claude-remotion-kickstart: Command for Claude Code

.claude/commands/generate-video.md

generate-video is a command for Claude Code from jhartquist/claude-remotion-kickstart. It costs 15 tokens per session (1,410 once invoked), scanned A, original, MIT.

A command for creating videos with Google's Veo 3.1 models through Replicate, an online service for running AI models. It can use text, reference images and optional start or end frames.

In plain words
What is it for?
Use it to create 4-, 6- or 8-second videos in supported aspect ratios, with audio and 1080p output.
Why use it?
It handles the model selection and waiting for the video result while the generation runs.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument; mentions Claude Code.

This is jhartquist/claude-remotion-kickstart's own configuration. It tells Claude Code how to work on claude-remotion-kickstart itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-remotion-kickstart configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jhartquist/claude-remotion-kickstart. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jhartquist/claude-remotion-kickstart/main/.claude/commands/generate-video.md
Clone the repo
git clone --depth 1 https://github.com/jhartquist/claude-remotion-kickstart

Made for: Claude Code.

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 generate-video

README.md
[![agentmods](https://agentmods.dev/badge/commands/jhartquist/claude-remotion-kickstart/generate-video/github.svg)](https://agentmods.dev/commands/jhartquist/claude-remotion-kickstart/generate-video)
Your own site
<a href="https://agentmods.dev/commands/jhartquist/claude-remotion-kickstart/generate-video"><img src="https://agentmods.dev/badge/commands/jhartquist/claude-remotion-kickstart/generate-video/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 generate-video

Your own site · 80×15
<a href="https://agentmods.dev/commands/jhartquist/claude-remotion-kickstart/generate-video"><img src="https://agentmods.dev/badge/commands/jhartquist/claude-remotion-kickstart/generate-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,410 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00015 $0.01410
Opus 5 $0.00008 $0.00705
Sonnet 5 $0.00003 $0.00282
Haiku 4.5 $0.00002 $0.00141

Measured 10d ago against content hash ee7a37401d7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

generate-video 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 10d 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.

allowed-tools: mcp__replicate__*, AskUserQuestion, Bash(curl*, sleep*)
.claude/commands/generate-video.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

context

This command uses the Replicate MCP server to generate videos with Google's Veo 3.1 Fast model by default.

Model options:

  • veo-3.1-fast (default): Faster and cheaper, great for most use cases
  • veo-3.1: Higher fidelity, use when user specifically requests "full model" or "high quality"

Veo 3.1 features:

  • Text-to-video with context-aware audio
  • Starting frame support (reference image)
  • Ending frame support (last frame)
  • Multiple reference images for style guidance (full model only)
  • 16:9, 9:16, 1:1 aspect ratios
  • 1080p resolution
  • 4, 6, or 8 second durations

Important: Video generation takes 90-120 seconds, so this command uses polling instead of waiting.

task

Generate a video using Veo 3.1 Fast (or full model if specified) with the prompt provided in $1:

  1. Determine which model to use:

    • Check if prompt contains keywords: "full model", "high quality", "high fidelity", "veo 3.1"
    • If yes: use google/veo-3.1 (full model)
    • If no: use google/veo-3.1-fast (default)
    • Inform user which model is being used
  2. Parse arguments and analyze prompt:

    • Main prompt is in $1 (required)
    • Ask if they want to use a starting frame image (optional)
    • Ask for aspect ratio: 16:9, 9:16, or 1:1 (default: 16:9)
  3. Intelligently determine duration (4, 6, or 8 seconds):

    • 4 seconds for:

      • Short phrases (1-5 words)
      • Quick actions or movements
      • Simple gestures
      • Example: "waves hello", "nods in agreement", "Hello there"
    • 6 seconds for:

      • Medium phrases (6-12 words)
      • Standard dialogue delivery
      • Most talking head content
      • Example: "This entire video was created using Claude Code"
    • 8 seconds for:

      • Long phrases (13+ words)
      • Complex sentences with pauses
      • Detailed actions or multiple movements
      • Example: "In this tutorial, I'm going to show you how to build amazing applications"
    • Count words in quoted dialogue or estimate speech length

    • Consider natural speaking pace: ~2 words per second

    • Inform user of your duration choice and reasoning

Read the full file on GitHub · 168 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. 10d ago First seen · 168 lines · 15 tokens per session scan A ee7a37401d7d

Subscribe to this mod's changes

generate-video is a command published in the GitHub repository jhartquist/claude-remotion-kickstart (116 stars, last pushed 9mo ago), licensed MIT. It adds 15 tokens to every session and 1,410 once invoked, about $0.0001 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.