ui-verify

ui-verify is a skill for Claude Code from iamcxa/kc-claude-plugins. It costs 80 tokens per session (2,244 once invoked), scanned A, original, MIT.

A browser-based checker for fixed visual properties in a web page, such as colors, sizes, and computed styles.

In plain words
What is it for?
It is for checking selected page elements, pseudo-elements, design tokens, dimensions, and temporary UI states against expected values.
Why use it?
It detects exact differences in a static interface that may not be obvious from behavior tests alone.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the e2e-pipeline plugin — 11 skills, 8 agents, 2 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add iamcxa/kc-claude-plugins
Claude Code
/plugin install e2e-pipeline

Made for: Claude Code.

Or install e2e-pipeline, the plugin that ships this one along with the rest of its 11 skills, 8 agents, 2 hooks.

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 ui-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/ui-verify.svg)](https://agentmods.dev/skills/iamcxa/kc-claude-plugins/ui-verify)
Your own site
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/ui-verify"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/ui-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,244 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 5.1 $0.00080 $0.02244
Opus 5 $0.00040 $0.01122
Sonnet 5 $0.00016 $0.00449
Haiku 4.5 $0.00008 $0.00224

Measured 6d ago against content hash 0a54122d4996, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ui-verify 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (bin/run.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

e2e-pipeline/skills/ui-verify/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Verify — Declarative UI Difference Check

Compare static UI properties (computed CSS values on known selectors) against expected tokens. Declarative YAML input, browser-driven via agent-browser, machine-judged pass/fail with report.

Role in the Pipeline

Skill What it compares Judgment
ui-verify (this) Static UI — computed styles, tokens, pseudo-elements, dimensions Machine (equality)
e2e-flow / e2e-test Dynamic behavior — navigation, state transitions, user actions Machine (flow asserts)
e2e-walkthrough Subjective visual QA, exploration, demo recording Human

If you need to check "did the sidebar bg change to #FAFAF8?" → ui-verify. If you need to check "clicking Submit navigates to /success?" → e2e-flow. If you need "does the new layout look right?" → e2e-walkthrough.

Scope

In scope:

  • Fixed selectors × fixed expected computed-style values
  • getComputedStyle(selector)[property] equality checks
  • Pseudo-element (::before, ::after) computed value checks
  • Optional pre-check setup actions (goto, click, wait) — needed when the target state is transient
  • Screenshot capture + pass/fail report

Out of scope (use agent-browser directly):

  • Dynamic queries (find elements with bg = X, walk parent chain, elementFromPoint)
  • Computed-style forensics across many candidate elements
  • CSS specificity wars / injected-style inspection
  • Any check where the selector is not known upfront

If the verification requires forensics → use agent-browser REPL-style. This skill is for cases where you already know WHICH element to check and WHAT value to expect.

Pipeline Context

/e2e-map       → mapping.yaml               (map UI + auth)
/ui-verify     → ui-verify.yaml + report    (check computed styles)
/e2e-flow      → flow.yaml                  (dynamic behavior)
/e2e-test      → flow replay + report

ui-verify reuses .claude/e2e/mappings/*.yaml for auth + base_url — same convention as the rest of the e2e-pipeline.

Read the full file on GitHub · 209 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 209 lines · 80 tokens per session scan A 0a54122d4996

Subscribe to this mod's changes

ui-verify is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 2,244 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.

Related

Other skills, from other repositories

Shade ShadCN install

Guardrails for running pnpm dlx shadcn@latest add in Shade — never overwrite existing components, fresh branch first, swap raw colours for semantic tokens after integrating. Trigger when the user proposes a shadcn add, or when a fresh ShadCN-shaped file lands in apps/shade/src/components/ui.

TryGhost/Ghost · 72 tokens

chakra-ui-builder

Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…

chakra-ui/chakra-ui · 214 tokens

frontend-visual-qa

Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…

daymade/claude-code-skills · 145 tokens

prototype-web

可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.

nexu-io/html-anything · 24 tokens

waitlist-page

【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.

nexu-io/html-anything · 25 tokens

design-frontend-dev

Clean Impeccable frontend design skill. Use when the user wants to design, redesign, critique, audit, polish, harden, optimize, adapt, clarify, colorize, animate, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, onboarding, empty states…

The-Vibe-Company/companion · 127 tokens