claude-web-animations: Instructions file for Claude Code

CLAUDE.md

claude-web-animations CLAUDE.md is an instructions file for Claude Code from TommyChryst/claude-web-animations. It costs 1,465 tokens per session, scanned C, original, MIT.

A web-design instruction guide for Claude Code that requires checking rendered pages with screenshots before and after visual changes, on both desktop and mobile.

In plain words
What is it for?
Use it when changing web pages or components, checking responsive layouts, or verifying that a visual fix did not create a regression.
Why use it?
It catches layout and visual problems that are easy to miss when reviewing code alone.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is TommyChryst/claude-web-animations's own configuration. It tells Claude Code how to work on claude-web-animations itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-web-animations configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TommyChryst/claude-web-animations. 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/TommyChryst/claude-web-animations/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/TommyChryst/claude-web-animations

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.

agentmods badge for claude-web-animations CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tommychryst/claude-web-animations/claude-md/github.svg)](https://agentmods.dev/instructions/tommychryst/claude-web-animations/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tommychryst/claude-web-animations/claude-md"><img src="https://agentmods.dev/badge/instructions/tommychryst/claude-web-animations/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-web-animations CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tommychryst/claude-web-animations/claude-md"><img src="https://agentmods.dev/badge/instructions/tommychryst/claude-web-animations/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,465 This file is loaded in full into every session.
When invoked 1,465 The same file — it is already loaded in full.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01465 $0.01465
Opus 5 $0.00732 $0.00732
Sonnet 5 $0.00293 $0.00293
Haiku 4.5 $0.00146 $0.00146

Measured 9d ago against content hash 46be57b9192d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

claude-web-animations CLAUDE.md scanned grade C with 1 finding 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 9d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Never auto-delete this folder.** The user clears it with `rm -rf .screenshots/` whenever they want.
CLAUDE.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Web Design

A general operating manual for any web design project. Project-specific details (stack, brand, file structure) belong in a separate CLAUDE.md layered on top of this one.


Non-negotiables

  1. Two-pass screenshot verification for every visual change. Reading code is not seeing the result.
  2. Parallel execution for independent file work — components, styles, tests, and stories ship in one batch.
  3. Use the design tools you actually have. See the Tools section below before defaulting to "I'll just write it blind."

Two-pass screenshot workflow

Whenever you make a visual change, add a component, or are asked to evaluate how something looks, screenshot the rendered output twice.

Pass 1 — Baseline. Render the current state. Capture at desktop (1440×900) and mobile (390×844). Write 3–5 specific observations: what works, what breaks, what feels off. This pass is diagnostic — do not skip to fixing.

Pass 2 — Verification. Apply the change. Re-screenshot at the same viewports as Pass 1. Compare directly. Did the fix land? Any regressions? If Pass 2 doesn't resolve what Pass 1 revealed, iterate — don't ship.

When this is required: after creating or modifying any component, after the user says "this doesn't look right," before declaring any task complete, and any time you're evaluating your own visual work.

Screenshot storage (mandatory)

All screenshots go in .screenshots/ at the project root. This folder is disposable and user-owned.

  • Add .screenshots/ to .gitignore on first use.
  • One subfolder per task: .screenshots/<task-slug>/
  • Filename format: pass-<1|2>-<viewport>-<timestamp>.png
    • Example: .screenshots/hero-redesign/pass-2-mobile-2026-04-24T14-31.png
  • Never overwrite — timestamps preserve iteration history.
  • Never auto-delete this folder. The user clears it with rm -rf .screenshots/ whenever they want.
  • Create the folder if it doesn't exist before taking the first shot of a session.
  • Never save screenshots anywhere else (not src/, not public/, not the project root).

Read the full file on GitHub · 116 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. 9d ago First seen · 116 lines · 1,465 tokens per session scan C 46be57b9192d

Subscribe to this mod's changes

claude-web-animations CLAUDE.md is an instructions file published in the GitHub repository TommyChryst/claude-web-animations (45 stars, last pushed 4mo ago), licensed MIT. It adds 1,465 tokens to every session, about $0.0073 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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 · 5,153 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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens