ux-compare

ux-compare is a command for Claude Code from jezweb/claude-skills. It costs 11 tokens per session (247 once invoked), scanned B, original, MIT.

A comparison command for reviewing user-experience patterns across libraries created by ux-extract. User-experience patterns are recurring interface solutions, such as empty states or keyboard shortcuts.

In plain words
What is it for?
Use it to compare specific patterns or whole pattern libraries across products such as Claude, Linear, and Superhuman.
Why use it?
It helps reveal how different products handle the same interface problem and where their approaches differ.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the dev-tools plugin — 16 skills, 14 commands shipped together

Good fit Use it to compare specific patterns or whole pattern libraries across products such as Claude, Linear, and Superhuman.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jezweb/claude-skills/ux-compare
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.

Clone the repo
git clone --depth 1 https://github.com/jezweb/claude-skills

Made for: Claude Code.

Or install dev-tools, the plugin that ships this one along with the rest of its 16 skills, 14 commands.

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-compare

README.md
[![agentmods](https://agentmods.dev/badge/commands/jezweb/claude-skills/ux-compare/github.svg)](https://agentmods.dev/commands/jezweb/claude-skills/ux-compare)
Your own site
<a href="https://agentmods.dev/commands/jezweb/claude-skills/ux-compare"><img src="https://agentmods.dev/badge/commands/jezweb/claude-skills/ux-compare/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.

agentmods 80×15 button for ux-compare

Your own site · 80×15
<a href="https://agentmods.dev/commands/jezweb/claude-skills/ux-compare"><img src="https://agentmods.dev/badge/commands/jezweb/claude-skills/ux-compare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 247 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00011 $0.00247
Opus 5 $0.00005 $0.00123
Sonnet 5 $0.00002 $0.00049
Haiku 4.5 $0.00001 $0.00025

Measured 10d ago against content hash 511d37d2c658, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

ux-compare scanned grade B with 1 finding 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 10d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

allowed-tools: "*"
plugins/dev-tools/commands/ux-compare.md · 19 lines

What it actually says

Load the ux-compare skill and run the comparison.

$ARGUMENTS should identify the scope (what to compare) and optionally the libraries to include:

  • /ux-compare empty states — across every available library
  • /ux-compare keyboard shortcuts across claude.ai, linear, superhuman — specific subset
  • /ux-compare destructive actions — across every available library
  • /ux-compare whole library across claude.ai and linear — wide scope, two apps

If fewer than 2 pattern libraries exist under docs/ux-extracts/ or .jez/artifacts/ux-extracts/, the skill will stop and suggest running ux-extract first. Comparison with one library is just the library.

Output goes to docs/ux-comparisons/<topic>-YYYY-MM-DD.md (or .jez/artifacts/ux-comparisons/ if that path exists).

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. 10d ago First seen · 19 lines · 11 tokens per session scan B 511d37d2c658

Subscribe to this mod's changes

ux-compare is a command published in the GitHub repository jezweb/claude-skills (999 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 247 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.