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 agentmods add skills/waybarrios/opencode-power-pack/paper-summarizernpx skills add waybarrios/opencode-power-pack --skill paper-summarizergit clone --depth 1 https://github.com/waybarrios/opencode-power-packWrote 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/waybarrios/opencode-power-pack/paper-summarizer)<a href="https://agentmods.dev/skills/waybarrios/opencode-power-pack/paper-summarizer"><img src="https://agentmods.dev/badge/skills/waybarrios/opencode-power-pack/paper-summarizer.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00934 |
| Opus 5 | $0.00023 | $0.00467 |
| Sonnet 5 | $0.00009 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
paper-summarizer 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- paper-summarizer — 86% identical, 11 lines differ
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Summarizer
Extract actionable insights from academic and technical papers.
Summary Format
# Paper Summary: <Paper Title>
**Authors:** [Author list]
**Published:** [Journal/Conference, Date]
**Link:** [URL]
**Quality:** Peer-reviewed / Preprint / Workshop paper
## TL;DR
[1-2 sentence summary of the key contribution]
## Problem
[What problem does this paper address? Why does it matter?]
## Approach
[Methodology in plain language — what did they do?]
## Key Findings
Anchor each finding to the paper so readers can verify. Use **§** for sections, **Fig.** / **Table** when the evidence is visual or tabular.
1. **[Finding 1]:** [Description with key metrics/numbers] — *Evidence:* §[N] [section name]; [Fig. X / Table Y if applicable]
2. **[Finding 2]:** [Description] — *Evidence:* §[N] …
3. **[Finding 3]:** [Description] — *Evidence:* §[N] …
## Claim–evidence map
| # | Claim (one line) | Where in paper | Type |
|---|------------------|----------------|------|
| 1 | [Claim] | §3.2 Results, Table 2 | Empirical |
| 2 | [Claim] | §1 Introduction | Stated goal |
| 3 | [Claim] | Fig. 4 | Qualitative |
Use this table for citation-audit alignment against the project's own research notes. If the PDF has no section numbers, use **page** or **heading text** instead of §.
## Practical Implications
[What does this mean for practitioners? How can we use these findings?]
- For the current stack: [Specific applicability to Rust/TS/Python work]
- For current projects: [How this might inform current work]
## Limitations
- [Limitation 1: e.g., small sample size, specific domain]
- [Limitation 2: e.g., not replicated, theoretical only]
## Related Work
- [Paper 1] — [How it relates]
- [Paper 2] — [How it relates]
## Verdict
**Reliability:** High / Medium / Low
**Relevance to us:** High / Medium / Low
**Action:** Apply directly / Consider for future / Interesting but not actionable
Process
Step 1 — Access the Paper
- Check arXiv, PubMed, Google Scholar for open-access versions
- If behind a paywall, note this and work with the abstract and any available supplementary material
- Check for author's personal page (often has preprints)
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.
- 6d ago First seen · 111 lines · 46 tokens per session scan A be91c68b3b58
paper-summarizer is a skill published in the GitHub repository waybarrios/opencode-power-pack (490 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 934 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
sci-figure
Extracts figures and sub-figures from academic PDF papers. Supports Fig/Figure, Scheme, Chart, Supplementary Figure, Extended Data Figure (Nature), and Chinese equivalents (图/方案/示意图/附图/补充图). Sub-figure label recognition supports (a)/(A)/a)/(i)/(1)/a. formats. High-quality PNG output at configurable DPI. Use when user…
sci-download
学术论文 PDF 下载。支持 8 个数据源：Elsevier、Springer Nature、IEEE Xplore、 arXiv、Unpaywall、Semantic Scholar、PubMed Central、知网(CNKI)。 自动根据 DOI 前缀路由到对应数据源，未知 DOI 自动尝试 Unpaywall → Semantic Scholar。.
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.