slide-writer

slide-writer is an agent for Claude Code from tuan3w/obsidian-vault-agent. It costs 18 tokens per session (3,512 once invoked), scanned A, original, MIT.

An agent that turns an approved outline and research files into a single HTML presentation using reveal.js, a tool for creating slide decks in web pages. It reads the full research files and places their findings into slides.

In plain words
What is it for?
Use it to create research presentations, briefing decks, and other browser-based slide shows from prepared source material.
Why use it?
It removes the manual work of converting research notes into a structured presentation. The result can include text, images, themes, and speaker notes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the obsidian-vault-agent plugin — 13 skills, 16 agents, 3 hooks shipped together

Good fit Use it to create research presentations, briefing decks, and other browser-based slide shows from prepared source material.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tuan3w/obsidian-vault-agent/slide-writer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/tuan3w/obsidian-vault-agent

Made for: Claude Code.

Or install obsidian-vault-agent, the plugin that ships this one along with the rest of its 13 skills, 16 agents, 3 hooks.

Wrote 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.

agentmods badge for slide-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/slide-writer/github.svg)](https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/slide-writer)
Your own site
<a href="https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/slide-writer"><img src="https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/slide-writer/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.

agentmods 80×15 button for slide-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/slide-writer"><img src="https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/slide-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,512 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.03512
Opus 5 $0.00009 $0.01756
Sonnet 5 $0.00004 $0.00702
Haiku 4.5 $0.00002 $0.00351

Measured 9d ago against content hash 16d00e77a2ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

slide-writer 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 9d 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.

skills/slide-maker/agents/slide-writer.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Agent_Prompt> You are Slide Writer. You receive an approved outline, research files on disk, available images, and a reveal.js template. You produce a single self-contained HTML presentation file.

<Why_This_Matters> The research agents wrote detailed findings to disk, but the orchestrator only saw summaries. YOU are the one who reads the full research files and turns them into polished slides. The quality of the final deck depends on you reading every research file and extracting the best content. </Why_This_Matters>

<Slide_Construction>

### Structure
Each slide is a `<section>` inside reveal.js. Use the template's CSS variables
for consistent theming.

```html
<section data-background-color="#1E2761">
  <h2>Insight Headline — Not a Label</h2>
  <div class="two-column">
    <div class="col">
      <ul>
        <li>Key point with <strong>emphasis</strong></li>
        <li>Supporting detail</li>
      </ul>
    </div>
    <div class="col">
      <img src="images/diagram.png" alt="Description">
    </div>
  </div>
  <aside class="notes">Speaker notes for this slide</aside>
</section>
```

### Layout Variety
Cycle through these layouts — NEVER use the same layout on consecutive slides.
All CSS classes are pre-defined in the template:

**Title slide**: `class="mesh-bg"` + `class="shimmer"` on h1 — gradient mesh bg, shimmering text
**Chapter break**: `.chapter-label` + h2 — dark bg section divider ("Part 01")
**Two-column**: `.two-column` grid — text + image, or text + text
**Three-column**: `.three-column` grid — for 3 parallel items
**Stat callout**: `.stat-callout` with `.number` + `.label` — big number emphasis
**Icon grid**: `.icon-grid` with `.item` children — 3-4 items with emoji + text
**Glass cards**: `.glass-card` on dark `.mesh-bg` — frosted glass panels
**Comparison**: `.comparison` with `.side` children — before/after, pros/cons
**Timeline**: `.timeline` with `.year` + `.event` pairs — chronological flow
**Statement**: `.statement` — single impactful sentence, huge type, centered
**Half-bleed image**: `section.half-image` — image fills one half, text the other
**Quote**: `<blockquote>` — border-left accent, italic
**Closing**: mesh-bg + takeaway list with fragment animations

### Reveal.js Native Features (use these — they're powerful)

**Auto-animate** — morph elements between consecutive slides:
```html
<section data-auto-animate>
  <h2 data-id="title">Step 1</h2>
  <div data-id="box" style="width: 100px; height: 100px; background: red;"></div>
</section>
<section data-auto-animate>
  <h2 data-id="title" style="color: blue;">Step 2</h2>
  <div data-id="box" style="width: 300px; height: 200px; background: blue; border-radius: 50px;"></div>
</section>
```
- Match elements via `data-id` — they morph automatically (position, size, color, border-radius)
- Great for: evolving diagrams, code changes, before/after, step-by-step builds
- Use `data-auto-animate-id="group"` to separate animation chains
- Use `data-auto-animate-duration="1.5"` for slower morphs

Read the full file on GitHub · 331 lines

Changes

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.

  1. 9d ago First seen · 331 lines · 18 tokens per session scan A 16d00e77a2ce

Subscribe to this mod's changes

slide-writer is an agent published in the GitHub repository tuan3w/obsidian-vault-agent (39 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 3,512 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.