visual-diff

visual-diff is a skill for Claude Code, Codex from Houseofmvps/ultraship. It costs 39 tokens per session (732 once invoked), scanned A, original, MIT.

A browser-based check that compares screenshots of a website before and after a change. It uses Playwright to reveal visible differences across desktop, tablet, and mobile views.

In plain words
What is it for?
Use it to verify CSS changes, component refactors, or dependency upgrades have not changed the interface unexpectedly.
Why use it?
It helps catch layout and styling bugs that ordinary code checks may miss before they reach users.

Skill for Claude CodeCodex

Part of the ultraship plugin — 45 skills, 16 commands, 13 agents, 3 hooks, 2 MCP servers shipped together

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/houseofmvps/ultraship/visual-diff
Any agent
npx skills add Houseofmvps/ultraship --skill visual-diff
Clone the repo
git clone --depth 1 https://github.com/Houseofmvps/ultraship

Made for: Claude Code, Codex.

Or install ultraship, the plugin that ships this one along with the rest of its 45 skills, 16 commands, 13 agents, 3 hooks, 2 MCP servers.

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 visual-diff

README.md
[![agentmods](https://agentmods.dev/badge/skills/houseofmvps/ultraship/visual-diff.svg)](https://agentmods.dev/skills/houseofmvps/ultraship/visual-diff)
Your own site
<a href="https://agentmods.dev/skills/houseofmvps/ultraship/visual-diff"><img src="https://agentmods.dev/badge/skills/houseofmvps/ultraship/visual-diff.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 732 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 $0.00039 $0.00732
Opus 5 $0.00019 $0.00366
Sonnet 5 $0.00008 $0.00146
Haiku 4.5 $0.00004 $0.00073

Measured yesterday against content hash dfc0e64a3ddb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-diff 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 yesterday.

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/visual-diff/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Regression Testing

Automated screenshot comparison using Playwright. Catch visual bugs before they ship.

Process

Phase 1: Determine Test Scope

Ask the user:

  1. What URL(s) to test? (localhost, staging, or production)
  2. What changed? (CSS update, component refactor, dependency upgrade, etc.)

If the user already described what changed, skip asking.

Phase 2: Take "Before" Screenshots

If comparing against the current state (before making changes):

Use the Playwright MCP to capture screenshots:

  1. Navigate to the URL:

    • Use browser_navigate to go to the target URL
  2. Take full-page screenshot:

    • Use browser_take_screenshot to capture the current state
  3. Capture key viewports:

    • Desktop (1920x1080): browser_resize then browser_take_screenshot
    • Tablet (768x1024): browser_resize then browser_take_screenshot
    • Mobile (375x812): browser_resize then browser_take_screenshot
  4. Save screenshots with descriptive names noting they are "before" state.

Phase 3: Make Changes

Let the user make their changes, or make them yourself if that's the task.

Phase 4: Take "After" Screenshots

Repeat the same screenshot process for the same URLs and viewports.

Phase 5: Visual Comparison

Compare before and after screenshots:

  1. Layout shifts — did any elements move unexpectedly?
  2. Color changes — did colors, gradients, or shadows change?
  3. Typography — did font sizes, weights, or spacing change?
  4. Responsive issues — does it look correct on all viewports?
  5. Missing elements — did anything disappear?
  6. Overflow issues — is content clipping or overflowing?

Use browser_snapshot to get the accessibility tree and compare DOM structure between before/after.

Phase 6: Report

Present findings in a clear format:

No Visual Regressions Found:

  • "All pages look identical across desktop, tablet, and mobile viewports."

Regressions Detected: For each regression:

  • Page: URL where the issue appears
  • Viewport: Which screen size is affected
  • What changed: Description of the visual difference
  • Severity: Critical (broken layout), High (noticeable shift), Medium (minor difference), Low (pixel-level)
  • Suggested fix: How to resolve the regression

Read the full file on GitHub · 97 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. yesterday First seen · 97 lines · 39 tokens per session scan A dfc0e64a3ddb

Subscribe to this mod's changes

visual-diff is a skill published in the GitHub repository Houseofmvps/ultraship (121 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 732 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 2026-09-03.

Related

Other skills, from other repositories

aceternity-ui

100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.

secondsky/claude-skills · 48 tokens

ios-device-qa

Use when the user runs /ios-device-qa to drive a real iPhone over USB through a debug-bridge daemon and return a device QA report with verified interactions. Do not use for remote, credential, publish, deploy, or irreversible changes.

OutlineDriven/odin-claude-plugin · 55 tokens

xcode-simulator-testing

Use when asked to run /xcode-simulator-testing with a scheme name or current to build and launch an iOS app in a simulator and capture per-surface evidence. Not for project regeneration — use xcode-project-sync.

OutlineDriven/odin-claude-plugin · 52 tokens

possible-worlds-qa

Use when a product surface must be tested against extreme or hostile worlds rather than collect green checks. Completeness mode classifies every world against stated criteria and reports gaps; break mode names an expected break signal per world, captures proof artifacts, and escalates worlds that survive. Not for…

OutlineDriven/odin-claude-plugin · 86 tokens

run-smoke-tests

Use when asked to run smoke tests or verify a local build. Applies minimal fixes that unblock a stable passing result and reports flake risk honestly. Not for iterative bug fixing — use fix.

OutlineDriven/odin-claude-plugin · 43 tokens

browser-testing

Test and debug browser code with Chrome DevTools MCP. Use when building or debugging browser UI, inspecting the DOM, capturing console errors, analyzing network requests, or verifying visual output.

OutlineDriven/odin-claude-plugin · 39 tokens