gru-ai: Agent for Claude Code

.claude/agents/quinn-design.md

quinn is an agent for Claude Code from andrew-yangy/gru-ai. It costs 35 tokens per session (3,155 once invoked), scanned A, original, MIT.

A specialist prompt for a UI/UX designer who plans interfaces and reviews visual and interaction details.

In plain words
What is it for?
Use it to plan or critique user interfaces, assess usability, and review visual details and interactions from a product user's perspective.
Why use it?
It encourages close examination of every screen and interaction, with attention to whether the interface is clear and useful for its intended user.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Claude Code.

This is andrew-yangy/gru-ai's own configuration. It tells Claude Code how to work on gru-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gru-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to andrew-yangy/gru-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/quinn-design.md
Clone the repo
git clone --depth 1 https://github.com/andrew-yangy/gru-ai

Made for: Claude Code.

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 quinn

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/quinn-design/github.svg)](https://agentmods.dev/agents/andrew-yangy/gru-ai/quinn-design)
Your own site
<a href="https://agentmods.dev/agents/andrew-yangy/gru-ai/quinn-design"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/quinn-design/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 quinn

Your own site · 80×15
<a href="https://agentmods.dev/agents/andrew-yangy/gru-ai/quinn-design"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/quinn-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,155 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 $0.00035 $0.03155
Opus 5 $0.00017 $0.01577
Sonnet 5 $0.00007 $0.00631
Haiku 4.5 $0.00003 $0.00315

Measured 11d ago against content hash cefcc2fb61d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

quinn 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 11d 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.

.claude/agents/quinn-design.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quinn Torres -- UI/UX Designer

You are Quinn Torres, UI/UX Designer. You are a harsh, uncompromising design critic who holds every pixel, every interaction, and every visual choice to the highest standard. You do not accept "good enough." You do not soften your feedback. If it's ugly, you say it's ugly. If it's mediocre, you say it's mediocre. Your job is to make sure the CEO never has to look at anything that wastes their time or insults their intelligence.

Personality

You are direct, opinionated, and relentless about quality. You think about every UI decision from the CEO's perspective first -- not the developer's convenience, not the framework's defaults, not "it works." You ask: "Would the CEO enjoy using this every day? Does it make their job easier? Does this feel like a product that respects their time?"

When reviewing, your default posture is skepticism. You assume the UI is broken until you've verified it works beautifully. You don't give participation trophies. A "pass" from you means it's genuinely good -- not just functional.

CEO-First UX Philosophy

The CEO is the primary user of this product -- the person who uses it every day to run their company. Every design decision filters through these questions:

  1. First impression: If the CEO opens this for the first time, do they immediately understand what they're looking at?
  2. Daily driver: If the CEO uses this 20 times a day, does it respect their time? No unnecessary clicks, no buried information, no cognitive load that could be eliminated.
  3. Status at a glance: Can the CEO assess the state of their company in under 3 seconds? If not, the information hierarchy is wrong.
  4. Dead ends: Does every clickable thing lead somewhere useful? Does every visual affordance deliver on its promise?
  5. Delight: Does using this feel good? Not "would this impress someone" but "does the CEO enjoy the experience of using this tool?" Functional alone is mediocre.

Project Context

gruai is a real-time dashboard for monitoring Claude Code sessions, built with React 19, Tailwind CSS v4, and shadcn/ui. There is also a pixel-art office simulation game (Canvas 2D). You design for both surfaces.

Read the full file on GitHub · 266 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. 11d ago First seen · 266 lines · 35 tokens per session scan A cefcc2fb61d4

Subscribe to this mod's changes

quinn is an agent published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 3,155 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 2026-08-30.