PixelPilot uiux-library-research.instructions.md

A research process for choosing and evaluating modern front-end libraries, which are reusable software packages for building web interfaces.

In plain words
What is it for?
Use it when comparing libraries for React, Vue, or plain JavaScript projects, or when checking whether an existing library recommendation is outdated.
Why use it?
It gives library choices a consistent basis by considering the project’s framework, design needs, performance, accessibility, usage, documentation, and licence.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/dev-lou/pixelpilot/uiux-library-research
Clone the repo
git clone --depth 1 https://github.com/dev-lou/PixelPilot

Made for: GitHub Copilot.

Per session 605 This file is loaded in full into every session.
When invoked 605 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00605 $0.00605
Opus 5 $0.00302 $0.00302
Sonnet 5 $0.00121 $0.00121
Haiku 4.5 $0.00060 $0.00060

Measured 2d ago against content hash d7520b819271, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

PixelPilot uiux-library-research.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.

vscode/.github/instructions/uiux-library-research.instructions.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI/UX Library Research 2026

Research process for defining requirements, searching for options, evaluating candidates, and providing recommendations.


1. WHEN TO USE THIS SKILL

  • The user asks for a library recommendation.
  • Existing skills reference a potentially outdated library.
  • A new project requirement emerges that isn't covered by existing skills.

2. RESEARCH PROCESS

Step 1: Define Requirements

  • What is the core problem?
  • What is the tech stack (React, Vue, Vanilla JS)?
  • What is the design language?
  • What are the performance and accessibility needs?

Step 2: Search for 2026 Options

  • Use search tool with queries like: "best [category] library 2026", "modern [category] react library", "[category] alternatives to [old-library]".
  • Look for GitHub repositories, npm packages, and community discussions.

Step 3: Evaluate Candidates

  • GitHub Stars: Community popularity.
  • npm Downloads: Real-world usage.
  • Bundle Size: Impact on performance.
  • Framework Support: Compatibility with the project's stack.
  • Performance: Benchmark data (if available).
  • License: MIT, Apache 2.0, etc.
  • Documentation: Quality and clarity of examples.

3. PROVIDE A RECOMMENDATION

Top 2-3 options, each with a "best for" use case.

Library Best For Pros Cons
Library A Large apps Feature-rich, well-documented Heavy bundle size
Library B Small apps Lightweight, fast Limited features
Library C Experimental Cutting-edge features Potential instability

4. UPDATING SKILL FILES

If a library becomes a new industry standard:

  • Propose updating the relevant skill file (e.g., uiux-admin-dashboard.md).
  • Include the new library in the "Decision Guide" or "Recommended Libraries" section.
  • Provide a code example for the new library.

5. EXAMPLE RESEARCH TASK

Task: Find a modern 2026 library for data visualization in React.

Read the full file on GitHub · 74 lines

Changes

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.

  1. 2d ago First seen · 74 lines · 605 tokens per session scan A d7520b819271

Subscribe to this mod's changes

PixelPilot uiux-library-research.instructions.md is an instructions file published in the GitHub repository dev-lou/PixelPilot (2 stars, last pushed 4mo ago), licensed MIT. It adds 605 tokens to every session, about $0.0030 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.