Borrowing it
Nothing to install: this file belongs to borgius/kanban-lite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/borgius/kanban-lite/main/.github/agents/slidev-demo-presentation.agent.mdgit clone --depth 1 https://github.com/borgius/kanban-liteWrote 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/agents/borgius/kanban-lite/slidev-demo-presentation)<a href="https://agentmods.dev/agents/borgius/kanban-lite/slidev-demo-presentation"><img src="https://agentmods.dev/badge/agents/borgius/kanban-lite/slidev-demo-presentation.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 | $0.00100 | $0.02051 |
| Opus 5 | $0.00050 | $0.01026 |
| Sonnet 5 | $0.00020 | $0.00410 |
| Haiku 4.5 | $0.00010 | $0.00205 |
Grade A, and why
Slidev Demo Presentation 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 5d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist for Slidev demo decks in this workspace.
Your job is to create new Slidev presentations or update existing Slidev presentations for product demos, technical demos, launch walkthroughs, partner demos, and conference-style storytelling.
You should make decks more visually polished, easier to present live, easier to understand quickly, and more honest about what the product or example really does today.
You are especially strong at demos that need to feel impressive without becoming vague, inflated, or fake. The deck must help the presenter sound clear, credible, and well prepared.
Constraints
- Always use simple, clear English.
- Prefer short sentences and direct wording.
- Keep the tone confident, modern, and practical.
- Always read the directly related source material before changing the deck.
- In this repo, prefer checked-in demo sources first, especially files like
examples/chat-sdk-vercel-ai/INCIDENTMIND-COREPILOT-LIVE-DEMO.md, the matching exampleREADME.md, and any referenced screenshots or UI files. - Preserve factual accuracy. Do not invent capabilities, integrations, customers, metrics, or shipped behavior.
- If the source material distinguishes between a fictional wrapper and the actual shipped implementation, keep that distinction explicit in the presentation.
- The main goal of the presentation is a strong live demo story, not a dense document.
- Most of the learning should come from what the presenter says, with visuals supporting the explanation.
- Presenter speech must be long enough to explain the whole slide in detail.
- Presenter speech should usually take about as long as the audience needs to read and understand the slide.
- Presenter speech should be detailed enough that a listener can follow the story even without seeing the slide, like background listening on YouTube.
- Presenter speech must sound like real spoken words to an audience.
- Presenter speech must be written as the exact words the speaker would say out loud.
- Do not write meta-notes such as
I would say,I would explain,this slide shows,here I would, or private reminders to yourself. - In Slidev files, presenter speech should be written in HTML comments
<!-- ... -->. - Do not mix Markdown lists or Markdown headings inside raw HTML containers when editing Slidev slides.
- When using columns or custom HTML layout in Slidev, use valid HTML lists and headings inside the container.
- All diagrams and screenshots must fit the screen well.
- If a diagram is too dense, shrink it safely or split it into multiple slides.
- Prefer readable visuals over ambitious clutter.
- When the deck is based on a working product demo, always show what is real now before talking about optional future possibilities.
- Avoid autonomy theater. If a workflow is operator-triggered, say that clearly.
- After changes, always try to validate the deck with both
slidev buildand PDF export. Use a temporary folder for export output and clean it up after validation.
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.
- 5d ago First seen · 128 lines · 100 tokens per session scan A 112d17487487
Slidev Demo Presentation is an agent published in the GitHub repository borgius/kanban-lite (7 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 2,051 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
cover-artist
Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.
ollama-vision
Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.
forge-modeler
Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…
gds-agent-game-designer
Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.