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 skills add siegerts/skill-canvas-video --skill creating-canvas-video-animationsgit clone --depth 1 https://github.com/siegerts/skill-canvas-videoWrote 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/siegerts/skill-canvas-video/creating-canvas-video-animations)<a href="https://agentmods.dev/skills/siegerts/skill-canvas-video/creating-canvas-video-animations"><img src="https://agentmods.dev/badge/skills/siegerts/skill-canvas-video/creating-canvas-video-animations/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/skills/siegerts/skill-canvas-video/creating-canvas-video-animations"><img src="https://agentmods.dev/badge/skills/siegerts/skill-canvas-video/creating-canvas-video-animations.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 | $0.00078 | $0.01227 |
| Opus 5 | $0.00039 | $0.00613 |
| Sonnet 5 | $0.00016 | $0.00245 |
| Haiku 4.5 | $0.00008 | $0.00123 |
Grade A, and why
creating-canvas-video-animations 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 11d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Canvas Video Animations
Build animated videos as self-contained HTML + JS files rendered on HTML5 Canvas, exportable to MP4.
When to use
- User wants to create an animated video, motion graphic, or visual clip
- User describes a scene, storyline, or visual sequence they want rendered
- User wants to export canvas animation to MP4
Workflow
Copy this checklist and track progress:
Animation Progress:
- [ ] Step 1: Clarify requirements with user
- [ ] Step 2: Plan the timeline
- [ ] Step 3: Gather visual references
- [ ] Step 4: Build the animation class
- [ ] Step 5: Create the HTML host
- [ ] Step 6: Validate the animation
- [ ] Step 7: Iterate — preview in browser, adjust timing/layout, repeat 6→7
- [ ] Step 8: Export to MP4 (only when animation is finalized)
Step 1: Clarify with the user — ask about:
- Format: horizontal (1920×1080) or vertical (1080×1920) or both. See PLATFORMS.md for platform-specific dimensions.
- Duration in seconds
- Visual style preferences (dark/light, color palette, retro, futuristic, minimal)
- Content: what text, UI elements, code snippets, or scenes to show
- Any custom fonts (loaded via FontFace API before animation starts)
- Whether they need an export script
Step 2: Plan the timeline — break the animation into phases with clear start/end times. See TIMELINE.md.
Step 3: Gather visual references — ask the user to paste or drag in screenshots, mockups, or reference images. Redraw these as canvas primitives (paths, shapes, gradients) — do not embed images directly. This keeps everything vector-clean and resolution-independent. See ELEMENTS.md for the redrawing approach and reusable drawing patterns.
Step 4: Build the animation class — one JS class per animation. See ARCHITECTURE.md.
Step 5: Create the HTML host — minimal HTML that loads fonts, creates canvas, instantiates the animation. See HTML-TEMPLATE.md.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 102 lines · 78 tokens per session scan A f43837a4b184
creating-canvas-video-animations is a skill published in the GitHub repository siegerts/skill-canvas-video (2 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 1,227 once invoked, about $0.0004 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.
Other skills, from other repositories
fal
Use when calling a fal.ai endpoint by id to generate image, audio, or video from JS/Python/curl: subscribe vs submit, queue states, ED25519 webhook signature verification, per-call cost, or migrating off @fal-ai/serverless-client. NOT which model or art direction (that is ai-media); NOT the same models on another…
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
threejs-interaction
Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.
threejs-textures
Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…