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.
curl -O https://raw.githubusercontent.com/jhartquist/claude-remotion-kickstart/main/.claude/commands/generate-video.mdgit clone --depth 1 https://github.com/jhartquist/claude-remotion-kickstartWrote 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/commands/jhartquist/claude-remotion-kickstart/generate-video)<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.
<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>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 | $0.00015 | $0.01410 |
| Opus 5 | $0.00008 | $0.00705 |
| Sonnet 5 | $0.00003 | $0.00282 |
| Haiku 4.5 | $0.00002 | $0.00141 |
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*) 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:
-
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
-
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)
-
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
-
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.
- 10d ago First seen · 168 lines · 15 tokens per session scan A ee7a37401d7d
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.
Other commands, from other repositories
video
Video projects - list, resume, or create new.
generate-voiceover
Generate AI voiceover from script.
scene-review
Scene-by-scene review in Remotion Studio (before voiceover).
design
Focused design session for improving video scene visuals using the frontend-design skill.
publish
Publish a finished video to YouTube.
template
List available templates and their features.