What is remotion-video-workflow?

A workflow for making reusable short videos in Remotion, a React-based video framework, from a brief, article, notes, or other source material.

Use it to build knowledge-focused short videos with hooks, content, and end cards; adapt them to different ratios; render them; and verify the video and cover outputs.

It provides a repeatable structure for storyboards, covers, branding, audio, rendering, and output checks instead of treating each video as an isolated experiment.

remotion-video-workflow — Skill for Codex by shaom

Install

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.

Any agent

npx skills add shaom/infocard-video-skills --skill remotion-video-workflow

Clone the repo

git clone --depth 1 https://github.com/shaom/infocard-video-skills

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/shaom/infocard-video-skills/remotion-video-workflow/github.svg)](https://agentmods.dev/skills/shaom/infocard-video-skills/remotion-video-workflow)

Your own site

<a href="https://agentmods.dev/skills/shaom/infocard-video-skills/remotion-video-workflow"><img src="https://agentmods.dev/badge/skills/shaom/infocard-video-skills/remotion-video-workflow/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/shaom/infocard-video-skills/remotion-video-workflow"><img src="https://agentmods.dev/badge/skills/shaom/infocard-video-skills/remotion-video-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,510 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00050	$0.01510
Opus 5.5	$0.00020	$0.00604
Sonnet 5.5	$0.00010	$0.00302
Haiku 4.5	$0.00005	$0.00151

Measured 2mo ago against content hash 0c6c45fe1811, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

remotion-video-workflow 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/probe_output.sh, scripts/render_cover.sh, scripts/render_video.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/remotion-video-workflow/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remotion Video Workflow

Overview

Use this skill to turn a brief, article, notes, or other source material into a structured Remotion short video workflow. This skill is designed for reusable production, not for one-off visual experiments.

The default target is a knowledge-oriented short video with clear pacing, stable structure, and linked video and cover outputs. The validated baseline for v1 is a 30fps Remotion project with:

a pure data storyboard module
a separate cover content module
one or more video compositions in Root.tsx
one still composition for the cover
tests that enforce structure and content preservation
render and ffprobe validation

This skill assumes the agent also follows the upstream remotion-best-practices skill for Remotion-specific implementation details. Use that upstream skill for:

composition and still registration
frame-driven animation rules
TransitionSeries usage
audio component behavior
sequencing rules
font loading behavior

When To Use

Use this skill when the user wants:

a knowledge-dense short video
a Hook / Content / End Card structure
a Remotion-based workflow instead of a generic script-only answer
a cover and video that should feel related
ratio-aware output such as 3:4 or 4:3
render and output validation as part of the task

Do not use this skill as the default choice for:

a single throwaway animation experiment
long-form narrative videos
narration-first talking-head edits
pure video editing tasks that do not need Remotion composition

Input Expectations

Collect or infer these inputs:

source material or topic
target ratio
target runtime
brand inputs if any
cover requirement
output requirement such as plan only, implementation, render, or verification

When inputs are missing, infer conservatively:

default ratio: 3:4
default fps: 30
default runtime target: 25 to 45 seconds
default structure: Hook -> Content -> End Card
default visual mode: one reusable theme with one warm accent and one cool accent
default output mode: planning first, implementation second

Read the full file on GitHub · 210 lines

Files

What ships with it

14 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.

Changes

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 · 210 lines · 50 tokens per session scan A 0c6c45fe1811

Subscribe to this mod's changes

remotion-video-workflow is a skill published in the GitHub repository shaom/infocard-video-skills (4 stars, last pushed 7mo ago), licensed MIT. It adds 50 tokens to every session and 1,510 once invoked, about $0.0002 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 2026-08-31.

Creative and media agent-skills remotion video-generation

remotion-video-workflow next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
remotion-video-workflowshaom/infocard-video-skills	Skill	4	7mo ago	MIT	A	50	Codex
frontend-verifyucsandman/marketing-studio	Skill	255	2mo ago	MIT	A	163	Claude Code
de-vibeucsandman/marketing-studio	Skill	255	2mo ago	MIT	A	128	Claude Code
launchucsandman/marketing-studio	Skill	255	2mo ago	MIT	A	62	Claude Code
marketingucsandman/marketing-studio	Skill	255	2mo ago	MIT	A	71	Claude Code
shipucsandman/marketing-studio	Skill	255	2mo ago	MIT	A	52	Claude Code
audio-trackucsandman/marketing-studio	Skill	255	2mo ago	MIT	A	79	Claude Code