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 instructions/dev-lou/pixelpilot/uiux-ai-workflowgit clone --depth 1 https://github.com/dev-lou/PixelPilotWhat 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 | $0.02762 | $0.02762 |
| Opus 5 | $0.01381 | $0.01381 |
| Sonnet 5 | $0.00552 | $0.00552 |
| Haiku 4.5 | $0.00276 | $0.00276 |
Grade A, and why
PixelPilot uiux-ai-workflow.instructions.md 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI/UX AI Workflow 2026
AI-native engineering patterns: using AI tools (Copilot, Claude, Cursor, Lovable) as design-system-aware partners, not generic code generators. Token enforcement, boilerplate generation, prompt patterns, and review checklists.
CORE PRINCIPLE — Constrain the AI
An AI that doesn't know your design system will generate:
padding: 10pxinstead ofvar(--space-3)color: #3B82F6instead ofvar(--accent)border-radius: 8pxinstead ofvar(--radius-md)Interfont instead of your brand fontwindow.alert()instead of SweetAlert2
Solution: Prime every AI prompt with your system context. This skill IS that context.
STEP 1 — AI SYSTEM PROMPT (paste at start of every session)
You are a senior frontend engineer building [PROJECT NAME].
Design language: [LANGUAGE — e.g., Premium Modern]
Tech stack: [e.g., Next.js 14, Tailwind v4, TypeScript]
RULES — non-negotiable:
1. All spacing uses CSS tokens: var(--space-1) through var(--space-40). Never arbitrary px.
2. All colors use semantic tokens: var(--bg), var(--surface), var(--text), var(--accent), etc.
3. All fonts via: var(--font-display), var(--font-body), var(--font-mono).
4. Border radius via: var(--radius-sm), var(--radius-md), var(--radius-lg).
5. No window.alert/confirm/prompt — use the swal object from uiux-components.md.
6. Every component handles all 8 states (default/hover/focus/active/loading/disabled/error/success).
7. Every <img> has width, height, loading, alt.
8. No inline styles except for dynamic/computed values.
9. Mobile-first: start at 390px.
10. Dark mode via [data-theme="dark"] on <html>. Colors must work in both themes.
Token file excerpt:
[paste relevant section of tokens.css here]
STEP 2 — PROMPT PATTERNS
Generate a New Component
Create a [COMPONENT NAME] component for a [LANGUAGE] design system.
Requirements:
- Uses only var(--*) tokens for colors, spacing, radius
- Handles all 8 states: default, hover, focus, active, loading, disabled, error, success
- Mobile-first, responsive
- Accessible: correct ARIA roles, keyboard navigable
- Follows the button/card/form patterns in [uiux-interactive.md / uiux-states.md]
Output: HTML + CSS (no Tailwind). Use BEM-adjacent naming (.component__element--modifier).
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 · 340 lines · 2,762 tokens per session scan A 363cda6d54c9
PixelPilot uiux-ai-workflow.instructions.md is an instructions file published in the GitHub repository dev-lou/PixelPilot (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,762 tokens to every session, about $0.0138 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 2026-08-31.
Other instructions, from other repositories
ui-ux-design-pro-skill CLAUDE.md
Instructions for saifyxpro/ui-ux-design-pro-skill, covering project overview, cli commands, full design system generation (markdown output), search across all databases (sub-50ms) and audit ui code quality.
UIX CLAUDE.md
Instructions for Deepractice/UIX, covering uix project rules, design system: lucid ui, colors, forbidden and preferred patterns.
wonder-blocks AGENTS.md
Instructions for Khan/wonder-blocks, covering wonder blocks – agentic workflows & storybook mcp, installing the mcp (consumer setup), storybook mcp server, when it’s available and mcp endpoint.
openbridge-webcomponents watch-radial-instruments.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering watch & radial instruments, architecture overview, key principle: logic in watch.ts, instruments stay thin, shared sibling modules and layering & stacking pattern.
aicanvas CLAUDE.md
Instructions for uiNerd16/aicanvas, covering ai canvas — global rules, what this project is, how work is organized, secrets & credentials — this is an open-source repo and tech stack.
naksha-studio GEMINI.md
Instructions for Adityaraj0421/naksha-studio, covering naksha design team — gemini cli, project memory (v5), how to use, the team and core design (6 roles).