A design-review command that checks a file against the project's design rules and broader interface-quality principles.

Use it to review a component or page, or to audit recent changes, including its typography, colours, spacing, and other design-related code.

It finds inconsistent design values and technical usability problems by checking both whether the project follows its own rules and whether those rules produce a sound interface.

How b1rdmania/ghostclaw configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to b1rdmania/ghostclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/b1rdmania/ghostclaw/main/.claude/skills/design/commands/audit.md

Clone the repo

git clone --depth 1 https://github.com/b1rdmania/ghostclaw

Made for: Claude Code.

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/commands/b1rdmania/ghostclaw/audit/github.svg)](https://agentmods.dev/commands/b1rdmania/ghostclaw/audit)

Your own site

<a href="https://agentmods.dev/commands/b1rdmania/ghostclaw/audit"><img src="https://agentmods.dev/badge/commands/b1rdmania/ghostclaw/audit/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/commands/b1rdmania/ghostclaw/audit"><img src="https://agentmods.dev/badge/commands/b1rdmania/ghostclaw/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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 5,692 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	$0.00000	$0.05692
Opus 5.5	$0.00000	$0.02277
Sonnet 5.5	$0.00000	$0.01138
Haiku 4.5	$0.00000	$0.00569

Measured 1mo ago against content hash ec8825b2d625, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit 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.

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/audit.md · 723 lines

How it starts

The opening of the file, as written. The whole thing — 723 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Audit Command

Trigger: /design audit [file]

Purpose: Two-layer audit - first checks config violations against .design.json, then evaluates technical design quality against Impeccable principles.

Two-Layer Audit Approach

Layer 1: Config Compliance Check against project's .design.json rules - are you following your own design system?

Layer 2: Technical Quality Check against Impeccable design principles (reference docs) - is your design system itself good?

Key Insight: You can be compliant with your config but still have poor design quality. Both layers matter.

Usage

/design audit src/components/Button.tsx    # Audit single file
/design audit src/pages/HomePage.tsx       # Audit page component
/design audit                              # Audit recent changes (interactive)

Detailed Process

Layer 1: Config Compliance Check

Load Project Config

# Read .design.json from project root
# If missing, offer to run `/design init` first

Parse Target File
- Extract all design-related code (CSS, Tailwind classes, inline styles, design tokens)
- Build list of all design values used
Check Each Category

Typography Compliance
- Font families: Must be from typography.fontFamily
- Font sizes: Must be from typography.fontSize
- Font weights: Must be from typography.fontWeight
- Flag: Any arbitrary values like text-[17px] or custom font names
Color Compliance
- All colors: Must be from colors array
- Check: hex values, rgb/rgba, Tailwind classes
- Flag: Any hardcoded colors like #3B82F6 or rgb(255,0,0)
Spacing Compliance
- Margins, padding, gaps: Must be from spacing scale
- Flag: Arbitrary values like mt-[13px] or padding: 15px
Border Radius Compliance
- All radius values: Must be from borderRadius
- Flag: Custom values like rounded-[12px]
Shadow Compliance
- All box-shadow usage: Must be from shadows
- Flag: Inline shadow definitions

Read the full file on GitHub · 723 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.

1mo ago First seen · 723 lines · 0 tokens per session scan A ec8825b2d625

Subscribe to this mod's changes

audit is a command published in the GitHub repository b1rdmania/ghostclaw (84 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,692 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.

Design and UX ai ai-agent claude nanoclaw openclaw personal-assistant

ghostclaw: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Design Audit Command

Two-Layer Audit Approach

Usage

Detailed Process

Layer 1: Config Compliance Check

Typography Compliance

Color Compliance

Spacing Compliance

Border Radius Compliance

Shadow Compliance

What this file has done since we first saw it

Other commands, from other repositories

find

checklist

clarify

specify

converge

implement