design

A command for a focused design session that improves the visual quality of scenes in a video project. It finds the project, lists its scenes, and targets one scene for refinement.

In plain words
What is it for?
It is for refining slide-like scenes, including their typography, colours, spacing, motion, atmosphere, and visual consistency.
Why use it?
It gives visual improvements a defined scope and checks the project's existing configuration and brand settings first.

Command for Claude Code

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.

agentmods
npx agentmods add commands/digitalsamba/claude-code-video-toolkit/design
Clone the repo
git clone --depth 1 https://github.com/digitalsamba/claude-code-video-toolkit

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,720 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01720
Opus 5 $0.00000 $0.00860
Sonnet 5 $0.00000 $0.00344
Haiku 4.5 $0.00000 $0.00172

Measured 3d ago against content hash ea1e6e6ecdbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

.claude/commands/design.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Refinement

Focused design session for improving video scene visuals using the frontend-design skill.

Purpose

Deep-dive visual refinement for slides and components:

  • Elevate generic aesthetics to distinctive, memorable visuals
  • Ensure visual narrative coherence across scenes
  • Iterate on typography, color, motion, and atmosphere

Usage

/design              # Discover project, list scenes, choose one
/design [scene-id]   # Jump directly to a specific scene

Step 1: Discover Project Context

First, find and understand the current project:

  1. Locate the project

    • Check if in a project directory (has project.json or template config)
    • If not, scan projects/ for active projects
    • If multiple, ask user which project
  2. Read project configuration

    • project.json if exists (scenes, phase, brand)
    • Or template config: src/config/sprint-config.ts or src/config/demo-config.ts
    • Brand/theme: src/config/theme.ts
  3. Build scene inventory

    • List all scenes from config
    • Identify which are slide-type (designable) vs demo-type (video playback)
    • Note each scene's purpose from config content

Step 2: Identify Target Scene

If no scene specified in command, show discovered scenes:

## Design Refinement

**Project:** {project_name}
**Template:** {template_type}

Which scene would you like to refine?

| # | Scene ID | Type | Description |
|---|----------|------|-------------|
{list slide-type scenes discovered from config}

(Demo/video scenes are not shown - they display recorded content)

Enter scene ID or number:

Step 3: Understand Scene Context

Before invoking frontend-design, gather specific context:

  1. Read the target slide component

    • Find component file from scene type mapping
    • e.g., src/components/slides/{Type}Slide.tsx
  2. Read scene content from config

    • What text/data does this scene display?
    • What's the intended message?
  3. Understand position in sequence

    • What scene comes before? What mood does it leave?
    • What scene comes after? What mood should we set up?

Read the full file on GitHub · 285 lines

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. 3d ago First seen · 285 lines · 0 tokens per session scan A ea1e6e6ecdbd

Subscribe to this mod's changes

design is a command published in the GitHub repository digitalsamba/claude-code-video-toolkit (2,035 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,720 tokens. 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.