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.
npx skills add floomhq/moto --skill ui-auditgit clone --depth 1 https://github.com/floomhq/motoWrote 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/floomhq/moto/ui-audit)<a href="https://agentmods.dev/skills/floomhq/moto/ui-audit"><img src="https://agentmods.dev/badge/skills/floomhq/moto/ui-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/floomhq/moto/ui-audit"><img src="https://agentmods.dev/badge/skills/floomhq/moto/ui-audit.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 | $0.00129 | $0.01276 |
| Opus 5.5 | $0.00052 | $0.00510 |
| Sonnet 5.5 | $0.00026 | $0.00255 |
| Haiku 4.5 | $0.00013 | $0.00128 |
Grade A, and why
ui-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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Audit
Two audit modes for web apps. Pick the right one for the task.
Mode 1: UX / Product Review (no wireframe needed)
Evaluate the app as a real user would. No design spec required.
Workflow
- Capture every screen at desktop (1280x800) and mobile (390x844):
python3 scripts/capture_screens.py <app_url> -o /tmp/ui-audit --config screens.json
Or manually navigate and screenshot each route.
-
For each screen, evaluate against the UX checklist (
references/ux-review-checklist.md):- First impressions (what grabs attention, what confuses)
- Information hierarchy (is the most important content most prominent?)
- Navigation clarity (can the user find what they need?)
- Interaction affordances (do clickable things look clickable?)
- Content quality (clear labels, no jargon, helpful empty states)
- Error and edge states (what happens when things go wrong?)
- Mobile experience (not just a squeezed desktop, actually usable)
- Loading and performance perception (skeleton states, progress indicators)
- Accessibility basics (contrast, touch targets, focus indicators)
-
Cross-screen analysis:
- Consistency (same patterns used everywhere?)
- User flow (can a new user complete the core task without confusion?)
- Visual cohesion (colors, spacing, typography consistent?)
- Missing states (what screens/states are absent that users will hit?)
-
Output report grouped by severity (S1-S4), with screenshots and fix recommendations.
When to use Mode 1
- No wireframe or design spec exists
- Evaluating a competitor's product
- Post-launch UX review
- Checking if the app "feels right" independent of any spec
- Product feedback before a redesign
Mode 2: Wireframe Comparison (requires design spec)
Compare a live implementation against a static wireframe HTML file. Produces exact CSS property mismatches.
Prerequisites
playwrightPython package with Chromium- Wireframe HTML file path
- Live app URL (deployed or localhost)
What ships with it
5 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.
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 · 143 lines · 129 tokens per session scan A a02d80565aa0
ui-audit is a skill published in the GitHub repository floomhq/moto (32 stars, last pushed 4mo ago), licensed MIT. It adds 129 tokens to every session and 1,276 once invoked, about $0.0005 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
ui-review
Retroactive visual audit of UI implementation with 1-4 scoring per dimension.
claude-design-patterns
Engineering rules and reusable patterns for building polished web UI, React artifacts, slide decks, animations, and device mockups — distilled from Anthropic's leaked Claude Design agent system prompt. Use ALONGSIDE the frontend-design skill whenever building or iterating on visual web output: single-file React/HTML…
gsap
Expert guidelines for building high-performance animations with GSAP (GreenSock Animation Platform).
eval-agents
Audit custom subagent definitions for Claude Code (.claude/agents/.md) and Codex (.codex/agents/.toml): loadability against the native schema, description overlap, model tier, tool scope, and headless-safe instructions. Use when onboarding to a project with agents, after adding or importing agents, or when the parent…
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eleven checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…