frontend-design

A guide for designing and implementing usable frontend interfaces such as product screens, dashboards, and tools. It covers matching existing app conventions, responsive layouts, interactions, and browser-based visual checks.

In plain words
What is it for?
Use it for new UI screens, dashboard work, redesigns, frontend polish, responsive fixes, and visual quality checks.
Why use it?
It helps turn a design request into a working interface that fits its product context and catches layout or usability problems before delivery.

Skill for Claude CodeCodex

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 skills/codeinfinity1/stram/frontend-design
Any agent
npx skills add CodeInfinity1/Stram --skill frontend-design
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 401 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 $0.00026 $0.00401
Opus 5 $0.00013 $0.00200
Sonnet 5 $0.00005 $0.00080
Haiku 4.5 $0.00003 $0.00040

Measured 2d ago against content hash ae7ec2f77293, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-design 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.

skills/browser-web/frontend-design/SKILL.md · 67 lines

What it actually says

Frontend Design

Purpose

Build usable interfaces, not placeholder pages. This skill guides product screens, dashboards, tools, and frontend changes with empathy, domain fit, and verification.

When To Use

Use for UI builds, redesigns, frontend polish, app screens, visual QA, responsive layout, and product-flow improvements.

Inputs And Evidence

  • Product domain, audience, existing design system, screenshots, current UI code, and interaction goals.
  • Browser observations, screenshots, and test results.

Tool Map

  • read_file
  • search_workspace
  • browser_live_open
  • browser_live_observe
  • browser_live_screenshot
  • live-browser-testing
  • codebase-inspection

Workflow

  1. Inspect existing frontend patterns before designing.
  2. Match density, tone, layout, and controls to the domain.
  3. Build the actual usable screen first, not a marketing shell.
  4. Keep interactions discoverable and ergonomic.
  5. Verify in browser with screenshots/observations.
  6. Fix responsive text/layout overlap before calling done.

Native Implementation Boundaries

  • Use repo-native frontend code and Stram browser tools.
  • Do not import Anthropic frontend-design or external reference design code.
  • Generated visual references may inspire, but implementation must be project-owned.

Safety And Approval

  • Avoid hiding important actions.
  • Do not add unrelated dependencies without approval.
  • Preserve existing design conventions unless the task asks for a redesign.

Verification

  • Browser evidence should prove the UI renders.
  • Check desktop/mobile where relevant.
  • Report any unverified viewports or interactions.

Failure Modes

  • Generic landing-page output for a tool/app.
  • Pretty but unusable controls.
  • No real browser verification.

References

  • Shortlist item: frontend-design.
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 · 67 lines · 26 tokens per session scan A ae7ec2f77293

Subscribe to this mod's changes

frontend-design is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 26 tokens to every session and 401 once invoked, about $0.0001 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.