Borrowing it
Nothing to install: this file belongs to rome-os/rome. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rome-os/rome/main/.claude/skills/ux-semantics-audit/SKILL.mdgit clone --depth 1 https://github.com/rome-os/romeWrote 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/skills/rome-os/rome/ux-semantics-audit)<a href="https://agentmods.dev/skills/rome-os/rome/ux-semantics-audit"><img src="https://agentmods.dev/badge/skills/rome-os/rome/ux-semantics-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.
<a href="https://agentmods.dev/skills/rome-os/rome/ux-semantics-audit"><img src="https://agentmods.dev/badge/skills/rome-os/rome/ux-semantics-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00161 | $0.01907 |
| Opus 5.5 | $0.00064 | $0.00763 |
| Sonnet 5.5 | $0.00032 | $0.00381 |
| Haiku 4.5 | $0.00016 | $0.00191 |
Grade A, and why
ux-semantics-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Audit
Evaluate UI code against a curated set of verifiable UX rules and emit findings a coding agent can directly act on. This is a linter for UX semantics, not an aesthetic critique: the goal is high-precision, evidence-backed findings, not a wall of vague suggestions.
Design philosophy (read this — it shapes every judgment call)
- Precision over recall. A false positive costs more than a miss: the consuming coding agent will "fix" a non-problem and degrade the design. When in doubt, don't flag.
- No evidence, no finding. Every finding must cite the exact file, line range, and quoted code snippet that demonstrates the violation. If you cannot point at the code, the finding does not exist.
- Exceptions are where precision lives. Each rule in
references/rules.mdhas an enumerated exceptions list. Before flagging, check the exceptions. A candidate that matches an exception is a pass, not a "borderline flag." - Severity is trust calibration.
blockfindings are mechanical and near-certain — the agent should fix all of them.warnfindings involve judgment — the agent should consider them and may reasonably decline with a reason. Never promote a judgment call toblock. - Feedback must be constructive and specific. Every finding includes a concrete suggested fix expressed in terms of the actual code, not a restatement of the rule.
Workflow
Step 1 — Scope the audit
Identify the unit of analysis: the view. A view is a screen, page, route, dialog, drawer, or self-contained form — the thing a user perceives at one time. Enumerate the views in scope:
- If given a whole repo/directory: find view-level components (pages, routes, dialogs, modals). List them and confirm scope with the user if there are more than ~10.
- If given a single component/file: that component and its rendered children are the view.
- If given a screenshot or design description alongside code, the code is the source of truth for findings; the image is context.
What ships with it
26 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.
- references/report-app.md 6.3 KB
- references/rules.md 16 KB
- report/.gitignore 229 B
- report/build.mjs 1.8 KB runs code
- report/findings.example.tsx 2.8 KB
- report/fonts.css 1.9 KB
- report/fonts/funnel-sans-latin-400-normal.woff2 10 KB
- report/fonts/funnel-sans-latin-500-normal.woff2 10 KB
- report/fonts/funnel-sans-latin-600-normal.woff2 11 KB
- report/fonts/ibm-plex-mono-latin-400-normal.woff2 14 KB
- report/fonts/ibm-plex-mono-latin-500-normal.woff2 15 KB
- report/fonts/LICENSE 880 B
- report/fonts/petrona-latin-500-normal.woff2 23 KB
- report/fonts/petrona-latin-600-normal.woff2 23 KB
- report/index.html 838 B
- report/main.tsx 569 B
- report/postcss.config.mjs 388 B runs code
- report/prompt.ts 2.0 KB runs code
- report/prose.tsx 1.1 KB
- report/Report.tsx 15 KB
- report/repros.example.tsx 1.7 KB
- report/rsbuild.config.ts 4.9 KB runs code
- report/styles.css 1.3 KB
- report/tsconfig.json 1.4 KB
- report/typecheck.mjs 1.3 KB runs code
- report/types.ts 2.6 KB runs code
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.
- 1mo ago First seen · 115 lines · 161 tokens per session scan A 564665437586
ux-semantics-audit is a skill published in the GitHub repository rome-os/rome (877 stars, last pushed today), licensed MIT. It adds 161 tokens to every session and 1,907 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for publishartifact, outputiframe, or slackattachhtml.
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.
a2ui
Make a reply easier to read and act on with rich blocks inside ordinary Markdown — a choice the user picks from, a form that collects several answers, a procedure as steps with warnings in place, a callout, a Mermaid diagram, a weather card, a live clock or countdown, a dashboard of gauges for a quota, a budget or a…
bento-slides
Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.
ui-design
Design-quality reference for financial-research visual output: typography, color, composition, and avoiding generic AI aesthetics.