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 XyrusCode/ai-sync --skill video-generationgit clone --depth 1 https://github.com/XyrusCode/ai-syncWrote 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/xyruscode/ai-sync/video-generation)<a href="https://agentmods.dev/skills/xyruscode/ai-sync/video-generation"><img src="https://agentmods.dev/badge/skills/xyruscode/ai-sync/video-generation/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/xyruscode/ai-sync/video-generation"><img src="https://agentmods.dev/badge/skills/xyruscode/ai-sync/video-generation.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 | $0.00156 | $0.01455 |
| Opus 5.5 | $0.00062 | $0.00582 |
| Sonnet 5.5 | $0.00031 | $0.00291 |
| Haiku 4.5 | $0.00016 | $0.00145 |
Grade A, and why
video-generation 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 1mo 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Generation (Remotion)
Make videos by writing them as code. Every visual — text, shapes, gradients, motion — is a React component drawn frame-by-frame and rendered to MP4 by Remotion. No editor, no stock footage, no AI-generated frames. This is deterministic, versionable, and re-renderable: change a color or a word, run one command, get a new video.
Why this framing matters
A generic "make a video" request sends most agents toward tools they can't run (video editors) or can't produce reliably (text-to-video models). That is the #1 failure mode. Everything here is CSS/SVG/React animated with math. Hold that line unless the user explicitly wants real footage or AI video.
The machine is already set up: Node 22, and Remotion's headless Chrome shell is
downloaded from prior renders. npm install in a new project is all that's
needed.
Pick the mode
Read the one reference file for the mode that fits, then follow the core workflow below. Modes combine freely (e.g. a promo, then a social cut of it).
| The user wants… | Mode | Read |
|---|---|---|
| A brand/product promo, advert, logo intro, kinetic-typography spot | Motion graphics | references/motion-graphics.md |
| To showcase one of their local apps (yt-grab, ani-jelly-pipeline, …) | Code-project demo | references/project-demos.md |
| To explain a concept/topic, animate data or charts, teach something | Explainer / data | references/explainer-data.md |
| A vertical 9:16 cut, captions, or a short-form edit of any of the above | Social cut | references/social-cuts.md |
| Music or sound effects on any of the above | Audio (add-on) | references/audio.md |
If unsure which mode, ask the user one short question about the goal and audience — but if they've given enough (a subject + a vibe), just pick and go.
Core workflow
Full command details and the project anatomy are in
references/remotion-setup.md — read it before the first render. In short:
What ships with it
18 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/template/package.json 566 B
- assets/template/remotion.config.ts 185 B runs code
- assets/template/src/config.ts 739 B runs code
- assets/template/src/index.ts 89 B runs code
- assets/template/src/Root.tsx 925 B
- assets/template/src/scenes/ContentScene.tsx 3.0 KB
- assets/template/src/scenes/OutroScene.tsx 3.6 KB
- assets/template/src/scenes/TitleScene.tsx 3.9 KB
- assets/template/src/theme.ts 942 B runs code
- assets/template/src/Video.tsx 1.5 KB
- assets/template/tsconfig.json 255 B
- PROMPT.md 2.7 KB
- references/audio.md 2.4 KB
- references/explainer-data.md 2.4 KB
- references/motion-graphics.md 2.8 KB
- references/project-demos.md 2.9 KB
- references/remotion-setup.md 3.8 KB
- references/social-cuts.md 2.1 KB
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.
- 1mo ago First seen · 109 lines · 156 tokens per session scan A 1962c98deac4
video-generation is a skill published in the GitHub repository XyrusCode/ai-sync (2 stars, last pushed 18d ago), licensed MIT. It adds 156 tokens to every session and 1,455 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 2026-09-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…