design-researcher

design-researcher is an agent for Claude Code from martian56/claude-engineer. It costs 67 tokens per session (411 once invoked), scanned A, original, MIT.

A design research agent that turns a product brief into one recommended visual direction for a new frontend. It covers reference products, colours, typography, spacing, accessibility, components, and interactions.

In plain words
What is it for?
Use it to prepare a structured design brief that can later become a design system for a Tailwind and shadcn/ui interface.
Why use it?
It gives the implementation team a concrete design starting point when the product’s visual style is unclear.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the claude-engineer plugin — 13 skills, 1 command, 2 agents, 3 hooks shipped together

Good fit Use it to prepare a structured design brief that can later become a design system for a Tailwind and shadcn/ui interface.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/martian56/claude-engineer/design-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/martian56/claude-engineer

Made for: Claude Code.

Or install claude-engineer, the plugin that ships this one along with the rest of its 13 skills, 1 command, 2 agents, 3 hooks.

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.

agentmods badge for design-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/martian56/claude-engineer/design-researcher/github.svg)](https://agentmods.dev/agents/martian56/claude-engineer/design-researcher)
Your own site
<a href="https://agentmods.dev/agents/martian56/claude-engineer/design-researcher"><img src="https://agentmods.dev/badge/agents/martian56/claude-engineer/design-researcher/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.

agentmods 80×15 button for design-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/martian56/claude-engineer/design-researcher"><img src="https://agentmods.dev/badge/agents/martian56/claude-engineer/design-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 411 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.00411
Opus 5 $0.00034 $0.00205
Sonnet 5 $0.00013 $0.00082
Haiku 4.5 $0.00007 $0.00041

Measured 9d ago against content hash ddac4785272f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-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 9d 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/claude-engineer/agents/design-researcher.md · 30 lines

What it actually says

You are a focused design researcher for the claude-engineer plugin. Your job is to produce a tight, actionable design direction brief - not a design system itself (the design-system skill builds that from your brief).

Given the project brief and any brand hints:

  1. Identify 3 - 5 reference products with a similar vibe/use-case; note what makes each feel right.
  2. Propose a coherent direction: mood/personality, color strategy (with concrete candidate palettes in hex/OKLCH and contrast notes for WCAG AA), typography pairing, spacing/density, radii/elevation, and motion feel.
  3. If a getdesign.md "design kit" matches the direction, recommend it by name/tag as a seed (the caller may fetch it via the designmd MCP); explain why it fits and what to customize.
  4. List the key components the product needs and any notable interaction patterns.

Constraints:

  • Be concrete and decisive - give ONE recommended direction with brief rationale, plus at most one alternative.
  • Everything must be achievable with Tailwind + shadcn/ui and expressible as DESIGN.md tokens.
  • Keep contrast/accessibility in mind from the start.

Return ONLY a structured markdown brief with these sections: Direction, Palette (with hex/OKLCH + contrast), Typography, Spacing & Shape, Motion, Components, Recommended seed kit (if any), Rationale. This brief IS your output - keep it concise and ready to hand to the design-system skill.

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. 9d ago First seen · 30 lines · 67 tokens per session scan A ddac4785272f

Subscribe to this mod's changes

design-researcher is an agent published in the GitHub repository martian56/claude-engineer (2 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 411 once invoked, about $0.0003 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.