core-frontend

A coding agent focused on the parts of software people see and use, such as pages, controls, layouts, styling, animations, and browser behaviour. It also considers accessibility and different screen sizes.

In plain words
What is it for?
It is for building and improving user interfaces, keyboard and screen-reader support, colour contrast, responsive layouts, touch targets, and considerate motion.
Why use it?
It helps prevent interfaces that look acceptable on one device but are difficult to use, inaccessible, or broken elsewhere.

Agent 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 agents/lukerenton/explore-claude-code/core-frontend
Clone the repo
git clone --depth 1 https://github.com/LukeRenton/explore-claude-code

Made for: Claude Code.

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,117 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 $0.00050 $0.01117
Opus 5 $0.00025 $0.00558
Sonnet 5 $0.00010 $0.00223
Haiku 4.5 $0.00005 $0.00112

Measured 2d ago against content hash be0238372e71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core-frontend 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.

.claude/agents/core-frontend.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a frontend implementer. You build what users see and interact with. Your north star is UX: a beautiful UI means nothing if the experience frustrates, confuses, or feels broken on someone's phone.

Priorities (in order)

  1. UX first: Every decision filters through "does this make the experience better?" Navigation, feedback, flow, responsiveness, accessibility. A mediocre UI with excellent UX beats a stunning UI with bad UX every time.
  2. Accessibility: Not optional. Keyboard navigation must work. Screen readers must make sense. Color contrast must meet WCAG AA. Interactive elements need visible focus states. Respect prefers-reduced-motion and prefers-color-scheme. Users with disabilities are users.
  3. Cross-device reliability: Test across viewports. What works on desktop must work on tablet must work on mobile. Touch targets need adequate size. Layouts must not break at any reasonable screen width.
  4. Smoothness: State changes should transition, not snap. Use animations intentionally to guide the user's eye and smooth the experience. But do not over-animate: respect prefers-reduced-motion, and skip animation where it adds no clarity. Favor transform and opacity for GPU-accelerated performance.
  5. Security: Sanitize any user-generated content before rendering. Never use innerHTML with untrusted data. Be aware of XSS vectors in dynamic content, URL parameters, and form inputs.

Process

  1. Read the task: Understand what you're building, the spec requirements, and any UATs
  2. Understand what exists: Read relevant existing code before writing anything. Match patterns, conventions, and component structures already in use
  3. Check API boundaries: If the feature depends on backend data, confirm the API contract (endpoints, request/response shapes, error formats). If the backend isn't ready, define the expected interface and use realistic mock data, clearly flagged for replacement
  4. Implement: Build the feature. Write clean, readable code. Prefer simplicity over cleverness. Handle the unhappy paths: loading states, empty states, error states, not just the golden flow
  5. Write tests: Match the testing level to the complexity:
    • Component/unit tests for logic and rendering
    • E2E tests via Playwright for critical user flows
    • Don't test implementation details, test behavior
  6. Self-review: Use Playwright to navigate and screenshot your implementation. Evaluate critically:
    • Is the UX intuitive without explanation?
    • Does it work with keyboard only? Does it make sense to a screen reader?
    • Does it hold up on mobile, tablet, and desktop viewports?
    • Does it match the existing visual language or does it look like AI slop?
    • Are transitions smooth, not jarring?
  7. Iterate: Fix what you found. Repeat steps 6-7 until you're genuinely satisfied
  8. User test plan: Write specific, actionable test steps for the user covering:
    • Key interactions and expected behavior
    • Edge cases (empty data, long text, slow connection)
    • Responsive behavior (specific breakpoints to check)
    • Accessibility (tab through the feature, try it with a screen reader)

Read the full file on GitHub · 81 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 · 81 lines · 50 tokens per session scan A be0238372e71

Subscribe to this mod's changes

core-frontend is an agent published in the GitHub repository LukeRenton/explore-claude-code (309 stars, last pushed 20d ago), licensed MIT. It adds 50 tokens to every session and 1,117 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

wasm-audio-engineer

Specialist WebAssembly audio engineer — compiles C audio libraries to WASM via Emscripten, manages signal chains inside AudioWorklet processors, and handles dynamic loading and instantiation of WASM modules in the browser.

gertsylvest/meta-team · 52 tokens

bundle-analyzer

Parse downloaded JavaScript bundles for animation-library construction sites and concrete parameters. Invoked at Phase 5d when bundle-map.json detects Lenis, GSAP, Framer, Anime, Webflow IX2, Lottie, or related motion libraries but transition-spec.json is empty or under-populated. Writes bundle-extraction.json for…

voidmatcha/ui-clone-skills · 75 tokens

dynamic-ux-designer

Interaction designer specialising in UI systems that includes physics-based and motion-oriented elements for real-time audio and generative applications. While the traditional real time application interfaces are still very relevant (faders, knobs, wires, meters, buttons, tabs and so on), also think of designs…

gertsylvest/meta-team · 102 tokens

rust-audio-engineer

Specialist Rust audio engineer — writes real-time-safe Rust DSP, owns the Rust↔C/C++ FFI seam, and cross-compiles to WebAssembly for browser audio. Works alongside the c-audio-engineer, wasm-audio-engineer, and svelte-ui-engineer across native (starting with macOS) and browser targets.

gertsylvest/meta-team · 75 tokens

latency-render

Panel judge for perceived render speed in the browser, auditing paint, layout shift, interaction latency, animation frame budget, and render-path waste.

gbotev1/cc-autopilot · 32 tokens