design-brain

design-brain is a skill for Claude Code from Zane-0x5a/remotion-director. It costs 143 tokens per session (883 once invoked), scanned A, original, MIT.

A design guide for creating motion pieces with a clear visual idea, story, texture, and rendering plan. It is written for a Remotion-based motion-design workflow.

In plain words
What is it for?
Use it to shape the narrative, define the central visual mechanism, plan textures and animation beats, build the piece, and review the rendered result.
Why use it?
It provides a structured way to develop the concept before building and to check that the final render matches the intended design.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the remotion-director plugin — 3 skills, 4 agents shipped together

Good fit Use it to shape the narrative, define the central visual mechanism, plan textures and animation beats, build the piece, and review the rendered result.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Zane-0x5a/remotion-director
Claude Code
/plugin install remotion-director

Made for: Claude Code.

Or install remotion-director, the plugin that ships this one along with the rest of its 3 skills, 4 agents.

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.

agentmods badge for design-brain

README.md
[![agentmods](https://agentmods.dev/badge/skills/zane-0x5a/remotion-director/design-brain/github.svg)](https://agentmods.dev/skills/zane-0x5a/remotion-director/design-brain)
Your own site
<a href="https://agentmods.dev/skills/zane-0x5a/remotion-director/design-brain"><img src="https://agentmods.dev/badge/skills/zane-0x5a/remotion-director/design-brain/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.

agentmods 80×15 button for design-brain

Your own site · 80×15
<a href="https://agentmods.dev/skills/zane-0x5a/remotion-director/design-brain"><img src="https://agentmods.dev/badge/skills/zane-0x5a/remotion-director/design-brain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 883 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00143 $0.00883
Opus 5 $0.00072 $0.00441
Sonnet 5 $0.00029 $0.00177
Haiku 4.5 $0.00014 $0.00088

Measured 2d ago against content hash 2942eef68cde, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-brain 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 2d 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.

skills/design-brain/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

design-brain

This skill is the standing equipment for 乙 — the unified design-and-build agent. It is design knowledge itself, not an interface specification. Do not skim it for an API; read it and let it make your design better.

Load this, in full, before any design judgment

Read ${CLAUDE_PLUGIN_ROOT}/skills/design-brain/reference/design-equipment.md completely and obey it. It carries, verbatim and load-bearing:

  • the opening framing (you are a top-tier motion designer; this is your best work this year; the full bandwidth is in your hands),
  • §0 心法 (understand before design; strategy before specifics),
  • §1 视觉 conceit — the命门: one falsifiable visual/structural mechanism that makes the piece itself; its protagonist is a concrete thing/event, never a light effect or material,
  • §2 工序与深度装备 — the 3-step process whose ORDER IS A HARD RULE (earlier step's output is frozen for later steps): 第一步 narrative → §A (texture.md FORBIDDEN here; §A lands on disk independently first) · 第二步 texture → §B · 第三步 engine plan annotated INLINE next to each beat,
  • §3 施工纪律 (make the render faithful to your design),
  • §4 渲染自检 — after R1, before handing to 甲: you-the-designer (with your standards) judge the real pixels, dare to change the DESIGN itself, refuse to sign off "acceptable residue", re-check everything after each fix,
  • §5 甲乙环纪律 — once in the critic loop: phenomena belong to 甲, mechanism/fix belong to you; pixel-verify before declaring FIXED; §A is protected but not welded shut.

The seven design-axis references

They live as siblings in ${CLAUDE_PLUGIN_ROOT}/skills/design-brain/reference/, loaded on demand per §2's timing (you decide which axis to read as the design advances; do NOT bulk-read them as a checklist up front):

narrative.md · aesthetic.md · color.md · composition.md · tempo.md · persuasion.md · texture.md

texture.md is forbidden during 第一步 — the conceit and narrative protagonist must be set without knowing the texture techniques (so the protagonist is a concrete thing/event, not a light effect). Read it only after §A is on disk; §B is appended.

Read the full file on GitHub · 37 lines

Files

What ships with it

8 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.

  1. 2d ago Changed 2942eef68cde
  2. 12d ago First seen · 37 lines · 143 tokens per session scan A 804c2906efe7

Subscribe to this mod's changes

design-brain is a skill published in the GitHub repository Zane-0x5a/remotion-director (29 stars, last pushed today), licensed MIT. It adds 143 tokens to every session and 883 once invoked, about $0.0007 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 2026-08-30.