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 surfmind-space/awesome-surfmind --skill paper-readergit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/paper-reader)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/paper-reader"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/paper-reader/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/surfmind-space/awesome-surfmind/paper-reader"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/paper-reader.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 | $0.00066 | $0.00741 |
| Opus 5.5 | $0.00026 | $0.00296 |
| Sonnet 5.5 | $0.00013 | $0.00148 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
paper-reader 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Reader
Make a dense paper or technical article approachable by laying out its research question, method, findings, limitations, and practical implications, defining specialized terms along the way. Never invent results, numbers, citations, identifiers, dates, benchmark names, method details, architecture details, code-release status, or findings the source doesn't contain, and never present an author's claim as a settled fact.
- Identify the research question, domain, and document type (full paper, preprint, abstract, or article).
- Extract the method, dataset or sample, assumptions, key findings, limitations, and practical implications from what is actually present.
- Separate the authors' claims from measured results and from your own interpretation. Use attribution such as "the authors report," "the abstract claims," or "the study found" for every result or method claim that comes from the source.
- Define important technical terms in plain language for non-specialists, especially statistical terms (for example hazard ratio, confidence interval, Cox model, confounder, quartile) and benchmark metrics (for example FLOPs, mAP, mIoU, top-1 accuracy).
- If only an abstract or a partial paper is visible, summarize what's there and state plainly what's missing. Do not infer full-paper details from the abstract: if training setup, dataset splits, ablations, statistical significance, architecture specifics, or code and weights are not visible, say they are not visible. Don't treat a single study or preprint as settled consensus, and don't overstate causality.
Report with concise headings. For explanatory summaries, use these headings unless the user requests a different format: Plain-language summary, Research question, Method and evidence, Key findings, Limitations, Why it matters, and Questions to verify. Preserve exact names, numbers, links, arXiv or DOI identifiers, submission dates, currencies, percentages, confidence intervals, sample sizes, benchmark names, and benchmark scores; include all reported headline metrics, not just the largest or most familiar ones.
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 · 41 lines · 66 tokens per session scan A a6f7fbc4f51c
paper-reader is a skill published in the GitHub repository surfmind-space/awesome-surfmind (7 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 741 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 2026-08-31.
Other skills, from other repositories
cs-master
Expert computer scientist for algorithms, complexity analysis, and distributed systems.
guidance
A guide for answering questions about installing and configuring QwenPaw, a software tool with local documentation. It says to check those documents first and use official website information only when needed.
edu-math-tutorial
A Chinese-language guide for turning a maths problem into a step-by-step teaching video. It explains how to break down the solution, write narration, format equations, and structure scenes.
learning-opportunities
Facilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema changes, refactors). Use when completing features, making design decisions, or when user asks to understand code better. Triggers on "learning exercise", "help me…
video-tutorial-maker
Create scripted tutorial videos with narration, TTS, aligned subtitles, MP4 rendering, and platform variants. Use when Codex needs to create or revise tutorial, explainer, product walkthrough, course, demo, or short-form videos; generate 16:9 landscape output by default unless the user explicitly asks for 9:16, 1:1…
azure-lab-services
Expert knowledge for Azure Lab Services development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring lab plans, VM templates/schedules, VNet-integrated labs…