What is motion-design?

A code-based video production workflow for motion graphics, explainers, product demos, music videos, and social clips. It coordinates writing, visual design, music, scenes, and critique through a shared orchestration file.

Use it to develop video concepts, scripts, visual styles, sound, scenes, and final motion pieces for products, data, music, or social media.

It organizes the many creative and technical parts of making a video so contributors can work in parallel and keep decisions together. It focuses on producing a finished video rather than only a rendered file.

motion-design — Skill for Claude Code and Codex by JairoTorregrosa

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 JairoTorregrosa/jaiskills --skill motion-design

Clone the repo

git clone --depth 1 https://github.com/JairoTorregrosa/jaiskills

Made for: Claude Code, Codex.

Or install jaiskills, the plugin that ships this one along with the rest of its 12 skills, 4 agents, 2 hooks.

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/jairotorregrosa/jaiskills/motion-design/github.svg)](https://agentmods.dev/skills/jairotorregrosa/jaiskills/motion-design)

Your own site

<a href="https://agentmods.dev/skills/jairotorregrosa/jaiskills/motion-design"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/motion-design/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/jairotorregrosa/jaiskills/motion-design"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/motion-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 234 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,214 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	$0.00234	$0.04214
Opus 5.5	$0.00094	$0.01686
Sonnet 5.5	$0.00047	$0.00843
Haiku 4.5	$0.00023	$0.00421

Measured 1mo ago against content hash d5ef2b757f60, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

motion-design 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.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/audio_check.py, scripts/beats.py, scripts/blender_mg_render.py, …), 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/creative/motion-design/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Motion Design

Approach every video as the creative director of a small motion studio whose work gets forwarded. The client has already seen the template version of this video — fade-up titles, stock whooshes, a logo at the end — and is paying for a point of view: one idea, one image people remember, sound that was designed, and craft they can feel in the timing.

The Definition of Done is the pride test: the human would post this under their own name today, without apologizing for anything, and it is better than the last video they shipped. "It renders" is the floor, not the goal.

Non-negotiables

Open the orchestration file first. Copy templates/ORCHESTRATION.md to the project root and fill §1 Brief and §2 Definition of Done before writing any code. It is the single source of truth for every agent, the ledger of decisions, sources and findings, and what you re-read after a context compaction. Update it at every phase gate.
Run it as a crew, in parallel. Divergent work (drafts, style frames, music takes, scenes, critique lenses) goes to parallel subagents launched in one message, each pointed at ORCHESTRATION.md and given one output path. Prompts: templates/crew-prompts.md. Playbook: references/orchestration.md.
Look at every render, and measure it. A render nobody looked at is not progress. Every iteration: a contact sheet for pacing, motion strips for easing and sync, stills for type (scripts/contact_sheet.py), and the mechanical gates for format, loudness, frame 0, frozen runs and cuts on the beat (scripts/video_gates.py). Taste is judged by independent critics, not by the builder (references/qa-critique.md).
Frame 0 is the poster; the hook lands in 1.5 s. Feeds and chats preview the first frame: design it as the thumbnail, never black, white or half-built (scripts/poster_frame.py fixes a fade-in). The premise reads in the first 1.5 s with the sound off, and the best material is in the first 5 s, because that is where the viewer and the person who commissioned it decide.
Truth on screen. Every number, name and claim traces to data or a source recorded in the ledger; a fact-check pass runs before final. Parody of a brand is fine; its real logo is not.
Native voice. Copy, lyrics and VO are written in the audience's language and register from scratch — never translated, never hype.
Decide, don't block. Make the reasonable call, log it in §7, keep going. Ask the human only at a genuine taste fork (which song take, which concept), with a recommended default, and keep building the default while waiting. Never leave a long run parked on a question.
Ship the whole package. Masters per aspect, feed exports, a WhatsApp review copy under 180 MB (scripts/export_social.py), .srt, covers, title, post copy in the human's voice, a "how it was made" note, provenance of every generated asset, and known issues stated plainly (references/delivery.md).

Read the full file on GitHub · 231 lines

Files

What ships with it

31 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.

1mo ago First seen · 231 lines · 234 tokens per session scan A d5ef2b757f60

Subscribe to this mod's changes

motion-design is a skill published in the GitHub repository JairoTorregrosa/jaiskills (10 stars, last pushed 3d ago), licensed MIT. It adds 234 tokens to every session and 4,214 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 2026-09-27.

Claude Code Creative and media Multi-Agent agents plugin skills

eliza

Skill "eliza" from aomi-labs/skills, covering elizaos, what you probably got wrong, installation, cli (recommended for new projects) and from source (contributor workflow).

aomi-labs/skills · 51 tokens

swarmclaw

AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.

swarmclawai/swarmclaw · 67 tokens

update-harness

Update an existing Claude Code harness — check for outdated components, duplication with official features, missing patterns, and improvement opportunities, then apply approved changes. Use whenever: 'update harness', 'update my harness', 'is my harness up to date', 'harness outdated', 'optimize harness', 'check my…

bzantium/meta-harness · 112 tokens

create-harness

Generate a complete, project-specific Claude Code harness — agents, skills, hooks, CLAUDE.md rules — tailored to any codebase. Use whenever someone says 'create a harness', 'set up agents for this project', 'configure Claude Code', 'build an agent team', 'make this project AI-ready', 'harness this project', or any…

bzantium/meta-harness · 117 tokens

help

Get oriented with the solopreneur plugin — see your AI team, check project status, and get suggestions for what to do next. Use when you're getting started or need a refresher.

pcatattacks/solopreneur-plugin · 41 tokens

review

Review code, specifications, or designs for quality, bugs, security, and best practices. Use when the user wants feedback on recent work, a pull request, or any artifact.

pcatattacks/solopreneur-plugin · 38 tokens