speckit.frontend

speckit.frontend is a skill for Claude Code, Codex from wedabro/bro-skills. It costs 31 tokens per session (1,559 once invoked), scanned A, original, MIT.

A set of instructions for building production-ready frontend interfaces from approved requirements and API contracts. It covers typed data, accessible interactions, responsive layouts, loading and error states, and performance.

In plain words
What is it for?
Use it to implement frontend features, inspect existing page patterns and design tokens, connect components to APIs and caches, handle permissions and empty states, and coordinate with backend, design, security, and testing work.
Why use it?
It helps keep new interface work consistent with an existing design system and reliable across screen sizes. It also clarifies which project files, shared components, data rules, and related specialists should be checked before coding.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to implement frontend features, inspect existing page patterns and design tokens, connect components to APIs and caches, handle permissions and empty states, and coordinate with backend, design, security, and testing work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wedabro/bro-skills/speckit.frontend
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.

Any agent
npx skills add wedabro/bro-skills --skill speckit.frontend
Clone the repo
git clone --depth 1 https://github.com/wedabro/bro-skills

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 speckit.frontend

README.md
[![agentmods](https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.frontend/github.svg)](https://agentmods.dev/skills/wedabro/bro-skills/speckit.frontend)
Your own site
<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.frontend"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.frontend/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for speckit.frontend

Your own site · 80×15
<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.frontend"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.frontend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,559 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00031 $0.01559
Opus 5 $0.00015 $0.00779
Sonnet 5 $0.00006 $0.00312
Haiku 4.5 $0.00003 $0.00156

Measured 10d ago against content hash 608122c9b2fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

speckit.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 10d 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.

.agents/skills/speckit.frontend/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mission

Turn approved UI requirements and API contracts into cohesive production UI. Honor .agents/knowledge_base/ui_ux_standards.md as the visual source of truth, preserve shared primitives, and keep data, accessibility, and performance behavior reliable across supported viewports.

Required Inputs

  • .agents/specs/[feature]/spec.md, plan.md, and tasks.md
  • .agents/knowledge_base/ui_ux_standards.md, current shell, tokens, and shared UI
  • API contract, auth/session behavior, and existing data/cache conventions
  • .agents/memory/constitution.md for ENV and Docker policy

Use speckit.uiux for new design-system decisions, speckit.backend for API contract changes, speckit.security for security review, and speckit.tester for broader test planning. Do not replace their ownership.

Protocol

0. Mandatory Preflight

  • Before writing code, inspect the current page family, shared layout, components, design tokens, theme, feature structure, rendering boundary, and API/data-cache conventions.
  • Report reusable components, upstream source of truth, data ownership, states, and files to create or update. Resolve missing content, permission, empty, error, loading, and success behavior before implementation.
  • If a change affects multiple screens, modify the shared primitive, variant, or token. Do not patch the same visual property page by page.

1. Layout and Component Architecture

  • Compose pages from the shared application shell, container, breadcrumb, page header, and content primitives. Same-type pages use the same structure, width, horizontal padding, and title placement.
  • Before creating a component, search for an existing primitive to reuse, extend with typed props/variants, or compose. When two components overlap by roughly 70% or more, prefer one shared component with variants.
  • Keep feature-only components, hooks, schemas, and API adapters within the feature. Promote a component only when multiple features use it; keep page files focused on composition and page-level data flow.
  • At roughly 250–300 lines, review a file and extract independent UI or logic. At the second repeated JSX, form, modal, state view, formatter, or API-error pattern, evaluate a component, hook, utility, config, schema, or service.
  • Use 100dvh rather than 100vh for viewport-sized mobile layouts. Use semantic HTML before ARIA and typed variants rather than style-only forks.

Read the full file on GitHub · 132 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. 10d ago First seen · 132 lines · 31 tokens per session scan A 608122c9b2fc

Subscribe to this mod's changes

speckit.frontend is a skill published in the GitHub repository wedabro/bro-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 31 tokens to every session and 1,559 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

developer-utilities-post-markdown

Convert a Markdown string to HTML. Useful for rendering user-submitted content, documentation previews, or README files.

bobadilla-tech/requiems-api-skills · 29 tokens

shopify-hydrogen

Hydrogen storefront implementation cookbooks. Some of the available recipes are: B2B Commerce, Bundles, Combined Listings, Custom Cart Method, Dynamic Content with Metaobjects, Express Server, Google Tag Manager Integration, Infinite Scroll, Legacy Customer Account Flow, Markets, Partytown + Google Tag Manager…

display-design-studio/skills · 106 tokens

gsap-plugins

Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG…

display-design-studio/skills · 91 tokens

shopify-pos-ui

Build retail point-of-sale applications using Shopify's POS UI components. These components provide a consistent and familiar interface for POS applications. POS UI Extensions also supports scaffolding new POS extensions using Shopify CLI commands. Keywords: POS, Retail, smart grid.

display-design-studio/skills · 53 tokens

gsap-core

Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia() (responsive, prefers-reduced-motion). Use when the user asks for a JavaScript animation library, animation in React/Vue/vanilla, GSAP tweens, easing, basic animation, responsive or reduced-motion…

display-design-studio/skills · 128 tokens

gsap-scrolltrigger

Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…

display-design-studio/skills · 68 tokens