A guide to measuring user experience with performance data, analytics, automated scores, and usability surveys.

It helps track Core Web Vitals such as loading speed, interaction response, and layout stability; define analytics events; interpret Lighthouse scores; and calculate usability measures such as SUS.

It replaces vague opinions about usability with defined measurements and guidance on interpreting them.

ux-metrics — Skill for Claude Code by TimboGP/timbogp-marketplace

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 TimboGP/timbogp-marketplace --skill ux-metrics

Clone the repo

git clone --depth 1 https://github.com/TimboGP/timbogp-marketplace

Made for: Claude Code.

Or install ux-design, the plugin that ships this one along with the rest of its 9 skills, 5 commands, 1 agent.

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/timbogp/timbogp-marketplace/ux-metrics/github.svg)](https://agentmods.dev/skills/timbogp/timbogp-marketplace/ux-metrics)

Your own site

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

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,671 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	$0.00101	$0.01671
Opus 5.5	$0.00040	$0.00668
Sonnet 5.5	$0.00020	$0.00334
Haiku 4.5	$0.00010	$0.00167

Measured 2mo ago against content hash 995bd23eda20, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ux-metrics 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/sus-score.mjs, scripts/web-vitals-snippet.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugin/ux-design/skills/ux-metrics/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX metrics

The quantitative measurement layer for UX. Use it to choose meaningful metrics, instrument them, and read the results honestly — covering performance, automated quality scores, analytics events, and self-reported usability.

When to use

Trigger when the user wants to "measure UX", set up or "track LCP/INP/CLS", instrument "Core Web Vitals", interpret a "Lighthouse score", "design analytics events", compute a "SUS score", define "usability metrics", or asks "how do I quantify UX". Detect the project's stack first via ../ux-foundations/references/stack-detection.md and adapt to any analytics or perf library already present.

1. Core Web Vitals

Google's user-centric performance signals. Thresholds (the "good" boundary is the one to design for; "poor" begins past the second number):

Metric	What it measures	Good	Needs improvement	Poor
LCP Largest Contentful Paint	Loading — when the largest content element renders	≤ 2.5s	2.5s–4.0s	> 4.0s
INP Interaction to Next Paint	Responsiveness — worst-case input latency across the visit	≤ 200ms	200ms–500ms	> 500ms
CLS Cumulative Layout Shift	Visual stability — unexpected layout movement (unitless)	≤ 0.1	0.1–0.25	> 0.25

INP replaced FID as a Core Web Vital in March 2024 — use INP.

Instrument with the bundled scripts/web-vitals-snippet.js (a copy-paste template using the web-vitals v4 library). It reports each metric to console and an endpoint.

Field vs lab data — distinguish the two and report both when you can:

Field (RUM) — real users, real devices and networks. The source of truth for CWV (e.g. CrUX, your own web-vitals beacons). Aggregate at the 75th percentile across page loads, per metric.
Lab — synthetic, controlled run (Lighthouse, WebPageTest). Reproducible and good for debugging regressions, but a single device/network — not the user-experienced number. Note: lab cannot measure INP (no real interactions); it reports TBT as a proxy.

Read the full file on GitHub · 81 lines

Files

What ships with it

3 files 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.

2mo ago First seen · 81 lines · 101 tokens per session scan A 995bd23eda20

Subscribe to this mod's changes

ux-metrics is a skill published in the GitHub repository TimboGP/timbogp-marketplace (3 stars, last pushed 23d ago), licensed MIT. It adds 101 tokens to every session and 1,671 once invoked, about $0.0004 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 2026-08-31.

Analytics and metrics Claude Code Design and UX Learning and teaching claude-code-plugin claude-code-skill claude-code-skills learning

ux-metrics next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ux-metricsTimboGP/timbogp-marketplace	Skill	3	23d ago	MIT	A	101	Claude Code
explainthoughtbot/rails-consultant	Skill	28	7d ago	MIT	A	45	Claude Code
gan-zhong-xuely8427/gan-zhong-xue	Skill	11	16d ago	MIT	B	288	Claude Code
accessibilityRealDougEubanks/ClaudeMarketplace	Skill	1	7d ago	MIT	A	41	Claude Code
abd-designRealDougEubanks/ClaudeMarketplace	Skill	1	7d ago	MIT	A	26	Claude Code
qector-educatorGuillaumeLessard/qector-claude-plugin	Skill	1	2mo ago	none	A	61	Claude Code
ux-designIdoCohen560/claude-unity-game-studio	Skill	27	4mo ago	MIT	A	61	Claude Code