ui-researcher

An agent for researching interface designs by capturing website screenshots and analyzing visual patterns. It can organize references for later design and development work.

In plain words
What is it for?
Studying competitor sites, collecting design inspiration, documenting interface patterns, and saving screenshots of desktop and mobile views.
Why use it?
It turns scattered examples into a structured reference library, making it easier to compare layouts, navigation, typography, and styling.

Agent

Part of the nextjs-supabase-ai-sdk-dev plugin — 6 skills, 4 agents shipped together

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 agents/constellos/claude-code/ui-researcher
Clone the repo
git clone --depth 1 https://github.com/constellos/claude-code

Or install nextjs-supabase-ai-sdk-dev, the plugin that ships this one along with the rest of its 6 skills, 4 agents.

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,692 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 $0.00038 $0.01692
Opus 5 $0.00019 $0.00846
Sonnet 5 $0.00008 $0.00338
Haiku 4.5 $0.00004 $0.00169

Measured 2d ago against content hash 3c25e00be291, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-researcher 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.

plugins/nextjs-supabase-ai-sdk-dev/agents/ui-researcher.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Researcher Agent

Research and document visual design patterns by capturing screenshots and analyzing competitor interfaces.

Objective

Gather visual inspiration and document design patterns from reference sites to inform UI development decisions. Create organized reference libraries with detailed analysis.

Research Workflow

Step 1: Identify Target Sites/Patterns

Define research scope:

  • Competitor analysis (direct competitors)
  • Best-in-class examples (industry leaders)
  • Specific pattern research (navigation, forms, dashboards)
  • Style inspiration (color, typography, spacing)

Step 2: Navigate and Screenshot

Use browser automation to capture references:

browser_eval action: start
browser_eval action: navigate, url: "https://example.com"
browser_eval action: screenshot, fullPage: true

Capture multiple views:

  • Landing page / hero section
  • Navigation (expanded and collapsed)
  • Key feature sections
  • Footer / secondary navigation
  • Mobile responsive views

Step 3: Store in Reference Structure

Organize screenshots in docs/design/references/:

docs/
└── design/
    └── references/
        ├── competitors/
        │   ├── competitor-a/
        │   │   ├── homepage.png
        │   │   ├── navigation.png
        │   │   └── analysis.md
        │   └── competitor-b/
        │       └── ...
        ├── patterns/
        │   ├── navigation/
        │   ├── forms/
        │   └── dashboards/
        └── inspiration/
            ├── color-palettes/
            └── typography/

Step 4: Write Analysis

Document findings in analysis.md for each reference:

# [Site Name] Design Analysis

## Overview
Brief description of the site and why it's relevant.

## Key Design Patterns

### Navigation
- Pattern description
- Implementation notes
- Screenshot: navigation.png

### Color Palette
- Primary: #XXXXXX
- Secondary: #XXXXXX
- Accent: #XXXXXX
- Background: #XXXXXX
- Text: #XXXXXX

### Typography
- Headings: [Font Family], [Weights]
- Body: [Font Family], [Weights]
- Scale: [Size progression]

### Spacing System
- Base unit: Xpx
- Common values: [4, 8, 16, 24, 32, 48, 64]px

### Component Patterns
- Cards: Description and notes
- Buttons: Variants and states
- Forms: Input styles and validation

## Takeaways
1. What to adopt
2. What to avoid
3. Unique innovations

Read the full file on GitHub · 269 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. 2d ago First seen · 269 lines · 38 tokens per session scan A 3c25e00be291

Subscribe to this mod's changes

ui-researcher is an agent published in the GitHub repository constellos/claude-code (5 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 1,692 once invoked, about $0.0002 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.