frontend-ui-workflow

frontend-ui-workflow is a skill for Claude Code, Codex from Daaaaave/agentic-workspace-core. It costs 85 tokens per session (3,087 once invoked), scanned A, original, MIT.

A workflow for building and reviewing website and app interfaces, including pages, forms, dashboards, and navigation. It focuses on visual consistency, ease of use, screen-size support, accessibility, and checking the result in the running app.

In plain words
What is it for?
Use it when creating, redesigning, polishing, or reviewing frontend screens and components, including implementations based on Figma designs or screenshots.
Why use it?
It helps prevent interfaces that look inconsistent, work poorly on some screens, or are difficult to use with accessibility tools. It also keeps changes aligned with the product’s existing design system.

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/daaaaave/agentic-workspace-core/frontend-ui-workflow
Any agent
npx skills add Daaaaave/agentic-workspace-core --skill frontend-ui-workflow
Clone the repo
git clone --depth 1 https://github.com/Daaaaave/agentic-workspace-core

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for frontend-ui-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/daaaaave/agentic-workspace-core/frontend-ui-workflow.svg)](https://agentmods.dev/skills/daaaaave/agentic-workspace-core/frontend-ui-workflow)
Your own site
<a href="https://agentmods.dev/skills/daaaaave/agentic-workspace-core/frontend-ui-workflow"><img src="https://agentmods.dev/badge/skills/daaaaave/agentic-workspace-core/frontend-ui-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,087 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 $0.00085 $0.03087
Opus 5 $0.00043 $0.01543
Sonnet 5 $0.00017 $0.00617
Haiku 4.5 $0.00009 $0.00309

Measured 5d ago against content hash c94c80b782b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-ui-workflow 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 5d 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.

payload/.agents/skills/frontend-ui-workflow/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend UI Workflow

Goal

Ship UI that is product-grounded, tasteful for its audience, accessible, responsive, consistent with local components/tokens, and verified in the running app.

Principles

  • UI quality includes design-system fit, hierarchy, states, responsive behavior, accessibility, and runtime evidence.
  • Default to production-grade UI work. For non-trivial visual changes, run the full loop: local system, product fit, correct owner, states, responsive behavior, accessibility, and running-app evidence.
  • Strong UI needs a clear product-fit point of view carried through composition, typography, spacing, color, surface/background, assets, and motion.
  • Prefer the smallest coherent change that preserves the product's visual system.
  • If a fix belongs in a shared component, token, layout primitive, or repeated pattern, update that owner or state the scope expansion before widening.
  • Existing product decisions beat generic taste rules. Improve within them unless the task is a redesign or migration.

Use When

  • Building or changing a page, screen, component, app shell, form, dashboard, landing page, onboarding flow, settings surface, empty state, navigation pattern, or marketing surface.
  • Changing layout, spacing, typography, color, motion, hierarchy, interaction states, responsive behavior, accessibility, or visible UI behavior.
  • Redesigning, polishing, improving taste, reducing generic AI output, or fixing "something looks off."
  • Reviewing frontend code or rendered UI for design-system drift, visual regressions, responsive risk, state coverage, accessibility, or component architecture.
  • Implementing from Figma, screenshots, URLs, brand references, product mockups, or an existing design system.
  • Repairing frontend bugs where the cause or fix affects layout, state rendering, browser behavior, accessibility, or shared components.

Do Not Use When

  • The task is backend-only, data-only, infrastructure-only, CLI-only, or documentation-only.
  • The user asks only for external research; use research-to-knowledge.
  • The user asks to create or change a skill; use write-agent-skill.
  • The user asks only to inspect or update durable project knowledge; use project-knowledge.
  • The user asks only for temporary transfer state; use write-agent-handoff.
  • The edit is copy-only with no layout, state, accessibility, interaction, or visual-system risk.

Read the full file on GitHub · 219 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. 5d ago First seen · 219 lines · 85 tokens per session scan A c94c80b782b8

Subscribe to this mod's changes

frontend-ui-workflow is a skill published in the GitHub repository Daaaaave/agentic-workspace-core (6 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 3,087 once invoked, about $0.0004 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.