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 agentmods add commands/laith0003/ux-skill/ux-recommendgit 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-recommend)<a href="https://agentmods.dev/commands/laith0003/ux-skill/ux-recommend"><img src="https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-recommend.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 | $0.00093 | $0.01371 |
| Opus 5 | $0.00046 | $0.00685 |
| Sonnet 5 | $0.00019 | $0.00274 |
| Haiku 4.5 | $0.00009 | $0.00137 |
Grade A, and why
ux-recommend 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 6d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ux-recommend — the flagship
One command. Five parallel searches. One merged system out.
Industry → Style → Palette → Type → Motion + Components + Brand Exemplars + Guardrails. The Python engine does the merging; you get a structured recommendation you can hand directly to /ux-design or /ux-system.
When to use
- Starting a new project, surface, or marketing page from zero.
- Pivoting a tired-looking product to a deliberate aesthetic.
- Pre-flight before any
/ux-designor/ux-componentso the generation has explicit constraints, not implicit ones.
When to skip
- You already ran
/ux-discoverand saved a brief —/ux-recommendis automatic in that flow. - You're fixing one bug in existing code — use
/ux-fixinstead. - You only need to lint, not recommend — use
/ux-lint.
How it works
- The engine reads your brief (project type, industry, audience, tone, must-haves, forbidden, stack, region).
- Lane 1 —
industries.jsonlookup gives style/palette/type biases for your domain. - Lane 2 —
styles.jsonfiltered by industry + brief tags. - Lane 3 —
palettes.jsonfiltered bystyle.compatible_palettes. - Lane 4 —
type-pairs.jsonfiltered bystyle.compatible_type_pairs. - Lane 5 —
motion-presets.jsonfiltered by style hints. - Auxiliary lanes: components by style compatibility, brand exemplars by industry, anti-pattern guardrails (always on).
- The engine returns one merged Recommendation with rationale lines.
Usage
One-shot (no discovery)
python3 -m engine.cli.main recommend \
--project-type=landing \
--industry=fintech-neobank \
--tone=warm --tone=editorial \
--must-have=dark-mode --must-have=a11y-AA \
--forbidden=brutalism --forbidden=purple-gradients \
--stack=nextjs-15-app-router \
--region=mena
From a saved discovery brief (the canonical flow)
python3 -m engine.cli.main discover # 10 questions, mandatory
python3 -m engine.cli.main recommend --brief-file .ux/last-discovery.json
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.
- 6d ago First seen · 129 lines · 93 tokens per session scan A c1411816f76c
ux-recommend is a command published in the GitHub repository Laith0003/ux-skill (66 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 1,371 once invoked, about $0.0005 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
design-screen
Design a complete screen layout from a description or requirements.
responsive-audit
Audit a design's responsive behaviour across breakpoints — layout, touch targets, and content reflow.
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
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.
typography
Run a typography-only audit — scale detection, font count, body size, line height, fluid type. Scoped variant of /ui-ux-suite:audit.
design-system
Command "design-system" from XINGANLIU/design-system-generator-skill, covering design system generator — claude code command, usage: /design-system [font-family] [style] and example: /design-system #6366f1 "outfit" rounded.