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 agentmods add skills/instavar/remotion-templates/make-videonpx skills add instavar/remotion-templates --skill make-videogit clone --depth 1 https://github.com/instavar/remotion-templatesWrote 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/instavar/remotion-templates/make-video)<a href="https://agentmods.dev/skills/instavar/remotion-templates/make-video"><img src="https://agentmods.dev/badge/skills/instavar/remotion-templates/make-video.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00529 |
| Opus 5 | $0.00013 | $0.00264 |
| Sonnet 5 | $0.00005 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
make-video 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 5d 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.
What it actually says
Make a video
- If the
instavar-remotionMCP server is connected, callget_capabilities,list_templates, andget_template. Otherwise use the template list in the README. - Ask for any missing brief details that materially affect the result: audience, goal, platform, aspect ratio, duration, source media, call to action, and audio intent. Audio intent must be narration, music, or explicitly silent.
- Create or scaffold a
*.video.jsonVideoSpec. Use only published template and scene identifiers. Write the creative copy from the user's brief. Do not treat placeholder copy as finished content. Never showscene.kindas audience copy. Avoid all-caps headings and decorative labels above headings. - If narration is approved, preserve the exact script in
audio.narrationText. For private Supertonic narration, write one paragraph per scene athttps://instavar.com/voice, download the WAV and timing manifest, then runnpm run video:timing -- <spec> --audio <wav> --manifest <timing.json>. The beat count must equal the scene count. Otherwise add an existing localaudio.narrationSrc, or runnpm run video:narrate -- <spec>for no-key system TTS. Never leave approved narration only in the conversation. - Run
npm run video:validate -- <spec>and fix every blocking error. Treat hierarchy, scene differentiation, text density, and audio diagnostics as product requirements. - Run
npm run video:preview -- <spec>. It renders a midpoint frame for every scene. Inspect every output inout/previews/<id>/, not only the opening, middle, and ending. Correct clipping, weak hierarchy, unreadable copy, repeated layouts, poor visual balance, or timing problems. Use--studioonly when an interactive review is useful. - Run
npm run video:render -- <spec>only after validation and every-scene preview are satisfactory. The render command performs post-render audio QA and fails if expected audio is absent or effectively silent. - Report the exact spec, preview directory, MP4 path, audio mode, and unresolved warnings. Do not claim a render succeeded unless the output exists and the expected-audio QA passes.
Keep all creative assets local unless the user explicitly approves an upload. Ask before using paid services or publishing to an external platform.
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.
- 5d ago First seen · 18 lines · 25 tokens per session scan A d53f890bfacb
make-video is a skill published in the GitHub repository instavar/remotion-templates (1 stars, last pushed 11d ago), licensed MIT. It adds 25 tokens to every session and 529 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 2026-08-31.
Other skills, from other repositories
video-hyperframes
Hyperframes / Remotion-compatible continuous frame animation with autoplay support.
video-hyperframes
Hyperframes / Remotion 兼容的连续帧动画, 可自动播放.
remocn
Build Remotion videos with remocn — copy-paste animation components and timeline-driven UI primitives from a shadcn registry. Use when composing a video or scene in a Remotion project, adding a single animation, transition, background, or UI-block sim, or reaching for a video-ready UI primitive (button, dialog…
multi-surface-render
Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes. Covers renderer target selection, registry mapping, and platform APIs (renderToBuffer, renderToStream, renderToFile). Use when generating output…
demo-producer
Universal demo video creator for skills, agents, plugins, tutorials, CLI commands, and code walkthroughs. Generates scripts, storyboards, VHS terminal recordings, and Remotion video compositions with task-tracked production phases. Use when producing video showcases, marketing content, or terminal recordings.
frame-data-rollup
A native Remotion data frame — bars grow from zero by real data via spring physics while the figures roll 0→target in sync. The numbers come alive in a way a static HTML chart can't.