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 hackermanishackerman/claude-skills-vault --skill ux-toolkitgit clone --depth 1 https://github.com/hackermanishackerman/claude-skills-vaultWrote 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/hackermanishackerman/claude-skills-vault/ux-toolkit)<a href="https://agentmods.dev/skills/hackermanishackerman/claude-skills-vault/ux-toolkit"><img src="https://agentmods.dev/badge/skills/hackermanishackerman/claude-skills-vault/ux-toolkit/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/hackermanishackerman/claude-skills-vault/ux-toolkit"><img src="https://agentmods.dev/badge/skills/hackermanishackerman/claude-skills-vault/ux-toolkit.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 | $0.00035 | $0.02223 |
| Opus 5.5 | $0.00014 | $0.00889 |
| Sonnet 5.5 | $0.00007 | $0.00445 |
| Haiku 4.5 | $0.00003 | $0.00222 |
Grade A, and why
ux-toolkit 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.
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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Toolkit
Professional-grade meta-skill for systematic UX evaluation across 9 domains. Framework-agnostic design works for web, mobile, and desktop applications.
When to Use
Invoke for:
- UI/UX heuristic evaluations (Nielsen + modern methodologies)
- Accessibility (WCAG 2.2) compliance audits
- User flow & friction analysis
- Responsive/cross-device testing
- Interaction & micro-interaction review
- Design system consistency audits
- Content & UX writing review
- AI/ML interface patterns
- Privacy & ethical design review
Audit Type Selection
What do you need to evaluate?
│
├─► Full UX Audit ─────────► Load ALL references
│
├─► Accessibility Only ────► Load accessibility-inspector.md
│
├─► Usability Review ──────► Load heuristic-audit.md + user-flow-analysis.md
│
├─► Visual/Responsive ─────► Load responsive-behavior.md + interaction-review.md
│
├─► Design System ─────────► Load design-system-audit.md
│
├─► Content Audit ─────────► Load content-ux-audit.md
│
├─► AI Interface ──────────► Load ai-ux-patterns.md
│
└─► Privacy/Ethics ────────► Load privacy-ethics-audit.md
Sub-Workflows
| Domain | Reference | Purpose |
|---|---|---|
| Heuristic Audit | references/heuristic-audit.md |
Nielsen's 10 + modern methodologies (OOUX, JTBD, Cognitive Walkthrough) |
| A11Y Inspector | references/accessibility-inspector.md |
WCAG 2.2 AA/AAA, keyboard nav, screen readers |
| Flow Analysis | references/user-flow-analysis.md |
Task paths, friction points, cognitive load |
| Responsive | references/responsive-behavior.md |
Breakpoints, touch targets, RTL/LTR, PWA |
| Interactions | references/interaction-review.md |
Micro-interactions, animations, feedback |
| Design System | references/design-system-audit.md |
Token consistency, component audit |
| Content UX | references/content-ux-audit.md |
UX writing, readability, voice & tone |
| AI/ML Patterns | references/ai-ux-patterns.md |
Explainability, trust, ML error handling |
| Privacy & Ethics | references/privacy-ethics-audit.md |
Dark patterns, consent, GDPR/DSA compliance |
What ships with it
13 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.
- data/issues-database.json 14 KB
- references/accessibility-inspector.md 14 KB
- references/ai-ux-patterns.md 11 KB
- references/content-ux-audit.md 10 KB
- references/design-system-audit.md 9.1 KB
- references/heuristic-audit.md 16 KB
- references/interaction-review.md 11 KB
- references/privacy-ethics-audit.md 12 KB
- references/responsive-behavior.md 9.7 KB
- references/user-flow-analysis.md 8.4 KB
- scripts/check_contrast.py 4.7 KB runs code
- scripts/generate_report.py 9.2 KB runs code
- scripts/run_axe.js 5.3 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.
- 2mo ago First seen · 246 lines · 35 tokens per session scan A 655a7de124bc
ux-toolkit is a skill published in the GitHub repository hackermanishackerman/claude-skills-vault (2 stars, last pushed 19d ago), licensed MIT. It adds 35 tokens to every session and 2,223 once invoked, about $0.0001 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.
Other skills, from other repositories
schematics
Creates or refines publication-quality technical diagrams with the native generateimage tool (Nano Banana Pro through Ace or a Gemini key, GPT Image 2 through an OpenAI key), method and architecture overviews, pipelines, CONSORT and PRISMA flows, experimental workflows, biological pathways, circuits and conceptual…
code-quality-principles
Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.
methodology-curator
Surface expert frameworks. Use when creating or evaluating skills, hooks, or agents.
visualize
Create visualizations and interactive tools directly in conversation. Use when the user asks to see how something works, explore 'what happens when' or 'what changes', compare or inspect, or wants a simulation, map, chart, graph, or mockup, or when a visual clearly explains better than text. Use standard tools for…
frontend-philosophy
Visual & UI philosophy (The 5 Pillars of Intentional UI). Understand deeply to avoid "AI slop" and create distinctive, memorable interfaces.
presentations
Create, inspect, edit, import, and export durable presentation artifacts and explicit PPTX file boundaries. Use for decks, slides, masters, layouts, rich text, tables, charts, imported media, groups, notes, and visual presentation QA.