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 yqi96/warranted --skill paper-download-browsergit clone --depth 1 https://github.com/yqi96/warrantedWrote 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/yqi96/warranted/paper-download-browser)<a href="https://agentmods.dev/skills/yqi96/warranted/paper-download-browser"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/paper-download-browser/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/yqi96/warranted/paper-download-browser"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/paper-download-browser.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 | $0.00063 | $0.00846 |
| Opus 5.5 | $0.00025 | $0.00338 |
| Sonnet 5.5 | $0.00013 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
paper-download-browser 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 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.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser-assisted Paper Download
Obtain the exact paper the user requested and save a verified local PDF without weakening or evading access controls.
Use this skill when a DOI or publisher page is reachable but direct HTTP download is insufficient because navigation, institutional access, redirects, consent screens, or JavaScript are involved. For ordinary open PDF URLs, download directly without browser automation.
Before operating the browser, load the browser skill and follow its session and human-handoff rules.
Resolve the target
Record enough identity to detect a wrong download:
- DOI, PMID, arXiv id, or canonical landing URL;
- exact or normalized title;
- first author and year when available;
- requested version, such as version of record, accepted manuscript, preprint, or supplementary information.
If the request is ambiguous, resolve the paper identity before downloading. Do not silently substitute a similarly titled paper, a correction, an editorial, or supplementary material for the article.
Choose the least privileged route
Try routes in this order, stopping at the first legitimate success:
- A known direct open-access PDF URL.
- The DOI or publisher landing page's explicit PDF/download control.
- A legitimate open repository linked from the record, such as a publisher repository, PubMed Central, arXiv, or an institutional repository.
- The publisher route after the user completes an authorized institutional or personal login in the browser.
Do not treat access failure as a reason to search for unauthorized copies. When no permitted route succeeds, report the access status and preserve the canonical URL so the user can obtain the paper through a librarian, document-delivery service, or another authorized channel.
Browser procedure
- Open an isolated browser session and retain its session id.
- Navigate to the canonical record.
- Inspect the page snapshot before clicking. Use the page's real PDF, full-text, repository, or download control; do not guess hidden endpoints.
- If authentication or verification appears, follow the human-handoff rule.
- After access is established, inspect the page and recent network requests to identify the legitimate document URL and response type.
- Prefer a direct download when the discovered URL is openly retrievable without exporting session credentials. Otherwise use the visible browser's normal download control.
- Close the browser session when the attempt is complete or blocked.
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 · 79 lines · 63 tokens per session scan A 07aa8f4d9d8c
paper-download-browser is a skill published in the GitHub repository yqi96/warranted (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 846 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-20.
Other skills, from other repositories
argument-mapping
Use this Skill to extract and visualize argument structure: Toulmin reconstruction, support/attack graph, circularity detection, argument scheme classification, and NLP-based premise extraction.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.