ux-audit

ux-audit is a skill for Claude Code, Codex from dundas/thinkrun. It costs 114 tokens per session (2,435 once invoked), scanned A, original, MIT.

A user-experience and quality review that walks through a product interface as a real user, records screenshots, and reports broken or confusing flows. It can inspect public pages or use an authenticated browser session.

In plain words
What is it for?
Use it to check a feature, onboarding flow, complete user journey, or public website for visual and interaction problems.
Why use it?
It exposes problems in navigation, onboarding, and user journeys that code-level tests may miss. The result is a structured report with specific fixes to consider.

Skill for Claude CodeCodex

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 skills/dundas/thinkrun/ux-audit
Any agent
npx skills add dundas/thinkrun --skill ux-audit
Clone the repo
git clone --depth 1 https://github.com/dundas/thinkrun

Made for: Claude Code, Codex.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/dundas/thinkrun/ux-audit.svg)](https://agentmods.dev/skills/dundas/thinkrun/ux-audit)
Your own site
<a href="https://agentmods.dev/skills/dundas/thinkrun/ux-audit"><img src="https://agentmods.dev/badge/skills/dundas/thinkrun/ux-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,435 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 $0.00114 $0.02435
Opus 5 $0.00057 $0.01218
Sonnet 5 $0.00023 $0.00487
Haiku 4.5 $0.00011 $0.00244

Measured 4d ago against content hash 8ce6d71a941e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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/skills/ux-audit/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Audit Skill

You are a world-class UX designer and QA engineer. Your job is to walk through a user journey on a product using a browser session, take screenshots at every meaningful step, and produce a structured UX report with a complete fix list.


Mode Selection

Local mode — use when the product requires auth/cookies (your real logged-in session):

  • Controls your actual Chrome via the ThinkRun extension + native host
  • All commands operate on the tab you attach to
  • Best for: apps behind login, staging environments with your cookies

Cloud mode — use for public-facing URLs, headless scraping, no auth needed:

  • Provisions an isolated cloud browser
  • Driven with thinkrun cloud start + --mode cloud (see the web-browse skill)
  • Best for: marketing pages, public flows, pre-auth journeys

Step 0 — Configure the Audit

PRODUCT="<product name>"
PRODUCT_URL="<http://localhost:PORT or https://your-app.example.com>"
AUDIT_DATE=$(date +%Y-%m-%d)
JOURNEY="<one-line description of the journey to test>"

If testing against localhost, check what's actually on the port before assuming the right app is there — other services may be squatting the default port:

PORT=$(printf '%s\n' "$PRODUCT_URL" | sed -nE 's#.*:([0-9]+).*#\1#p')
[ -n "$PORT" ] && lsof -iTCP:"$PORT" -sTCP:LISTEN 2>/dev/null | head -3

Step 1 — Start Session

Local Mode (auth required)

# List available Chrome tabs
thinkrun tabs

# Attach to an existing tab (use a clean one — New Tab, or any non-critical tab)
# TAB_ID comes from the tabs output above
TAB_ID=656847550
thinkrun attach $TAB_ID

# Navigate to the product
thinkrun navigate "$PRODUCT_URL"
sleep 2

The attached tab is now the active session. All subsequent commands route to it automatically — no session ID needed.

Cloud Mode (no auth required)

# Start an isolated cloud browser; it becomes the active session.
thinkrun cloud start
# Subsequent commands run against it. Force cloud per-command with --mode cloud.
thinkrun navigate "$PRODUCT_URL" --mode cloud
# When done: thinkrun cloud stop

Read the full file on GitHub · 284 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 284 lines · 114 tokens per session scan A 8ce6d71a941e

Subscribe to this mod's changes

ux-audit is a skill published in the GitHub repository dundas/thinkrun (1 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 2,435 once invoked, about $0.0006 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.