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/mcpware/pagecast/record-demonpx skills add mcpware/pagecast --skill record-demogit clone --depth 1 https://github.com/mcpware/pagecastWrote 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/mcpware/pagecast/record-demo)<a href="https://agentmods.dev/skills/mcpware/pagecast/record-demo"><img src="https://agentmods.dev/badge/skills/mcpware/pagecast/record-demo.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 | $0.00064 | $0.02456 |
| Opus 5 | $0.00032 | $0.01228 |
| Sonnet 5 | $0.00013 | $0.00491 |
| Haiku 4.5 | $0.00006 | $0.00246 |
Grade A, and why
record-demo scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:<port> | head -1 # verify How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record Demo — Storytelling Product Demo with Auto-Zoom
Record a polished, story-driven product demo using Pagecast's auto-zoom pipeline.
This is NOT random clicking. You are a demo director — you plan the story, choreograph the interactions, and iterate until the output is GitHub-README quality.
Phase 1: Understand the Product
Before touching the browser, understand what you're demoing.
1a. Read the product
Read: <product-path>/README.md
Read: <product-path>/package.json
Extract:
- One-liner: What does this product do? (1 sentence)
- Pain point: What problem does it solve?
- Key features: List 3-5 demo-worthy features, ranked by wow-factor
- Target audience: Who is this README for? (developers, designers, managers)
1a.1. Sandbox mode (if available)
If the product has E2E tests with a sandbox/fixture setup, use that to create fake demo data instead of exposing real user data. Look for test fixtures that create temp directories with realistic content. Start the app pointing to the sandbox (e.g., HOME=/tmp/sandbox node app.js). This lets you safely demo ALL features including destructive ones like delete and move.
1b. Read the frontend (if web app)
Find the actual CSS selectors you'll need:
Read: <product-path>/src/ui/index.html (or equivalent)
Read: <product-path>/src/ui/app.js (or equivalent)
Extract:
- Search input selector
- Main list/card selectors
- Button/action selectors
- Navigation elements
- Loading indicator (to know when page is ready)
- Any
data-*attributes useful for targeting
1c. Check existing demos
ls <product-path>/docs/demo* <product-path>/docs/screenshot* 2>/dev/null
If demos exist, review them to understand what was shown before and what can be improved.
Phase 2: Plan the Demo Story
A good demo tells a story: Problem → Discovery → Solution → Wow moment
Story structure (8-15 seconds total)
| Beat | Time | What happens | Why |
|---|---|---|---|
| 1. Context | 0-1s | Show the full UI, let viewer orient | First frame must work as static screenshot |
| 2. Pain point | 1-3s | Show the problem the product solves | "Look how messy/hard this is" |
| 3. Feature A | 3-6s | First key interaction | The primary use case |
| 4. Feature B | 6-9s | Second interaction | Shows breadth |
| 5. Wow moment | 9-12s | The "aha" feature | Most impressive capability |
| 6. Result | 12-15s | Pause on the outcome | Let viewer see what happened |
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 · 260 lines · 64 tokens per session scan A 97aae90b9ad7
record-demo is a skill published in the GitHub repository mcpware/pagecast (44 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 2,456 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
demo
Record a short demo VIDEO of a PR or feature — drive the repo's web UI in a real headless browser, capture the session, and composite a titled, size-capped mp4 with ffmpeg. Use on the docker QA image when the deliverable is a playable demo clip (single walkthrough or before/after comparison), not a text/screenshot…
session-context
Lightweight demo-vid-mcp session start prompt (tools, recall/save actions).
faceless-explainer
Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a…
slideshow
Author a HyperFrames slideshow — a presentation, pitch deck, or interactive deck with discrete slides, fragment reveals, branching, hotspot navigation, and built-in presenter mode with speaker notes; also converts an existing page into a deck. Output is a navigable deck, not a rendered MP4. If the user didn't…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
hyperframes-core
The HyperFrames composition contract — build one renderable project. Use for composition structure, the data- timing attributes, class="clip", tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Also covers Tailwind projects and the STORYBOARD.md / SCRIPT.md…