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 Liamrjohnston/remotion-motion-graphics-skill --skill motion-graphicsgit clone --depth 1 https://github.com/Liamrjohnston/remotion-motion-graphics-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/liamrjohnston/remotion-motion-graphics-skill/motion-graphics)<a href="https://agentmods.dev/skills/liamrjohnston/remotion-motion-graphics-skill/motion-graphics"><img src="https://agentmods.dev/badge/skills/liamrjohnston/remotion-motion-graphics-skill/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/liamrjohnston/remotion-motion-graphics-skill/motion-graphics"><img src="https://agentmods.dev/badge/skills/liamrjohnston/remotion-motion-graphics-skill/motion-graphics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00021 | $0.01813 |
| Opus 5 | $0.00010 | $0.00907 |
| Sonnet 5 | $0.00004 | $0.00363 |
| Haiku 4.5 | $0.00002 | $0.00181 |
Grade A, and why
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 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.
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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion Graphics for AI Videos
Use with remotion-best-practices and cinematic-camera. This skill owns intake, research, authentic assets, reference selection, visual quality, and delivery authorization.
Hard execution contract
Every build must pass scripts/promptible-gate.mjs.
Common paths:
- Claude Code:
.claude/skills/motion-graphics/scripts/promptible-gate.mjs - Other agents:
.agents/skills/motion-graphics/scripts/promptible-gate.mjs
Do not write composition code until the script prints BUILD AUTHORIZED. Do not deliver a render until it prints DELIVERY AUTHORIZED. A failed command is a hard stop.
Stage 1 — concise intake
Ask only for missing choices:
- Format: 4:3 half-screen Instagram insert (1440×1080) or 9:16 full-screen Instagram (1080×1920). Use 16:9 only when explicitly requested.
- Surface: warm light, clean dark, light grid, or dark grid.
- Exact script beat, duration, named products, verified claims, and supplied assets.
Never silently default to dark. If the user delegates surface choice, use warm light.
Stage 2 — research and authentic assets
Read references/research-and-assets.md and references/logo-library.md.
Run the smallest useful research course before concept work:
- Supplied user assets are authoritative. Use them exactly; never redraw or replace them.
- For common products, copy a suitable bundled logo from
assets/logos/into the project and retain its provenance. - If missing, inspect 1–3 authoritative pages: official brand kit/homepage, official docs/product page, then a reputable curated icon source.
- Prefer transparent SVG. Never use screenshots of logos, search-result thumbnails, baked checker/gray backgrounds, unofficial recreations, or hotlinked remote assets.
- For a dashboard/product UI, acquire a real supplied screenshot/recording or an official public product/docs screenshot. If none exists, ask; do not invent a dashboard.
- Research visible structure, terminology, brand color, and the exact action/state relevant to the beat. Do not copy unsupported metrics, private information, or claims.
- Cache assets and notes under
.promptible/research/. Reuse a cache hit when product, sources, asset hashes, and reference mechanism are unchanged.
What ships with it
29 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.
- assets/logos/claude-mark.svg 748 B
- assets/logos/cursor.svg 469 B
- assets/logos/deepseek.svg 2.1 KB
- assets/logos/github.svg 837 B
- assets/logos/google-gemini.svg 416 B
- assets/logos/linear.svg 468 B
- assets/logos/notion.svg 993 B
- assets/logos/openai-codex-mark.png 22 KB
- assets/logos/playwright.svg 4.9 KB
- assets/logos/slack.png 11 KB
- assets/references/kickbacks-same-run-editor-contact-sheet.jpg 34 KB
- assets/references/kickbacks-same-run-editor.mp4 3217 KB
- assets/references/openmontage-claude-pipeline-contact-sheet.jpg 48 KB
- assets/references/openmontage-claude-pipeline.mp4 2732 KB
- assets/references/openmontage-hook-contact-sheet.jpg 38 KB
- assets/references/openmontage-hook.mp4 1422 KB
- assets/references/smartlead-prewarmed-burn-contact-sheet.jpg 26 KB
- assets/references/smartlead-prewarmed-burn.mp4 1592 KB
- assets/references/tsenta-apply-faster-contact-sheet.jpg 59 KB
- assets/references/tsenta-apply-faster.mp4 2926 KB
- assets/references/tsenta-one-click-wall-contact-sheet.jpg 90 KB
- assets/references/tsenta-one-click-wall.mp4 3113 KB
- references/approved-references.md 2.4 KB
- references/logo-library.md 1.7 KB
- references/rejected-patterns.md 1.6 KB
- references/research-and-assets.md 2.6 KB
- references/visual-critic.md 2.1 KB
- scripts/promptible-gate.mjs 15 KB runs code
- templates/critic-output.example.json 452 B
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 · 185 lines · 21 tokens per session scan A d5e8f91176a6
motion-graphics is a skill published in the GitHub repository Liamrjohnston/remotion-motion-graphics-skill (59 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,813 once invoked, about $0.0001 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.