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/Laith0003/ux-skillWrote 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/laith0003/ux-skill/ux-mcp)<a href="https://agentmods.dev/commands/laith0003/ux-skill/ux-mcp"><img src="https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-mcp.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.01978 |
| Opus 5 | $0.00036 | $0.00989 |
| Sonnet 5 | $0.00014 | $0.00396 |
| Haiku 4.5 | $0.00007 | $0.00198 |
Grade A, and why
ux-mcp 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 8d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ux-mcp — the design intelligence MCP
One server. Fourteen tools. Every MCP-aware client gets the engine.
This is the asymmetric move. None of the leading Claude UX skills (ui-ux-pro-max-skill, open-design, taste-skill, huashu-design, stitch, nothing-design, hallmark, material-3) ship an MCP server. Doing so turns ux-skill into the canonical design-intelligence MCP — agents in any host can call into the same recommender, linter, and manifests that the plugin uses, without needing to install the plugin itself.
When to use
- You're using Cursor, Windsurf, Claude Desktop, or any other MCP-capable host and want ux-skill available without forcing the host to learn the plugin layout.
- You're orchestrating a multi-agent pipeline and need a single source of truth for design constraints across agents.
- You're writing CI tooling that calls the recommender or linter from a long-running daemon rather than spawning a CLI each time.
When to skip
- You're already inside Claude Code with the plugin installed — the slash commands hit the engine directly, no MCP transport needed.
- You only need a one-shot recommendation or lint —
ux recommend/ux lintfrom the CLI is simpler.
Install
The MCP transport is an optional dependency to keep the base install slim:
pip install 'uxskill[mcp]'
Or, if you already have uxskill:
pip install 'mcp>=1.0'
Start the server
ux-mcp # entry point (preferred — wired by pyproject.toml)
python3 -m engine.mcp.server # equivalent module form
The server speaks stdio JSON-RPC. Logs go to stderr only; stdout is reserved for the protocol stream.
Exposed tools (14)
| Tool | What it does |
|---|---|
ux_recommend |
Run the 5-parallel-search recommender over a brief. Returns style + palette + type pair + motion + components + brand exemplars + guardrails + rationale. |
ux_lint |
Run the anti-AI-slop regex linter over paths. Returns findings with rule id, severity, file, line, excerpt, fix. |
ux_styles |
Return all 84+ entries from data/styles.json. |
ux_palettes |
Return all 176+ entries from data/palettes.json. Optional mode filter (light / dark). |
ux_type_pairs |
Return all 70+ entries from data/type-pairs.json. |
ux_components |
Return all 148+ entries from data/components.json. Optional category filter. |
ux_industries |
Return all 184+ entries from data/industries.json. Optional category filter. |
ux_motion_presets |
Return all 57+ entries from data/motion-presets.json. Optional category filter. |
ux_anti_patterns |
Return all 35+ regex rules from data/anti-patterns.json. Optional severity filter. |
ux_brands |
Return all 92 brand specs from data/brands/*.json (Apple, Stripe, Linear, Tesla, Notion, etc.). Optional category filter. |
ux_landing_patterns |
Return all 24+ entries from data/landing-patterns.json. Optional category filter. |
ux_persist_save |
Persist a recommendation as .ux/design-system/MASTER.md in a given project root. Idempotent — same input writes byte-identical bytes. |
ux_persist_load |
Load .ux/design-system/MASTER.md back into a structured dict. |
ux_stats |
Return the engine version and per-manifest entry counts. Useful as a health probe. |
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.
- 8d ago First seen · 208 lines · 72 tokens per session scan A 3d2529535c5c
ux-mcp is a command published in the GitHub repository Laith0003/ux-skill (68 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 1,978 once invoked, about $0.0004 per session on Opus 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 commands, from other repositories
accessibility-audit
You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct comprehensive audits, identify barriers, provide remediation guidance, and ensure digital products are accessible to all users.
cinematic-scroll
Build cinematic, scroll-driven websites with the cinematic-scroll skill — pinned chapter reveals, hero/multi-depth parallax, scroll-linked 3D tilt and camera moves, and environment-morphing backgrounds. From a single self-contained .html scroll section (Mode A) to a full Next.js release site with optional AI-generated…
healthcare-ux-specialist
Use when designing clinical or patient-facing interfaces. Clinical workflows, displaying sensitive patient data, HIPAA considerations in the UI, and medical terminology patients do not speak.
motion-designer
Use when animation feels wrong. Transitions too slow or too bouncy, motion with no purpose, blanket transitions on every property, no reduced-motion support, or animation that drops frames.
spacing-layout-specialist
Use when spacing looks arbitrary. Padding and margins off any scale, inconsistent gaps between the same components, no grid underneath, or a layout that needs a denser mode.
add-library
Kullanıcı "kütüphane ekle", "library ekle", "tasarım sistemi ekle", "design system ekle" dediğinde bu komutu uygula.