What is looksy CLAUDE.md?

Project instructions for looksy, a Node.js command-line tool that takes screenshots of web pages or HTML files for AI-assisted visual quality checks. They describe its technology, commands, workflows, and session-specific guidance.

Developing looksy, using its command-line options, following screenshot-review-iterate workflows, and deciding which project guidance applies to visual QA, CLI work, or refactoring.

They give the coding agent the project context needed to work consistently on the screenshot tool and its visual-review process.

How atre/looksy configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to atre/looksy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/atre/looksy/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/atre/looksy

Made for: Claude Code.

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/instructions/atre/looksy/claude-md.svg)](https://agentmods.dev/instructions/atre/looksy/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/atre/looksy/claude-md"><img src="https://agentmods.dev/badge/instructions/atre/looksy/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 756 This file is loaded in full into every session.

When invoked 756 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00756	$0.00756
Opus 5	$0.00378	$0.00378
Sonnet 5	$0.00151	$0.00151
Haiku 4.5	$0.00076	$0.00076

Measured 5d ago against content hash b3af038c871b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

looksy CLAUDE.md 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 5d 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.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Looksy — Claude Code Project Config

What This Is

A standalone CLI screenshot tool for AI-driven visual QA. Point it at any URL or HTML file, it screenshots it, AI reads the image, and iterates on design. Closes the visual feedback loop.

Project-agnostic. Works with Astro, Next.js, plain HTML, deployed sites, local dev servers — anything with a URL.

Tech Stack

Runtime: Node.js (ES modules, TypeScript)
Screenshot engine: Playwright (Chromium only)
Diff engine: pngjs (pixel-level comparison)
Output: PNG to ~/.looksy/ (configurable via LOOKSY_DIR env var)
Testing: Vitest (540 tests)
Distribution: npm package + global CLI binary (looksy)
Config: CLI flags only, no config files

AI Iteration Workflow

See the Workflows section of README.md for the full screenshot → AI review → iterate loop, token costs, and common workflows.

Session Types

Visual QA / design work: read the Workflows section of README.md
CLI behavior / flag reference: .claude/rules/flag-behavior.md auto-loads in src/
Pure refactor/test: neither needed

Core Commands

looksy <url>                    # Screenshot → ~/.looksy/preview.png
looksy <url> --design           # Full design review (meta + fonts + contrast + suggest)
looksy <url> --design-audit     # Pre-launch QA gate
looksy <url> --speed            # Performance audit

looksy --serve                  # Start persistent Chromium
looksy save <url> <name>        # Save visual baseline
looksy diff <url> <name>        # Visual regression (pixel diff)
looksy <url> --pages "/,/about" --design --batch-report  # Multi-page review

For complete flag reference, device options (mobile/tablet/sweep), analysis modes (contrast/a11y/perf), and assertion grammar, see .claude/rules/flag-behavior.md.

Key Rules

~17,000 lines across 76 source files, 540 tests
Strict flag parsing (unknown flags error; catches typos like --contrast-aa)
Default viewport: 1280x800 (desktop)
Exit code 0 on success, 1 on failure (budget fail, check fail, --fail-on-aa, guard fail)
No interactive prompts — pure CLI, batch-friendly
connectOrLaunch() transparently uses persistent --serve server if available
pMap() concurrency-limited Promise.all for parallel captures
safeRun() wraps each analysis module (failures reported, don't crash)
Security: CSS selector injection prevention, path traversal guards, TOCTOU race fixes, LOOKSY_DIR mode 0o700
Fleet contract + cross-tool backlog: ~/git/hub/TOOLS.md — read it before any release/push work (naming + repo-hygiene rules)

Read the full file on GitHub · 67 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.

5d ago First seen · 67 lines · 756 tokens per session scan A b3af038c871b

Subscribe to this mod's changes

looksy CLAUDE.md is an instructions file published in the GitHub repository atre/looksy (0 stars, last pushed 6d ago), licensed MIT. It adds 756 tokens to every session, about $0.0038 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

looksy: Instructions file for Claude Code