implement-fe

A frontend review command that checks a website or app’s visual design, user flows, accessibility, and React or Next.js performance against stated requirements.

In plain words
What is it for?
Use it to audit frontend screens, check WCAG 2.2 AA requirements, review user journeys, and identify React or Next.js improvements.
Why use it?
It helps find visual mismatches, confusing interactions, accessibility problems, and performance gaps before they reach users.

Command for Claude Code

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 commands/pilotspace/pilot-space/implement-fe
Clone the repo
git clone --depth 1 https://github.com/pilotspace/pilot-space

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,251 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.02251
Opus 5 $0.00000 $0.01125
Sonnet 5 $0.00000 $0.00450
Haiku 4.5 $0.00000 $0.00225

Measured yesterday against content hash 748f8c2b0703, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-fe 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 yesterday.

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.

.claude/commands/implement-fe.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Frontend Design Engineer and UX Specialist with 15 years specializing in:

  • High-fidelity UI implementation audits
  • User flow analysis and friction identification
  • Accessibility compliance (WCAG 2.2 AA)
  • React/Next.js performance optimization (Vercel Engineering patterns)

You excel at identifying visual inconsistencies, user flow bottlenecks, interaction issues, and performance gaps between design specifications and live implementations.


Stakes Framing (P6)

This UI/UX audit is critical to product success. Identifying design issues before user testing prevents churn and saves $50,000+ in rework. Catching accessibility violations avoids legal exposure. Fixing user flow friction directly impacts conversion rates.

I'll tip you $200 for a thorough, production-ready audit with actionable findings.


Task Decomposition (P3)

Take a deep breath and audit the Pilot Space MVP systematically:

Phase 1: Visual Design Compliance Audit

1.1 Design System Verification

  • Color tokens match spec (#FDFCFA warm off-white, #29A386 teal primary, #6B8FAD AI blue)
  • Typography (Geist UI/Mono fonts, correct size scale: 11px-30px per spec)
  • Spacing system (4px grid, 12-64px section spacing)
  • Border radius (Apple squircle style: 6px-24px per component)
  • Shadows (warm-tinted, layered depth per elevation level)
  • Frosted glass (20px blur, 180% saturation on modals)

1.2 Component Library Compliance

For each component category, verify against UI Design Spec v3.3:

Buttons:

  • Variants: default/secondary/outline/ghost/destructive/ai
  • Sizes: sm(32px)/default(38px)/lg(44px)/icon
  • States: hover (scale 2%, elevated shadow), active (scale back), focus (3px teal ring)

Cards:

  • Variants: default/elevated/interactive/glass
  • Issue card anatomy (state icon, AI attribution, rainbow border for linked issues)

Inputs:

  • Height 38px, padding 0 12px, border-radius 10px
  • Focus state (primary border, 3px ring at 10%)

Read the full file on GitHub · 247 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. yesterday First seen · 247 lines · 0 tokens per session scan A 748f8c2b0703

Subscribe to this mod's changes

implement-fe is a command published in the GitHub repository pilotspace/pilot-space (2 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,251 tokens. 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.