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/itallstartedwithaidea/agent-skills/programmatic-videonpx skills add itallstartedwithaidea/agent-skills --skill programmatic-videogit clone --depth 1 https://github.com/itallstartedwithaidea/agent-skillsWrote 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/itallstartedwithaidea/agent-skills/programmatic-video)<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/programmatic-video"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/programmatic-video.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 | $0.00031 | $0.01585 |
| Opus 5 | $0.00015 | $0.00792 |
| Sonnet 5 | $0.00006 | $0.00317 |
| Haiku 4.5 | $0.00003 | $0.00159 |
Grade A, and why
programmatic-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 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Programmatic Video
Part of Agent Skills™ by googleadsagent.ai™
Description
Programmatic Video enables React-based video rendering with Remotion, where every frame is a React component and every animation is expressed in code. The agent builds video compositions with sequences, transitions, spring animations, and data-driven content, producing MP4/WebM output rendered in headless Chromium without any video editing software.
Traditional video editing is manual, non-reproducible, and impossible to template. Programmatic video treats video as code: compositions are versioned in git, parameterized for batch rendering, and tested with snapshot assertions. A single template can generate thousands of personalized videos by changing the input data—product demos, social media clips, onboarding sequences, or marketing videos, each customized per recipient.
Remotion's architecture maps React's component model to video: each component receives a frame number and the total durationInFrames, using these to calculate animations, transitions, and timing. The agent composes scenes from reusable components, orchestrates their timing with <Sequence> wrappers, and applies spring-based physics animations for natural motion.
Use When
- Creating videos from code without video editing software
- Generating personalized or data-driven video content at scale
- Building animated explainers, product demos, or social media clips
- Automating video production in CI/CD pipelines
- The user requests "programmatic video", "Remotion", or "video from code"
- Producing video assets with consistent branding across hundreds of variants
How It Works
graph TD
A[Video Specification] --> B[Define Composition: FPS + Duration]
B --> C[Build Scene Components]
C --> D[Arrange with Sequences]
D --> E[Add Spring Animations]
E --> F[Inject Dynamic Data]
F --> G[Preview in Browser]
G --> H{Approved?}
H -->|No| C
H -->|Yes| I[Render: Headless Chromium]
I --> J[Encode: MP4 / WebM]
J --> K[Output Video File]
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 · 174 lines · 31 tokens per session scan A 407eb65b59c7
programmatic-video is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (36 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,585 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
story-illustrator
Generates a consistent illustrated image for every scene of a story — keeping characters, locations, and visual style coherent across the whole sequence using cascading reference images. Reads a {slug}scenes.json (from scene-splitter), proposes a visual style, ASKS the user for the aspect ratio and image model…
story-narrator
Generates one expressive narration MP3 per scene for an English storybook, using the ElevenLabs MCP (texttospeech). Reads {slug}scenes.json (from scene-splitter), proposes a warm storyteller voice, drafts the narration text per scene (optionally with Eleven v3 audio tags for emotion), lets the user review, then…
creative-generate
Generate creator-quality ad creatives — text-free key visuals plus composed banners — from a strategy-grounded brief. Use when the user asks to create ad creatives, generate ad images or banners, make banner variations, design display / social ad creatives, or asks in Japanese (クリエイティブ作成 / バナー作成 / 広告画像を生成 /…
scene-splitter
Splits a plain English story into a numbered list of SCENES — each scene being one moment that gets exactly one illustration AND one narration clip downstream. The first step of the AI Storybook pipeline. Tuned for beginner-level stories (short sentences, 8-12 scenes), with a per-scene length cap so each scene fits…
storybook-pipeline
Orchestrator that runs the full AI Storybook pipeline end-to-end on one English story. Dispatches the 4 component skills in order — scene-splitter → story-illustrator → story-narrator → story-html-publisher — using the locked filename convention {slug} and {slug}partNN.{png,mp3} so every image and audio clip pairs by…
3d-image-renderer
Generate PNG images by building a real Three.js 3D scene and capturing one frame headlessly — no image model involved. Takes a text prompt and an aspect ratio (1:1, 16:9, or 9:16) and produces a rendered PNG. Use this skill whenever the user asks to generate, create, or render an image, picture, scene, wallpaper…