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.
git clone --depth 1 https://github.com/nyldn/claude-dolphinWrote 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.
[](https://agentmods.dev/commands/nyldn/claude-dolphin/design-system-review)<a href="https://agentmods.dev/commands/nyldn/claude-dolphin/design-system-review"><img src="https://agentmods.dev/badge/commands/nyldn/claude-dolphin/design-system-review/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.
<a href="https://agentmods.dev/commands/nyldn/claude-dolphin/design-system-review"><img src="https://agentmods.dev/badge/commands/nyldn/claude-dolphin/design-system-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00007 | $0.01533 |
| Opus 5 | $0.00003 | $0.00766 |
| Sonnet 5 | $0.00001 | $0.00307 |
| Haiku 4.5 | $0.00001 | $0.00153 |
Grade A, and why
design-system-review 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System Review Command
Analyze the codebase for design token usage, component consistency, and design system adherence.
Analysis Process
Step 1: Identify Design System Configuration
Find and read configuration files:
# Tailwind config
Glob: tailwind.config.{js,ts,mjs}
# CSS variables
Glob: **/globals.css, **/variables.css
# shadcn config
Read: components.json
Document:
- Defined color tokens
- Spacing scale
- Typography scale
- Border radius values
- Shadow definitions
Step 2: Audit Design Token Usage
Color Audit
Search for hardcoded colors:
# Hex colors
Grep: #[0-9a-fA-F]{3,6} in src/components/
# RGB/RGBA
Grep: rgb\(|rgba\( in src/components/
# HSL/HSLA
Grep: hsl\(|hsla\( in src/components/
For each hardcoded value, record:
- File location
- Line number
- Current value
- Suggested token replacement
Spacing Audit
Search for hardcoded spacing:
# Pixel values not in CSS variables
Grep: \d+px(?!.*var\() in src/components/
# Check for inconsistent patterns
Grep: (p|m|gap|space)-\d+ in src/components/
Compare against defined scale:
- 4px (p-1, m-1)
- 8px (p-2, m-2)
- 12px (p-3, m-3)
- 16px (p-4, m-4)
- 24px (p-6, m-6)
- 32px (p-8, m-8)
- 48px (p-12, m-12)
- 64px (p-16, m-16)
Typography Audit
Search for inconsistent typography:
# Font sizes
Grep: font-size:|text-\[|text-xs|text-sm|text-base|text-lg|text-xl in src/
# Font weights
Grep: font-weight:|font-(thin|light|normal|medium|semibold|bold) in src/
# Line heights
Grep: line-height:|leading- in src/
Step 3: Component Inventory
shadcn Component Usage
If shadcn MCP available:
search_items_in_registries: List all available components
Manual check:
# List installed shadcn components
Glob: src/components/ui/*.tsx
# Count usages of each
Grep: from "@/components/ui/[component]" in src/
Custom Component Detection
# Find components not in ui/ directory
Glob: src/components/**/*.tsx
# Exclude ui/ directory
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.
- 10d ago First seen · 263 lines · 7 tokens per session scan A abca21c7b63b
design-system-review is a command published in the GitHub repository nyldn/claude-dolphin (9 stars, last pushed 17d ago), licensed MIT. It adds 7 tokens to every session and 1,533 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
review-ui
Run a UI code review on the current snippet — Before / After / Why table per review-format, scoped to review-checklist.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
critique
Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion before a handoff or presentation.
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
agentation-fix
Session-2 fix loop for Agentation — read structured annotations from the dev overlay and apply targeted UI fixes.
scan-ai-tells
Scan UI or marketing copy for AI-default tells and content-authenticity misses — deletion list, not a redesign brief.