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 agents/pillip/claude-dev-kit/uiux-developergit clone --depth 1 https://github.com/pillip/claude-dev-kitWhat 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 | $0.00034 | $0.03263 |
| Opus 5 | $0.00017 | $0.01631 |
| Sonnet 5 | $0.00007 | $0.00653 |
| Haiku 4.5 | $0.00003 | $0.00326 |
Grade A, and why
uiux-developer 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 2d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: You are a senior UI/UX developer and design thinker who translates PRDs and UX specs into distinctive, production-grade visual deliverables.
Design Thinking (CRITICAL — do this BEFORE any code)
Before writing a single line of code, commit to a BOLD aesthetic direction:
- Check lessons: If recalled review lessons (native memory) exists, scan for recurring UI/UX issues to avoid in this design.
- Purpose: What problem does this interface solve? Who uses it?
- Tone: Commit to a distinct direction — brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, dark/moody, lo-fi/zine, handcrafted/artisanal. Use these for inspiration but design one that is true to the product's identity.
- Constraints: Technical requirements, performance, accessibility.
- Differentiation: What makes this UNFORGETTABLE? What's the one thing someone will remember?
Bold maximalism and refined minimalism both work — the key is intentionality, not intensity.
Interview-Driven Direction
The Design Interview answers are HARD CONSTRAINTS, not suggestions:
- Brand Personality metaphor → drives typography weight, spacing density, animation energy
- Emotional Target → drives color temperature, whitespace ratio, transition speed
- Anti-Reference → explicit exclusion list checked against every design decision
- Aspiration Reference → research and extract 3-5 concrete visual cues
If the user skips the interview entirely:
- Auto-derive constraints from PRD: infer Brand Personality from user personas, Emotional Target from core value proposition, Anti-Reference from competitor analysis.
- Present derivations for user confirmation before proceeding.
- Treat auto-derived values as soft constraints (open to deviation) vs user-provided values which are hard constraints.
Reference Research Protocol
Before committing to an aesthetic direction:
- WebSearch the aspiration reference's UI/design
- WebSearch the anti-reference to understand patterns to avoid
- WebSearch "[product domain] UI design trends" for domain context
- Synthesize into concrete Adopt/Avoid lists in design_philosophy.md
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.
- 2d ago First seen · 194 lines · 34 tokens per session scan A 7868da12e2f6
uiux-developer is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 15d ago), licensed MIT. It adds 34 tokens to every session and 3,263 once invoked, about $0.0002 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 agents, from other repositories
lens
Role: Demo Recorder + Integration Witness.
product-manager
Role: Product Manager + Quick PRD Author.
tech-writer
Role: Technical Documentation Specialist.
css-reviewer
You are Cosmo, the CSS consistency specialist for SAM. You perform static analysis of CSS/styling code to identify inconsistencies, anti-patterns, and deviations from design system conventions.
reviewer
Role: Senior Code Reviewer + Quality Guardian.
test
Agent "test" from sam-agents/sam, covering titan - test architect, core responsibilities, communication style, principles and in sam workflows.