A tool for saving browsable versions of a website's built user interface. Each saved version has a permanent local address and can be compared with other versions side by side.

Use it after changing frontend components, styles, layouts, pages, or themes to save a snapshot, view its local URL, take screenshots, and compare saved versions.

It prevents visual changes from being lost and makes it easier to inspect how the interface changed from one iteration to the next.

ui-snapshot — Skill for Claude Code by vvek475

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 vvek475/uiver-plugin

Claude Code

/plugin install uiver

Made for: Claude Code.

Or install uiver, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vvek475/uiver-plugin/ui-snapshot.svg)](https://agentmods.dev/skills/vvek475/uiver-plugin/ui-snapshot)

Your own site

<a href="https://agentmods.dev/skills/vvek475/uiver-plugin/ui-snapshot"><img src="https://agentmods.dev/badge/skills/vvek475/uiver-plugin/ui-snapshot.svg" alt="Measured on agentmods" height="20"></a>

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 705 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.

Model	Per session	Once invoked
Fable 5.1	$0.00101	$0.00705
Opus 5	$0.00051	$0.00352
Sonnet 5	$0.00020	$0.00141
Haiku 4.5	$0.00010	$0.00071

Measured 6d ago against content hash 95265dad1a27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ui-snapshot 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.

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/ui-snapshot/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Snapshot (uiver)

uiver stores immutable, fully browsable versions of a site's built output in a local content-addressed store (~/.uiver). Each version gets a permanent local URL and appears in a dashboard where the user can compare versions side by side.

Prefer the MCP tools

If the uiver MCP tools are available (ui_snapshot, ui_get_url, ui_list_versions, ui_screenshot, ...), use them instead of the CLI — same capabilities, structured results.

Locating the CLI (fallback)

If command -v uiver succeeds, use uiver.
Otherwise use the copy bundled with this plugin: node "$CLAUDE_PLUGIN_ROOT/bin/uiver.js" (this plugin ships the full tool).

After finishing a UI change

Make sure there is built output. If the project builds to dist/, build/, out/, or _site/, and the existing build is stale, run the project's build first. Plain static sites (an index.html at the root) need no build.
Snapshot it:
```
uiver snap [dir] \
  --title "<3–6 word label for what changed visually>" \
  --prompt "<the user request or task that produced this change>"
```
- Omit [dir] to auto-detect dist/, build/, out/, _site/, or an index.html in the current directory.
- --title should describe the visual change ("hero full-bleed video"), not the code change.
- Add --pin for milestones the user explicitly wants to keep — pinned versions are never auto-cleaned.
- If nothing changed since the last snapshot, the command reports "unchanged" and creates nothing. That is fine — do not retry with --force.
Include the printed version id and URL in your completion message so the user can open it.

Other operations

uiver list — list stored versions for this project.
uiver label [id] "<new title>" [--pin] — retitle (defaults to latest).
uiver open — open the comparison dashboard (starts the server if needed).
uiver export <id> / uiver import <file>.uiver — share a version across machines as a single portable bundle file.

Read the full file on GitHub · 62 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.

6d ago First seen · 62 lines · 101 tokens per session scan A 95265dad1a27

Subscribe to this mod's changes

ui-snapshot is a skill published in the GitHub repository vvek475/uiver-plugin (0 stars, last pushed 21d ago), licensed MIT. It adds 101 tokens to every session and 705 once invoked, about $0.0005 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.

Claude Code Frontend mcp ui-versioning visual diff

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

prototype-web

A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.

nexu-io/html-anything · 24 tokens

menu-transitions-rtl

Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…

asmyshlyaev177/react-horizontal-scrolling-menu · 137 tokens

vite

Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps with Vite.

antfu/skills · 49 tokens