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.
npx agentmods add commands/nyldn/claude-dolphin/refactor-uigit clone --depth 1 https://github.com/nyldn/claude-dolphinWhat 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 | $0.00009 | $0.01801 |
| Opus 5 | $0.00005 | $0.00901 |
| Sonnet 5 | $0.00002 | $0.00360 |
| Haiku 4.5 | $0.00001 | $0.00180 |
Grade A, and why
refactor-ui 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.
How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor UI Command
Apply tactical UI improvements to the specified component using Refactoring UI principles.
Required: Specify a component file path.
Refactoring Process
Step 1: Current State Analysis
Read the target component and document:
Visual Structure:
- Current spacing values
- Typography (sizes, weights, colors)
- Color usage
- Border and shadow usage
- Layout approach
Hierarchy:
- What's the primary element?
- What's secondary?
- What's tertiary?
- Is hierarchy clear?
Step 2: Apply Tactical Improvements
Spacing Improvements
Before checking: What spacing values are currently used?
Principles:
- Use consistent scale: 4, 8, 12, 16, 24, 32, 48, 64px
- Start with MORE whitespace than feels necessary
- Group related items closer together
- Separate unrelated items further apart
Common fixes:
// Before: Random spacing
<div className="p-5 mb-3 gap-7">
// After: Scale-based spacing
<div className="p-6 mb-4 gap-8">
Padding guidance:
- Tight (dense UI): 8-12px
- Standard: 16-24px
- Spacious: 24-32px
- Hero/cards: 32-48px
Typography Improvements
Principles:
- Maximum 2-3 font sizes per component
- Create hierarchy through WEIGHT first, then size
- Don't use pure black for text (use #111 or similar)
- Body text minimum 16px for readability
Font size scale:
text-xs: 12px - Labels, captions
text-sm: 14px - Secondary text
text-base: 16px - Body text
text-lg: 18px - Large body
text-xl: 20px - Subheadings
text-2xl: 24px - Section headings
text-3xl: 30px - Page headings
Weight hierarchy:
// Before: Size-only hierarchy
<h2 className="text-2xl">Title</h2>
<p className="text-base">Body</p>
<span className="text-sm">Meta</span>
// After: Weight + size hierarchy
<h2 className="text-xl font-semibold text-gray-900">Title</h2>
<p className="text-base font-normal text-gray-600">Body</p>
<span className="text-sm font-normal text-gray-500">Meta</span>
Color Improvements
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.
- yesterday First seen · 275 lines · 9 tokens per session scan A c773b0b29441
refactor-ui is a command published in the GitHub repository nyldn/claude-dolphin (9 stars, last pushed 8d ago), licensed MIT. It adds 9 tokens to every session and 1,801 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
code-review
OWASP-mapped, skill-aware code review with autofix suggestions. Reviews the diff, not the world.
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.
stop
Stop the voice dictation daemon.
wp-tailwindify
Convert an HTML/CSS demo to Tailwind-native HTML — preserves section delimiters, maps colors to @theme variables.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.
ui-synth
Master orchestration command that synthesizes ALL LibreUIUX plugins - archetypal-alchemy, design-mastery, accessibility, security, performance, testing - into one cohesive, production-ready UI/UX implementation. The ultimate synthesis.