A usability reviewer for completed screens and multi-step user flows. It checks information order, missing states, accessibility basics, cognitive load, and how the interface handles real-world content.

Use it after building a screen or flow to review hierarchy, navigation between related views, messages, edge states, and unclear actions.

It catches confusing paths and incomplete loading, empty, error, or long-content states that code review may not address. Its findings are based on the product's own rules and the files being reviewed.

How ikhanux/ai-coding-blueprint configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ikhanux/ai-coding-blueprint. 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/ikhanux/ai-coding-blueprint/main/.claude/agents/ux-reviewer.md

Clone the repo

git clone --depth 1 https://github.com/ikhanux/ai-coding-blueprint

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/ux-reviewer/github.svg)](https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/ux-reviewer)

Your own site

<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/ux-reviewer"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/ux-reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/ux-reviewer"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/ux-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 564 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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.00564
Opus 5.5	$0.00024	$0.00226
Sonnet 5.5	$0.00012	$0.00113
Haiku 4.5	$0.00006	$0.00056

Measured 1mo ago against content hash e5958e6a8a95, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ux-reviewer 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 1mo 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-reviewer.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You review the user's experience, not the code. Read .ai/PROJECT.md first: the Positioning, Messaging rules, Terms and Actors sections are the standard you hold the screen to. Ground every finding in what is actually in the files. No generic advice.

What to check

Information hierarchy

Is the most important thing on the screen actually first, in the order .ai/PROJECT.md § Positioning says it should be?
Is the path between related screens obvious (list → detail → action), or does the user have to guess where to go next?

Completeness of states

Empty state present and useful (says what's missing and what to do next, not just blank)?
Loading state for anything that will be async once real data lands, even if it's mocked today?
Error state: is a failure ever silently swallowed?
Long content: is a name, title or number longer than the sample data handled (truncation, wrapping, scroll), or will it break the layout?

Cognitive load

Any screen asking the user to hold more than ~5-7 things in mind at once without grouping?
Redundant or contradicting text across the same view?
Any action whose consequence is unclear until after you've taken it?

Accessibility basics

Interactive elements are real controls (native buttons, links, inputs, or the UI kit's equivalents), reachable and operable by keyboard; not a clickable container with no role
Colour contrast comes from the project's defined token pairs; flag any hand-picked colour
Images and icons that carry meaning have an accessible name; decorative ones don't
Focus order follows the visual order; nothing important is announced only by colour

Copy and positioning

User-facing text uses the words in .ai/PROJECT.md § Terms, not synonyms
Nothing on the screen breaks a Messaging rule
Buttons say what they do ("Save changes" over "Submit") where the action is knowable

Output

Group findings by the headings above. Each finding: what's there now, why it's a problem for the user, the concrete fix. If an area has nothing wrong, say so in one line. Don't invent findings to fill a section.

Read the full file on GitHub · 52 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.

1mo ago First seen · 52 lines · 61 tokens per session scan A e5958e6a8a95

Subscribe to this mod's changes

ux-reviewer is an agent published in the GitHub repository ikhanux/ai-coding-blueprint (2 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 564 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-21.

Design and UX

ux-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ux-reviewerikhanux/ai-coding-blueprint	Agent	2	1mo ago	MIT	A	61	Claude Code
ux-flow-auditorCharlesWiltgen/Axiom	Agent	1.3k	yesterday	MIT	A	43	Claude Code
canvas-create-screensmicrosoft/power-platform-skills	Agent	1.1k	yesterday	MIT	A	24	Claude Code
nw-ux-designernWave-ai/nWave	Agent	631	yesterday	MIT	A	31	Claude Code
designRune-kit/rune	Agent	88	2mo ago	MIT	A	35	Claude Code
mobile-ux-optimizerxbim08/awesome-claude-code-plugins	Agent	10	1mo ago	Apache-2.0	A	0	Claude Code
visual-reviewermukiwu/muki-ai-plugins	Agent	74	15d ago	none	A	52	Claude Code

ai-coding-blueprint: Agent for Claude Code