A command that reviews a web interface for design violations and proposes fixes at two levels: project design rules and broader interface quality. It shows a preview before applying changes unless told to apply them immediately.

Use it on a file or interface component to audit and fix design problems. You can apply only project-rule fixes, only quality fixes, or both.

It helps replace inconsistent values such as hardcoded colors, spacing, or fonts and addresses issues such as contrast, line height, and touch-target size. Separating the two review levels makes the intended type of fix clearer.

normalize — Command by b1rdmania

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/normalize

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 3,000 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.03000
Opus 5	$0.00000	$0.01500
Sonnet 5	$0.00000	$0.00600
Haiku 4.5	$0.00000	$0.00300

Measured 2d ago against content hash 02774d0c2df9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

normalize 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.

.claude/skills/design/commands/normalize.md · 424 lines

How it starts

The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Normalize Command

Fix design violations at both layers (config compliance + technical quality) with preview before applying.

Two-Layer Normalization

Layer 1: Config Compliance - Replace hardcoded values with design system tokens
Layer 2: Technical Quality - Fix Impeccable principle violations

Usage

/design normalize <file_or_component>

Examples:

/design normalize src/components/Button.tsx
/design normalize src/pages/HomePage.tsx
/design normalize src/app/dashboard/page.tsx

Optional flags:

/design normalize src/components/Button.tsx --auto-apply  # Skip preview, apply immediately
/design normalize src/components/Button.tsx --layer=config  # Only fix config violations
/design normalize src/components/Button.tsx --layer=quality  # Only fix quality issues

Process Flow

Step 1: Audit

Run the design audit command internally to identify violations:

Layer 1: Config violations (hardcoded colors, spacing, fonts, etc.)
Layer 2: Technical quality issues (contrast, line-height, touch targets, etc.)

Step 2: Generate Fixes

For each violation, generate a fix:

Layer 1: Config Compliance Fixes (Auto-fixable)

Hardcoded Colors → Palette Tokens

// Before:
<div className="bg-[#3b82f6] text-white">

// After (using .design.json palette):
<div className="bg-primary-600 text-white">

Arbitrary Spacing → Scale Tokens

// Before:
<div className="p-[13px] mb-[27px]">

// After (using .design.json spacing scale):
<div className="p-3 mb-6">  // p-3=12px, mb-6=24px from scale

Custom Font Sizes → Modular Scale

// Before:
<h1 className="text-[26px]">

// After (using .design.json type scale):
<h1 className="text-2xl">  // 2xl=24px from scale

Custom Border Radius → System Values

// Before:
<div className="rounded-[13px]">

// After (using .design.json radius values):
<div className="rounded-lg">  // lg=12px from system

Read the full file on GitHub · 424 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.

2d ago First seen · 424 lines · 0 tokens per session scan A 02774d0c2df9

Subscribe to this mod's changes

normalize 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 3,000 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.

Frontend ai ai-agent claude nanoclaw openclaw personal-assistant

triage-pr

Triage a PR — classify, optionally fix, optionally enable auto-merge.

lobu-ai/lobu · 16 tokens

tech-debt

Run bun run check:fix and then bunx knip and identify unused files and functions to refactor the project and simplify. Look at the deprecated features and confirm with the user to delete them. Look at the dependencies and remove the ones that are not needed based on knip results.

lobu-ai/lobu · 0 tokens

normalize