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/agent0ai/space-agent/pdf-reportnpx skills add agent0ai/space-agent --skill pdf-reportgit clone --depth 1 https://github.com/agent0ai/space-agentWrote 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/agent0ai/space-agent/pdf-report)<a href="https://agentmods.dev/skills/agent0ai/space-agent/pdf-report"><img src="https://agentmods.dev/badge/skills/agent0ai/space-agent/pdf-report.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 | $0.00014 | $0.01072 |
| Opus 5 | $0.00007 | $0.00536 |
| Sonnet 5 | $0.00003 | $0.00214 |
| Haiku 4.5 | $0.00001 | $0.00107 |
Grade A, and why
PDF Report 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 4d 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:
- PDF Report — 100% identical, 83 lines differ
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill when the user wants a browser-generated PDF report, a downloaded PDF summary, or a PDF built from structured data or custom HTML.
load helper
- Import
/mod/_core/skillset/ext/skills/pdf-report/pdf-report.js - Prefer the helper instead of hand-writing raw
%PDFstrings - The helper renders HTML and CSS to canvas, converts that into a valid downloadable PDF, and also exposes a structured report builder
helpers
await import("/mod/_core/skillset/ext/skills/pdf-report/pdf-report.js")buildReportHtml(report)->{ html, css, backgroundColor, widthPx }createPdfFromReport({ report, ...options })->Uint8ArraydownloadPdfFromReport({ report, filename?, page?, widthPx?, scale?, jpegQuality?, html2canvasOptions? })->{ downloaded: true, filename, byteLength }createPdfFromHtml({ html, css?, widthPx?, backgroundColor?, page?, scale?, jpegQuality?, html2canvasOptions? })->Uint8ArraydownloadPdfFromHtml({ html, css?, filename?, widthPx?, backgroundColor?, page?, scale?, jpegQuality?, html2canvasOptions? })->{ downloaded: true, filename, byteLength }downloadPdfBytes(bytes, filename?)->{ downloaded: true, filename, byteLength }
structured report shape
report.title,eyebrow,subtitle,summary,introHtml,footer,widthPx,filenamereport.sections[]may usetitle,eyebrow,text,items,metrics,cards,columns, and rawhtmlreport.thememay overrideaccentColor,backgroundColor,borderColor,surfaceColor,textColor,mutedColor,fontFamily, andcustomCss
pdf and html options
page.size:letterora4page.orientation:portraitorlandscapepage.marginPtwidthPx,backgroundColor,scale,jpegQuality,filename
guidance
- Use
downloadPdfFromReport(...)when the user wants a clean report quickly from structured data - Use
downloadPdfFromHtml(...)when the user wants a custom visual direction or tighter markup control - Change theme colors, typography, section structure, cards, columns, and raw HTML to match the request; do not reuse one canned layout unless the user asked for it
- Keep the HTML self-contained and pass any extra styling through
cssorreport.theme.customCss - After the download starts, answer the user with a brief summary
examples Downloading a structured PDF report _____javascript const pdfReport = await import("/mod/_core/skillset/ext/skills/pdf-report/pdf-report.js") return await pdfReport.downloadPdfFromReport({ filename: "project-status.pdf", report: { title: "Project Status", eyebrow: "Sprint 14", subtitle: "Frontend runtime workstream", summary: "The helper move is complete and the remaining work is doc cleanup.", theme: { accentColor: "#0b6bcb", backgroundColor: "#eef5ff", surfaceColor: "#ffffff" }, sections: [ { title: "Highlights", items: [ "Skill-specific helpers now live inside their owning skill folders.", "PDF output is built from generic HTML and CSS instead of a canned weather wrapper." ] }, { title: "Counts", metrics: [ { label: "Open items", value: "2" }, { label: "Blocked", value: "0" } ] } ], footer: "Generated locally in the browser." } })
Downloading a custom HTML PDF
_____javascript
const pdfReport = await import("/mod/_core/skillset/ext/skills/pdf-report/pdf-report.js")
return await pdfReport.downloadPdfFromHtml({
filename: "brief.pdf",
widthPx: 900,
page: { size: "a4", marginPt: 28 },
css: .brief { padding: 48px; font-family: Georgia, serif; color: #1f2937; } .brief h1 { margin: 0 0 12px; font-size: 36px; } .brief .lede { font-size: 18px; color: #4b5563; } ,
html: <article class="brief"> <h1>Research Brief</h1> <p class="lede">This layout is fully custom HTML and CSS.</p> <p>Use this path when the user wants a specific art direction instead of the built-in structured report layout.</p> </article>
})
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.
- 4d ago First seen · 100 lines · 14 tokens per session scan A 48fea673d93d
PDF Report is a skill published in the GitHub repository agent0ai/space-agent (1,392 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 1,072 once invoked, about $0.0001 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
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.
paddleocr-doc-parsing
Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表…
paper-reader
Use when user asks to "read paper", "analyze paper", "summarize paper", "读论文", "分析文献", "帮我看一下这篇paper", "论文笔记", or provides a PDF file that appears to be an academic paper. Specialized for CV/DL papers. Also supports Zotero integration: "读一下这篇论文 ...", "快速看一下这篇论文 ...", "批判性分析这篇论文 ...", "读一下 Zotero 里的 XXX", "批量读一下 Zotero…
citra
Skill "citra" from SylphxAI/pdf-reader-mcp, covering citra — pdf evidence for agents, install, or, tools and sdk.
graphic-ebook
Creates professionally designed B2B SaaS e-books in HTML + CSS, exported as print-ready PDF. 3–10 pages, 9 style presets, 11 page layout types. Trigger when user says "create an ebook", "design a lead magnet", "make a PDF guide", "build a gated content piece", "write a B2B ebook", "design a white paper", "create a…
larksnap-fetch
把飞书/Lark 文档或普通网页抓取并保存到本地,也能编辑用户有权限的飞书文档,并用已登录浏览器执行一次网页搜索。用户要求下载、导出、抓取、写入飞书文档,或联网搜索资料/参考链接时使用本技能,即使没有提到 larksnap。底层通过技能自带 daemon 桥接已登录的 larksnap 浏览器扩展;arXiv 使用独立脚本。.