gen-demo-video

gen-demo-video is a command for coding agents from alphaaiservice/cortex. It costs 131 tokens per session (1,732 once invoked), scanned A, original, MIT.

A command that turns a product brief or project files into a branded product video, with a script, storyboard, voiceover, captions, and rendered MP4.

In plain words
What is it for?
It helps create marketing videos, product demos, explainers, and launch videos in widescreen or vertical formats, using either an HTML template or React-based video code.
Why use it?
It removes the need to plan, animate, record, and assemble a product video manually. The result can be rendered again from versioned source files when the product changes.

Command

Part of the cortex plugin — 43 commands, 13 agents, 1 MCP server shipped together

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.

agentmods
npx agentmods add commands/alphaaiservice/cortex/gen-demo-video
Clone the repo
git clone --depth 1 https://github.com/alphaaiservice/cortex

Or install cortex, the plugin that ships this one along with the rest of its 43 commands, 13 agents, 1 MCP server.

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 gen-demo-video

README.md
[![agentmods](https://agentmods.dev/badge/commands/alphaaiservice/cortex/gen-demo-video.svg)](https://agentmods.dev/commands/alphaaiservice/cortex/gen-demo-video)
Your own site
<a href="https://agentmods.dev/commands/alphaaiservice/cortex/gen-demo-video"><img src="https://agentmods.dev/badge/commands/alphaaiservice/cortex/gen-demo-video.svg" alt="Measured on agentmods" height="20"></a>
Per session 131 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00131 $0.01732
Opus 5 $0.00066 $0.00866
Sonnet 5 $0.00026 $0.00346
Haiku 4.5 $0.00013 $0.00173

Measured 4d ago against content hash 790528434745, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gen-demo-video 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.

commands/gen-demo-video.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Demo / Marketing Video Generator — Template or Code

Produce a branded, re-renderable product video. The video-producer skill auto-loads and defines the pipeline + quality bar. Two engines:

  • HyperFrames (default) — open-source HTML-template → MP4 CLI; best for high-quality branded templated video. Proven in your FrameCraft product.
  • Remotion — React/TypeScript; best for code-driven animation. Productizes the voicemint/marketing-video workflow.

$ARGUMENTS = PRD path, product/idea text, or empty (infer from the current project).


Section 0: Input & Context

0a. Parse input & flags

  • File path → PRD. Free text → brief. Empty → scan project (PRD.md, README.md, BRAND_GUIDE.md, mockups/).
  • Flags: --engine=hyperframes|remotion (default hyperframes), --length= (default 60s), --style=marketing|demo|explainer|launch (default marketing), --aspect=16:9|9:16 (default 16:9; 9:16 for social), --quality=draft|standard|high (HyperFrames; default high), --fps=24|30|60 (default 30), --voice=on|off (default on), --music=on|off (default off).

0b. Gather assets (reuse)

  • BRAND_GUIDE.md → logo, OKLCH colors, fonts (@remotion/google-fonts).
  • mockups/ screenshots (from /gen-mockup) → product B-roll. If none and the video is a demo, suggest running /gen-mockup first or fall back to animated UI built in Remotion.
  • Existing voicemint/marketing-video is the reference implementation for structure.

Section 1: Script & Storyboard (FIRST)

1a. Write the script

Tight spoken script for the target length. Structure by style:

  • marketing: hook (3s) → problem → solution → 2–3 key features → CTA.
  • demo: intro → walk through the core flow screen-by-screen → outro/CTA.
  • explainer: question → concept → how-it-works → payoff.
  • launch: tease → reveal → what's new → availability/CTA.

1b. Storyboard → src/data/script.ts

Break into 5–9 scenes; for each: visual, on-screen text, duration (frames @ 30fps), voiceover line. This data file is the single edit point for copy/timing. Confirm the scene outline to the user in one line before scaffolding.

Read the full file on GitHub · 93 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. 4d ago First seen · 93 lines · 131 tokens per session scan A 790528434745

Subscribe to this mod's changes

gen-demo-video is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 29d ago), licensed MIT. It adds 131 tokens to every session and 1,732 once invoked, about $0.0007 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.