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.
git clone --depth 1 https://github.com/jezweb/claude-skillsWrote 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.
[](https://agentmods.dev/commands/jezweb/claude-skills/ux-extract)<a href="https://agentmods.dev/commands/jezweb/claude-skills/ux-extract"><img src="https://agentmods.dev/badge/commands/jezweb/claude-skills/ux-extract/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.
<a href="https://agentmods.dev/commands/jezweb/claude-skills/ux-extract"><img src="https://agentmods.dev/badge/commands/jezweb/claude-skills/ux-extract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00016 | $0.00191 |
| Opus 5 | $0.00008 | $0.00096 |
| Sonnet 5 | $0.00003 | $0.00038 |
| Haiku 4.5 | $0.00002 | $0.00019 |
Grade B, and why
ux-extract 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 9d 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: "*" What it actually says
Load the ux-extract skill and run the extraction.
$ARGUMENTS should identify the reference app (URL or well-known name) and optionally a scope or focus lens:
/ux-extract claude.ai— extract the whole app/ux-extract claude.ai focus on empty states— narrower scope/ux-extract https://linear.app the onboarding flow— specific feature area
Output goes to docs/ux-extracts/<app-name>/pattern-library.md (or .jez/artifacts/ux-extracts/<app-name>/ if that directory exists).
The pattern library can be consumed by ux-audit as a comparison bar.
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.
- 9d ago First seen · 17 lines · 16 tokens per session scan B 973eb59d67d2
ux-extract is a command published in the GitHub repository jezweb/claude-skills (999 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 191 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.
Other commands, from other repositories
pr
Create a pull request using the git-pushing skill.
canvas-designer
Use the @canvas-designer agent for UI/UX design and implementation: $ARGUMENTS.
diagram-coordinator
Coordinate with agents to generate comprehensive educational diagrams.
diagram-from-file
Generate educational diagram from a source file using Excalidraw.
design-handoff
Write a design-to-engineering handoff as Markdown in the user's repository. Use when invoked as /document-design-system:design-handoff. Produce designed HTML or PDF only when asked.
designer
UI/UX design with Memory coordination for consistent experiences.