A browser-based check of how easily people can complete key tasks in a web app, using usability guidelines and Playwright, a tool for controlling browsers.

It helps review login and other user journeys for different roles, measuring task completion and checking the listed routes.

It finds unclear feedback, confusing steps, mental effort, and poor recovery from mistakes before they affect users.

ux-audit — Skill for Claude Code by marcoguillermaz

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.

Any agent

npx skills add marcoguillermaz/Tierward --skill ux-audit

Clone the repo

git clone --depth 1 https://github.com/marcoguillermaz/Tierward

Made for: Claude Code.

Or install tierward, the plugin that ships this one along with the rest of its 29 skills, 1 command, 1 hook, 1 MCP server.

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/skills/marcoguillermaz/tierward/ux-audit/github.svg)](https://agentmods.dev/skills/marcoguillermaz/tierward/ux-audit)

Your own site

<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/ux-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/ux-audit/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/skills/marcoguillermaz/tierward/ux-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/ux-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,284 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	$0.00000	$0.04284
Opus 5	$0.00000	$0.02142
Sonnet 5	$0.00000	$0.00857
Haiku 4.5	$0.00000	$0.00428

Measured 11d ago against content hash b417907f549b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ux-audit 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.

packages/cli/templates/tier-l/.claude/skills/ux-audit/SKILL.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configuration (fill in before first run)

Replace these placeholders:

[DEV_URL] - e.g. http://localhost:3000

[LOGIN_ROUTE] - your login page path, e.g. login, signin, auth/login

[SITEMAP_OR_ROUTE_LIST] - e.g. docs/sitemap.md

[TEST_ACCOUNTS] - email/password pairs per role

[DEV_COMMAND] - e.g. npm run dev, pnpm dev

Then fill in the Flow catalog (Step 5) with your project's key user journeys. Start with 3-5 Priority 1 flows covering the most critical tasks per role.

If [DEV_URL] or [SITEMAP_OR_ROUTE_LIST] is not filled, the skill reports an error and exits.

Step 0 - Mode + target detection

Parse $ARGUMENTS:

Mode (which flows to run):

role:<role> → run all flows for a specific role (e.g. role:viewer)
full → run all flows including Priority 2
No mode keyword → standard - run all Priority 1 flows (P1) for all roles

Target (filters to a specific area - applied on top of mode):

target:role:<role_name> → only that role's flows
No target → no filter - run ALL flows in the selected mode across ALL routes in [SITEMAP_OR_ROUTE_LIST]

STRICT PARSING - mandatory: derive mode and target ONLY from the explicit text in $ARGUMENTS. Do NOT infer target from conversation context, recent work, active block names, or project memory. If $ARGUMENTS contains no target: token → apply NO filter (run all flows in the selected mode). If $ARGUMENTS is empty → STANDARD mode, full scope (all P1 flows, no filter).

Announce at start: Running ux-audit in [STANDARD | FLOW:<id> | ROLE:<role> | FULL] mode - scope: [FULL | target: <resolved description>]

Step 1 - Load architecture context

Read in parallel:

[SITEMAP_OR_ROUTE_LIST] - full route inventory, sub-hierarchies, role mapping, test accounts

From sitemap sub-hierarchies, build a mental model of:

What tabs exist per page
What states each page can be in (empty, loading, error, data)
What actions are available per role
Which flows are newly implemented (check docs/implementation-checklist.md for recently completed blocks) - these need extra scrutiny

Read the full file on GitHub · 350 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.

11d ago First seen · 350 lines · 0 tokens per session scan A b417907f549b

Subscribe to this mod's changes

ux-audit is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,284 tokens. 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.

Claude Code Design and UX ai-assisted-development ai-governance cli developer-tools nodejs

diagrams

Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".

anton-abyzov/specweave · 0 tokens

preview-design

Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…

egregore-labs/egregore · 71 tokens

atomic-visual-options

Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by…

damusix/atomic-claude · 150 tokens

ux-audit