visual-qa

visual-qa is a skill for Claude Code, Codex from atre/looksy. It costs 115 tokens per session (1,183 once invoked), scanned A, original, MIT.

A screenshot-based workflow for checking how rendered web pages look and behave. It uses the looksy command-line tool to capture pages, review them with AI, compare versions, and check items such as contrast or horizontal scrolling.

In plain words
What is it for?
Reviewing UI changes in a browser, comparing before-and-after screenshots, checking WCAG contrast and other page conditions, auditing performance, and checking multiple sites.
Why use it?
It helps find visual and accessibility problems that ordinary code tests may miss, and supports checking whether a change altered the page.

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/atre/looksy/visual-qa
Any agent
npx skills add atre/looksy --skill visual-qa
Clone the repo
git clone --depth 1 https://github.com/atre/looksy

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 visual-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/atre/looksy/visual-qa.svg)](https://agentmods.dev/skills/atre/looksy/visual-qa)
Your own site
<a href="https://agentmods.dev/skills/atre/looksy/visual-qa"><img src="https://agentmods.dev/badge/skills/atre/looksy/visual-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,183 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 $0.00115 $0.01183
Opus 5 $0.00057 $0.00592
Sonnet 5 $0.00023 $0.00237
Haiku 4.5 $0.00012 $0.00118

Measured 3d ago against content hash 932ec5d7f71f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-qa 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 3d 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/visual-qa/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual QA Workflow (looksy)

Screenshots show THAT something looks wrong; the sidecar (--meta/--compact) shows WHY (font-size, padding, colors, contrast). Full flag reference: ~/git/looksy/.claude/rules/flag-behavior.md. Off PATH → node ~/git/looksy/bin/looksy.js.

Core loop

looksy --serve                                       # once; detached, idempotent (--serve-stop to kill)
looksy <url> --design --name baseline                # --full --meta --compact --fonts --css-vars --contrast --suggest (~1k tokens)
[make changes]
looksy <url> --design --name v1
looksy <url> --diff-inline /tmp/looksy/preview-baseline.png   # pixel side-by-side → preview-diff.png
looksy <url> --delta                                 # ~80 tokens: metadata diff vs previous capture
looksy <url> --check "contrast:aa, no-hscroll, text:Expected"  # ~50 tokens, exit 1 on fail

--name/-o/--suffix force the PNG even in text-only modes (--report, --check). Stale DNS after a cutover: --host-resolver domain:ip.

Cost / mode picker

Mode Tokens Use
--check "…" ~50 assertion pass/fail (CI, hooks)
--report / --delta ~100 / ~80 text-only summary / changed props only
--design ~1,000 design review
--design-audit ~1,200 pre-launch gate: + --seo --schema --font-sources --responsive-check --check "no generator, self-hosted-fonts, contrast:aa"
--speed ~2,500 perf: perf/network/coverage/bundles/images/compression/third-party/cache/critical-path/hints/server-timing/image-optimizer

Fleet / batch

looksy fleet https://a.com https://b.com --design-audit -q   # N URLs, shared browser, batch-report.md, exit 1 on AA fail
looksy fleet --design-audit                                  # no URLs → ./fleet.yaml (domains × pages; --fleet <path> to override)
looksy fleet --brief                                         # red-only ≤10 lines: `✗ <url> — HTTP 404, hscroll +21px, 2 AA fail` | `✓ N URLs clean`
looksy fleet https://a.com https://b.com -o out/             # -o dir/ → one preview-<slug>.png + sidecar per URL (else last URL wins)
looksy <url> --pages "/,/pricing,/about" --design --consistency --batch-report   # same-domain, cross-page consistency
looksy <url> --links --links-allow "linkedin.com,x.com"      # dead links; allow-list hosts → `unverifiable`, not dead

Read the full file on GitHub · 59 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. 3d ago First seen · 59 lines · 115 tokens per session scan A 932ec5d7f71f

Subscribe to this mod's changes

visual-qa is a skill published in the GitHub repository atre/looksy (0 stars, last pushed 4d ago), licensed MIT. It adds 115 tokens to every session and 1,183 once invoked, about $0.0006 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

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…

vercel-labs/agent-browser · 112 tokens

browserwing-executor

Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.

MemTensor/MemOS · 42 tokens

ce-polish

Polish a working feature through user-directed live browser feedback. Use when a functional feature needs focused UX refinement before shipping.

EveryInc/compound-engineering-plugin · 28 tokens

chrome-cdp

Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…

mattzcarey/shippie · 91 tokens

agent-browser

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection.

UnicomAI/wanwu · 21 tokens

html-game-generator

Build a complete, polished, production-quality browser game inside a single self-contained HTML file using only vanilla HTML, CSS and JavaScript — no frameworks, no libraries, no external assets. Use this skill whenever the user asks for a game, a playable demo, a prototype, an interactive toy, or anything "inspired…

buildfastwithai/gen-ai-experiments · 195 tokens