAYWALL_EMAIL, readbest_oa_location.url_for_pdf(skipped ifUNPAYWALL_EMAILnot set) - Semantic Scholar —
https://api.semanticscholar.org/graph/v1/paper/DOI:{doi}?fields=openAccessPdf,externalIds - arXiv — if
externalIds.ArXivpresent,https://arxiv.org/pdf/{arxiv_id}.pdf - PubMed Central OA — if PMCID present,
https://www.ncbi.nlm.nih.gov/pmc/articles/{pmcid}/pdf/ - bioRxiv / medRxiv — if DOI prefix is
10.1101, queryhttps://api.biorxiv.org/details/{server}/{doi}for the latest version PDF URL - Publisher direct (institutional mode only —
PAPER_FETCH_INSTITUTIONAL=1) — DOI-prefix → publisher PDF template (Nature / Science / Wiley / Springer / ACS / PNAS / NEJM / Sage / T&F / Elsevier). The caller's own subscription IP / cookies / EZproxy are what authorize the fetch; unauthorized responses fail the%PDFcheck and fall through to step 7. - Sci-Hub mirrors (on by default; disable with
PAPER_FETCH_NO_SCIHUB=1) — last-resort fallback. Tries the mirror list inPAPER_FETCH_SCIHUB_MIRRORS(or built-in defaultssci-hub.ru,sci-hub.st,sci-hub.su,sci-hub.box,sci-hub.red,sci-hub.al,sci-hub.mk,sci-hub.ee) in order; on full miss, scrapeshttps://www.sci-hub.pub/once per process for fresh mirrors. CAPTCHA / missing-paper pages have no PDF iframe and fall through silently. - Otherwise → report failure with title/authors so the user can request via ILL
CloakBrowser fallback (download layer, opt-in — PAPER_FETCH_CLOAK=1). This is not a separate source: it sits at the download chokepoint, so it applies to any of the sources above. When a resolved PDF URL is blocked by Cloudflare — HTTP 403/429, or a "Just a moment…" HTML interstitial served in place of the file — and the operator opted in, the URL is retried through CloakBrowser (a stealth Chromium that passes the JS challenge) via the cloak_pdf.py companion. Bytes it returns are re-validated through the same %PDF magic-byte + 50 MB checks; on success the result carries via: "cloak". Off by default, fails closed (missing CloakBrowser → silent fall-through), and the agent cannot opt in — see CloakBrowser access below.
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.
- 9d ago First seen · 325 lines · 162 tokens per session scan A c3b4b1c4ebe5
paper-fetch is a skill published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 25d ago), licensed MIT. It adds 162 tokens to every session and 5,848 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to paper-fetch, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
peer-review
Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating…
scientific-critical-thinking
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…
scientific-brainstorming
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use…
alterlab-pyhealth
Develops, tests, and deploys clinical machine learning models with the PyHealth healthcare AI toolkit. Use when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare…
alterlab-cobrapy
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…
alterlab-phylogenetics
Build phylogenetic trees end-to-end from raw sequences — MAFFT multiple sequence alignment, optional TrimAl trimming, IQ-TREE 2 maximum-likelihood inference with model selection and bootstraps, FastTree for large datasets, then visualize with ETE3 or FigTree. Use when reconstructing trees from sequences (FASTA) for…