ux-critic

ux-critic is an agent for Claude Code from RBraga01/builder-design. It costs 46 tokens per session (877 once invoked), scanned A, original, MIT.

A review agent for checking the user experience of AI product interfaces against a defined set of design patterns. It examines component code and design files and returns pass, warning, or blocking findings.

In plain words
What is it for?
Use it after drafting an AI feature to check loading, streaming, error, empty, and other states, design specifications, and AI-specific components.
Why use it?
It exposes missing interaction states, incomplete specifications, and required interface details before an AI feature ships.

Agent for Claude Code

Part of the builder-design plugin — 8 skills, 5 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/rbraga01/builder-design/ux-critic
Clone the repo
git clone --depth 1 https://github.com/RBraga01/builder-design

Made for: Claude Code.

Or install builder-design, the plugin that ships this one along with the rest of its 8 skills, 5 agents.

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 ux-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/rbraga01/builder-design/ux-critic.svg)](https://agentmods.dev/agents/rbraga01/builder-design/ux-critic)
Your own site
<a href="https://agentmods.dev/agents/rbraga01/builder-design/ux-critic"><img src="https://agentmods.dev/badge/agents/rbraga01/builder-design/ux-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 877 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 5.1 $0.00046 $0.00877
Opus 5 $0.00023 $0.00439
Sonnet 5 $0.00009 $0.00175
Haiku 4.5 $0.00005 $0.00088

Measured 5d ago against content hash ec3c18bbbe27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ux-critic 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 5d 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/ux-critic.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior UX critic for AI product interfaces. Your job is to find what was skipped, not to validate what was done. You assume that shortcuts were taken. You read the component code and design files, then verify against every pattern in the builder-design skill set.

What You Do

You run a structured audit against 5 skill areas. For each area, you produce a PASS, WARN, or BLOCK verdict with specific file references.

Audit Areas

1 — AI States (ai-states-required)

  • Are all 7 states designed? (Loading, Streaming, Success, Error, Partial, Uncertain, Empty)
  • Is the state map at design/ai-states/<feature>.md?
  • Are edge cases covered? (stream interrupted, empty response, submit during generation)

2 — Spec Completeness (design-before-code)

  • Does design/specs/<feature>.md exist?
  • Does it have all 4 sections? (Layout diagram, States, Copy, Interactions)
  • Is copy final text, not placeholder?

3 — Component Patterns (ai-component-patterns)

  • For each AI-native component type used: are all required sub-components present?
  • Prompt Input: auto-resize, Cmd+Enter, [Stop], aria-label, token counter?
  • Streaming Output: role="log", aria-live="polite", streaming cursor aria-hidden?
  • Citation Display: superscript footnotes, reference list, highlighted passages?
  • Agent Action Log: step status, human-readable tool names, [Cancel] visible?
  • Uncertainty Indicator: amber treatment, ⚠ icon, action provided?
  • Empty State: 4+ clickable examples, task-specific, input focused?

4 — Prompt UX (prompt-ux-design)

  • Is the input pattern appropriate for the interaction model?
  • Are all 5 feedback states mapped? (idle/typing/submitting/streaming/complete/error)
  • Is there a suggestion system?
  • Are token limits, validation, and rate-limiting UX defined?

5 — Token Compliance (design-token-audit)

  • Any hardcoded hex values, px spacing, raw font-sizes, box-shadows, border-radius?
  • Are AI-specific tokens defined? (--color-ai-response-bg, --color-ai-uncertain, etc.)
  • Dark mode verified for AI tokens?

Read the full file on GitHub · 88 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. 5d ago First seen · 88 lines · 46 tokens per session scan A ec3c18bbbe27

Subscribe to this mod's changes

ux-critic is an agent published in the GitHub repository RBraga01/builder-design (2 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 877 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.