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-architecturegit 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 | $0.03018 | $0.03018 |
| Opus 5 | $0.01509 | $0.01509 |
| Sonnet 5 | $0.00604 | $0.00604 |
| Haiku 4.5 | $0.00302 | $0.00302 |
Grade A, and why
PixelPilot uiux-architecture.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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI/UX Architecture 2026
Feature-Sliced Design, component architecture, state management (Signals vs Context), folder structure, and code organization patterns for scalable UI systems. Prevents spaghetti code in large applications.
DECISION TREE — Architecture Tier
Project size?
├─ Small (1 dev, <10 routes, <3 months)
│ └─ Flat structure: /components, /hooks, /pages — that's enough
├─ Medium (2–5 devs, 10–30 routes)
│ └─ Layer by type: /features, /shared, /pages
└─ Large (5+ devs, 30+ routes, long-lived)
└─ Feature-Sliced Design (FSD) — see below
STATE MANAGEMENT DECISION TREE
Use this tree to choose the right state management tool for your specific use case:
- Local Component State (e.g., form input, toggle, local counter)
- Tool:
useState/useReducer - Why: Simplest, built-in, no overhead.
- Tool:
- Shared UI State (e.g., theme, current user, small group of components)
- Tool:
useContext - Why: Built-in, avoids prop drilling for shared static or low-frequency data.
- Tool:
- Global App State (e.g., cart, multi-step workflow, complex cross-page data)
- Tool:
Zustand - Why: Global, simple API, excellent performance, supports persistence (localStorage).
- Tool:
- High-Frequency / Fine-Grained State (e.g., real-time dashboards, complex animations)
- Tool:
Signals(Preact Signals in React) - Why: Fine-grained reactivity; only components reading the signal re-render. Massive performance gain.
- Tool:
- Server State (e.g., API responses, loading/error states, caching)
- Tool:
TanStack Query(React Query) - Why: Mandatory. Handles caching, revalidation, and loading states automatically.
- Tool:
FEATURE-SLICED DESIGN (FSD) — Large Apps
FSD organizes by business domain, not file type. Prevents import cycles. Rule: each layer can only import from layers below it.
src/
├─ app/ (L1 — top) config, providers, global styles, router
├─ pages/ (L2) page components — compose features, no business logic
├─ widgets/ (L3) self-contained page sections (Header, Sidebar, PlayerBar)
├─ features/ (L4) user interactions (auth, cart, search, notifications)
├─ entities/ (L5) business objects (User, Product, Order)
└─ shared/ (L6 — bottom) UI kit, utils, API clients, hooks
├─ ui/ (Button, Input, Card — no business knowledge)
├─ api/ (base fetch client)
├─ lib/ (date, format, validate utils)
└─ config/ (env vars, constants)
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 · 369 lines · 3,018 tokens per session scan A bfd65681bd3d
PixelPilot uiux-architecture.instructions.md is an instructions file published in the GitHub repository dev-lou/PixelPilot (2 stars, last pushed 4mo ago), licensed MIT. It adds 3,018 tokens to every session, about $0.0151 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
arai CLAUDE.md
Instructions for taniwhaai/arai, covering claude.md — arai, commands, architecture, prompt-collector module (src/promptcollector.rs) and extending the match pipeline.
healthcare-agents AGENTS.md
Instructions for ajhcs/healthcare-agents, covering healthcare agents repository instructions, repository map, git workflow and self-improvement loop.
arai AGENTS.md
Instructions for taniwhaai/arai, covering agents.md — arai, core discipline (non-negotiable), taniwha / subagent rules, work style and tool usage.
shenzjd-skills CLAUDE.md
Claude Code instructions for wu529778790/shenzjd-skills, covering claude.md, project overview, commands, a single skill's unit test and architecture.
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.
syncai copilot-instructions.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.