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/martian56/claude-engineerWrote 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/agents/martian56/claude-engineer/design-researcher)<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.
<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>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 | $0.00067 | $0.00411 |
| Opus 5 | $0.00034 | $0.00205 |
| Sonnet 5 | $0.00013 | $0.00082 |
| Haiku 4.5 | $0.00007 | $0.00041 |
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.
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:
- Identify 3 - 5 reference products with a similar vibe/use-case; note what makes each feel right.
- 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.
- 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.
- 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.
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.
- 9d ago First seen · 30 lines · 67 tokens per session scan A ddac4785272f
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.
Other agents, from other repositories
design-token-extractor
Use this agent to extract design tokens from CSS, SCSS, JavaScript, or Tailwind config files. Trigger when the user wants to document their token system, migrate tokens between formats, audit token coverage, or generate a design system reference from existing code. Context: User wants to document their CSS custom…
design-auditor
Master audit orchestrator. Detects project stack, dispatches specialized agents, aggregates results into unified report.
typography-analyst
Diagnose and improve typography systems. Covers font selection, type scale, readability, and performance.
ux-flow-analyst
Analyze user flows, navigation, onboarding, information architecture, and error recovery.
component-reviewer
Audit component quality, consistency, state coverage, and patterns.
psychology-analyst
Evaluate design through behavioral psychology. Covers cognitive load, hierarchy, trust, persuasion, and dark patterns.