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 haidrrrry/claude-remotion-skill --skill remotion-motion-graphicsgit clone --depth 1 https://github.com/haidrrrry/claude-remotion-skillWrote 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/haidrrrry/claude-remotion-skill/remotion-motion-graphics)<a href="https://agentmods.dev/skills/haidrrrry/claude-remotion-skill/remotion-motion-graphics"><img src="https://agentmods.dev/badge/skills/haidrrrry/claude-remotion-skill/remotion-motion-graphics/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/haidrrrry/claude-remotion-skill/remotion-motion-graphics"><img src="https://agentmods.dev/badge/skills/haidrrrry/claude-remotion-skill/remotion-motion-graphics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
- Socket pass
- Snyk pass
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 65 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 72 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 83 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00141 | $0.01930 |
| Opus 5.5 | $0.00056 | $0.00772 |
| Sonnet 5.5 | $0.00028 | $0.00386 |
| Haiku 4.5 | $0.00014 | $0.00193 |
Grade A, and why
remotion-motion-graphics 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 2mo 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remotion Motion Graphics
Remotion renders React components frame-by-frame into video. Code quality is not the bottleneck — motion design craft is. Untrained generation produces linear easing, opacity-only fades, simultaneous entrances, flat colors, and no texture. That is the "generic AI video" look. This skill exists to prevent it.
Non-negotiable rules (apply to EVERY composition)
- NEVER use linear interpolation. Every
interpolate()gets an easing curve; every entrance prefersspring(). AlwaysextrapolateLeft/Right: "clamp". - Entrances animate 2–3 properties together (opacity + translateY + scale). A lone fade is forbidden.
- Stagger everything. Lists, words, rays, cards: 3–6 frame offsets. Nothing enters simultaneously.
- Exits exist and are faster than entrances (~10 frames vs ~20).
- Five-layer stack in every scene, bottom to top: background mesh → assets → graphics/type → color grade → grain + vignette. Never a flat solid background.
- Every still image gets Ken Burns (slow scale 1→1.08 + pan). Every video asset
uses
<OffthreadVideo>, never<Video>. - Idle elements breathe: anything on screen >2s gets sin-wave micro-motion.
- All timing derives from
fpsviauseVideoConfig(). No magic frame numbers. - One theme object at the top of the project (colors, easings, spring presets, fonts). Never inline a hex color or easing in a component.
- Render, extract frames, LOOK at them, fix, re-render. Never deliver an unverified render. This loop is mandatory — see Verification below.
Workflow
Step 1 — Scope
Determine: duration, fps (30 default; 60 only for heavy fast motion), dimensions
(1080×1920 Reels/Shorts, 1920×1080 landscape), what assets exist (images, footage,
audio, logos), and whether this is a new composition or an edit to an existing project.
If editing an existing project: read src/ fully first, find the theme (or create one),
and refactor violations of the rules above before adding features.
What ships with it
3 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.
- 2mo ago First seen · 137 lines · 141 tokens per session scan A 7bc57dcc03c9
remotion-motion-graphics is a skill published in the GitHub repository haidrrrry/claude-remotion-skill (849 stars, last pushed 2mo ago), licensed MIT. It adds 141 tokens to every session and 1,930 once invoked, about $0.0006 per session on Opus 5.5. 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.
remotion-motion-graphics compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| remotion-motion-graphicshaidrrrry/claude-remotion-skill | Skill | 849 | 2mo ago | MIT | A | 141 | Claude Code, Codex |
| create-videoDojoCodingLabs/remotion-superpowers | Skill | 157 | 8d ago | MIT | A | 50 | Claude Code |
| review-videoDojoCodingLabs/remotion-superpowers | Skill | 157 | 8d ago | MIT | A | 75 | Claude Code |
| create-shortDojoCodingLabs/remotion-superpowers | Skill | 157 | 8d ago | MIT | A | 58 | Claude Code |
| generate-clipDojoCodingLabs/remotion-superpowers | Skill | 157 | 8d ago | MIT | A | 32 | Claude Code |
| transcribeDojoCodingLabs/remotion-superpowers | Skill | 157 | 8d ago | MIT | A | 75 | Claude Code |
| add-captionsDojoCodingLabs/remotion-superpowers | Skill | 157 | 8d ago | MIT | A | 89 | Claude Code |