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 anton-abyzov/vskill --skill motion-graphics-promogit clone --depth 1 https://github.com/anton-abyzov/vskillWrote 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/anton-abyzov/vskill/motion-graphics-promo)<a href="https://agentmods.dev/skills/anton-abyzov/vskill/motion-graphics-promo"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/motion-graphics-promo/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/anton-abyzov/vskill/motion-graphics-promo"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/motion-graphics-promo.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 | $0.00226 | $0.02464 |
| Opus 5.5 | $0.00090 | $0.00986 |
| Sonnet 5.5 | $0.00045 | $0.00493 |
| Haiku 4.5 | $0.00023 | $0.00246 |
Grade A, and why
motion-graphics-promo 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
motion-graphics-promo
After Effects-quality motion, authored as HTML/GSAP compositions and rendered deterministically with HyperFrames. You get editable source, exact native-screen fidelity and a reproducible render, which a hand-keyed After Effects project does not give an agent.
Source study: Higgsfield AI, "AI Created Every Motion Graphic in This Video" (YouTube W3-RIZ-Ps64, 11:33, Sep 2026), inspected at 720p with contact sheets, plus the pacing of a 4-minute official SaaS product overview. Use them for grammar and pacing only. Never reuse their pixels, music, voice, logos or UI.
1. Brief before motion (lock the story first)
The tutorial spends its first minutes turning a brief into asset choices and a storyboard before anything moves. Do the same, in five lines:
- Audience and moment: who is watching, on which platform, sound on or off.
- One product, two jobs, one next step: the viewer should remember exactly that.
- Proof inventory: real screenshots and screen recordings you actually have, with source build/date. Anything not in this list cannot appear on screen.
- Palette and type: the brand's own identity. Borrow the reference's contrast level (bold condensed type over saturated fields), not its exact colors.
- Aspect: design vertical (1080x1920) as its own composition; don't crop landscape.
2. Motion grammar
| Beat | Rule | Why |
|---|---|---|
| Entry (0-3 s) | Energetic: a label falls, rotates, bounces and settles once; or a device drops in with weight. | Hooks the scroll-stop without hiding the product. |
| Transition | One main transition per task. A phone slides or tilts between color fields, or navigation hands off to the next real screen. | Motion should explain grouping or movement between actual product states. |
| Settle | Short spring (GSAP back.out(1.4) or elastic.out(1, 0.6), 0.4-0.7 s). The device settles before the screen needs reading. |
Physical weight reads as premium; wobble during reading reads as noise. |
| Proof hold | At least 2-3 s of stable, readable screen after each transition. | Screens need more reading time than decorative labels. |
| Accents | Masked/clip-reveal typography, rectangular color accents, collage or color-field handoffs. Use sparingly. | This is the "After Effects look"; overuse turns into a template. |
What ships with it
1 file 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.
- 6d ago Changed · -54 tokens per session 23deba3f6858
- 27d ago First seen · 95 lines · 280 tokens per session scan A 87d28cd22e3a
motion-graphics-promo is a skill published in the GitHub repository anton-abyzov/vskill (48 stars, last pushed yesterday), licensed MIT. It adds 226 tokens to every session and 2,464 once invoked, about $0.0009 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 2026-09-26.
Other skills, from other repositories
start-coding-task
Start a CodeAgent coding task from the user's request on one of their existing sessions, and report the session id so they can follow it.
review-agent-work
Review the changes a CodeAgent session made, and open or review a pull request when the user asks.
continue-with-codeagent-credits
Switch a session to a CodeAgent managed agent billed from the user's prepaid credits, with the user's explicit confirmation.
supervise-session
Monitor, redirect, answer or stop an existing CodeAgent session.
prereview
Review the current diff against this team's conventions and invariants before it ships. Invoke with /prereview before opening a PR, or run as a pre-push gate.
agent-config-setup
Generate AI agent config files for any project — Cursor, Claude Code, Copilot, Windsurf, Cline, AGENTS.md. Use when setting up a new project for AI agents.