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 Fergana-Labs/stash --skill slidesgit clone --depth 1 https://github.com/Fergana-Labs/stashWrote 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/fergana-labs/stash/slides)<a href="https://agentmods.dev/skills/fergana-labs/stash/slides"><img src="https://agentmods.dev/badge/skills/fergana-labs/stash/slides/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/fergana-labs/stash/slides"><img src="https://agentmods.dev/badge/skills/fergana-labs/stash/slides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.00970 |
| Opus 5.5 | $0.00010 | $0.00388 |
| Sonnet 5.5 | $0.00005 | $0.00194 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
slides 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building slide decks
A slide deck is a single HTML page with html_layout: "fixed-aspect" whose
<body> contains one <section class="slide"> per slide.
The canvas — 1920 × 1080 (16:9)
Every slide is a fixed 1920 × 1080 px canvas with overflow:hidden.
Stay inside a 64 px safe-area margin (working area 1792 × 952 px).
Nothing should scroll inside a slide; the viewer scales the canvas to fit
the viewport, and the exporter renders at native 1920×1080.
Required structure
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<title>Deck title</title>
<script src="https://cdn.tailwindcss.com"></script>
<link href="https://cdn.jsdelivr.net/npm/@fortawesome/fontawesome-free@6/css/all.min.css" rel="stylesheet">
<style>
/* Belt-and-suspenders — the viewer enforces these too. */
section.slide {
width: 1920px; height: 1080px;
overflow: hidden; position: relative;
box-sizing: border-box;
padding: 64px;
}
</style>
</head>
<body>
<section class="slide" data-type="cover">…</section>
<section class="slide" data-type="content">…</section>
<section class="slide" data-type="content">…</section>
<section class="slide" data-type="final">…</section>
</body>
</html>
Page types (data-type, optional but recommended)
cover— title slide.toc— table of contents.chapter— section divider.content— regular content slide.final— thanks / Q&A / contact slide.
These let presenter view and future templates target slides by role.
Typography
- Title text: ≥ 56 px.
- Body text: ≥ 28 px.
- Footnotes / captions: ≥ 20 px.
- Use the system font stack or one CDN font (Inter, Geist).
Avoid
@font-face— it adds latency in export.
Recommended libraries (all CDN-loadable)
| Need | Use |
|---|---|
| Charts | Chart.js for 1–2 charts per slide; ECharts for dashboards; D3 only when custom |
| Tables | Plain <table> + Tailwind classes. No DataTables. |
| Icons | Font Awesome 6 (CDN) or Lucide |
| Code | Shiki (preferred, vector-clean) or highlight.js |
| Math | KaTeX with auto-render (never MathJax inside iframe) |
| Diagrams | Mermaid via CDN, render once on load |
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 · 104 lines · 24 tokens per session scan A 2ab40e0c9951
slides is a skill published in the GitHub repository Fergana-Labs/stash (340 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 970 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
modality-preserving-binary-offload
Persist binary output with a mime-derived extension and a matching saved-file message so downstream tools keep the right modality.
preview-first-large-output-messages
Annotate persisted tool results with a preview-first header that leads with the saved artifact reference and shows the first slice before truncation.
gws-sheets
Google Sheets: Read and write spreadsheets.
recipe-create-presentation
Create a new Google Slides presentation and add initial slides.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
gws-docs
Read and write Google Docs.