init

A setup command that creates two project files for design rules and design guidance. The files can hold things such as fonts, colors, spacing, brand style, and writing tone.

In plain words
What is it for?
Use it to start a design configuration from a minimal template, an example style, or a guided custom setup. It can initialize the current project or another directory.
Why use it?
It gives the project a shared design reference instead of leaving these decisions scattered or undocumented. It also checks for existing files before asking whether to overwrite or merge them.

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/b1rdmania/ghostclaw/init
Clone the repo
git clone --depth 1 https://github.com/b1rdmania/ghostclaw

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 1,987 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 $0.01987
Opus 5 $0.00000 $0.00993
Sonnet 5 $0.00000 $0.00397
Haiku 4.5 $0.00000 $0.00199

Measured yesterday against content hash 564a76da21eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 yesterday.

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/skills/design/commands/init.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/design-init - Initialize Design Configuration

Create project-level design configuration files (.design.json and .design.md) that combine design system rules with Impeccable best practices.

Purpose

The /design-init command sets up a two-layer design configuration for your project:

Layer 1: Design System Rules (.design.json)

  • Fonts, colors, spacing, typography
  • Project-specific design constraints
  • Used for fast anti-pattern detection and normalization

Layer 2: Design Philosophy (.design.md)

  • Project context and brand personality
  • Design principles and guidelines
  • UX writing voice and tone
  • Used for deep design reviews and polish

Usage

/design-init [directory]

Arguments:

  • directory (optional): Project directory to initialize. Defaults to current directory.

Behavior

Interactive Setup

  1. Check for existing config

    • If .design.json or .design.md exists, ask to overwrite or merge
  2. Choose starting point

    Initialize from:
    1. Minimal starter (recommended for new projects)
    2. Emergence example (brutalist aesthetic)
    3. Velocity example (clean, modern)
    4. Custom (guided setup)
    
  3. Create .design.json

    • Based on chosen template
    • User can customize fonts, colors, spacing
  4. Create .design.md

    • Project context template
    • User fills in: project name, target audience, brand personality, design principles
  5. Confirm

    ✓ Created .design.json
    ✓ Created .design.md
    
    Next steps:
    - Edit .design.md to add project context
    - Run /design-rules to view current config
    - Run /design-audit [file] to check compliance
    

Templates

Minimal Starter (.design.json)

{
  "name": "Project Name",
  "version": "1.0.0",
  "fonts": {
    "heading": "Inter",
    "body": "Inter",
    "mono": "JetBrains Mono"
  },
  "colors": {
    "primary": "#000000",
    "secondary": "#666666",
    "background": "#FFFFFF",
    "text": "#000000"
  },
  "spacing": {
    "xs": "4px",
    "sm": "8px",
    "md": "16px",
    "lg": "24px",
    "xl": "32px",
    "2xl": "48px"
  },
  "typography": {
    "h1": { "size": "48px", "lineHeight": "1.2", "weight": "700" },
    "h2": { "size": "36px", "lineHeight": "1.3", "weight": "700" },
    "h3": { "size": "24px", "lineHeight": "1.4", "weight": "600" },
    "body": { "size": "16px", "lineHeight": "1.6", "weight": "400" },
    "small": { "size": "14px", "lineHeight": "1.5", "weight": "400" }
  },
  "rules": [
    "Use design system fonts only",
    "Use design system colors only",
    "Use design system spacing scale only",
    "Maintain WCAG AA contrast ratios (4.5:1 for text)"
  ]
}

Read the full file on GitHub · 306 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. yesterday First seen · 306 lines · 0 tokens per session scan A 564a76da21eb

Subscribe to this mod's changes

init is a command published in the GitHub repository b1rdmania/ghostclaw (91 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,987 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.