wonder-blocks: Instructions file for Claude Code

CLAUDE.md

wonder-blocks CLAUDE.md is an instructions file for Claude Code from Khan/wonder-blocks. It costs 4,034 tokens per session, scanned A, original, MIT.

Technical and coding guidance for Khan Academy’s Wonder Blocks design system, a reusable set of interface components. It covers React, TypeScript, styling, state, testing, Storybook, and naming conventions.

In plain words
What is it for?
Use it when creating or changing Wonder Blocks components, hooks, styles, tests, Storybook examples, routes, or TypeScript interfaces.
Why use it?
It gives contributors the rules needed to extend shared components without breaking strict type checks, visual conventions, or the project’s testing setup.

Instructions file for Claude Code

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

This is Khan/wonder-blocks's own configuration. It tells Claude Code how to work on wonder-blocks 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 wonder-blocks configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Khan/wonder-blocks. 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/Khan/wonder-blocks/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Khan/wonder-blocks

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 wonder-blocks CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/khan/wonder-blocks/claude-md/github.svg)](https://agentmods.dev/instructions/khan/wonder-blocks/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/khan/wonder-blocks/claude-md"><img src="https://agentmods.dev/badge/instructions/khan/wonder-blocks/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 wonder-blocks CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/khan/wonder-blocks/claude-md"><img src="https://agentmods.dev/badge/instructions/khan/wonder-blocks/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,034 This file is loaded in full into every session.
When invoked 4,034 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04034 $0.04034
Opus 5.5 $0.01614 $0.01614
Sonnet 5.5 $0.00807 $0.00807
Haiku 4.5 $0.00403 $0.00403

Measured 8d ago against content hash b1bbfecb2a9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wonder-blocks 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 8d 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 · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wonder Blocks Design System

This file provides instructions for Claude when working on the Wonder Blocks design system codebase.

Technology Stack

  • Language: TypeScript (Strict mode enforced)
  • Framework: React (Functional Components and Hooks)
  • Styling: Aphrodite (aphrodite) for CSS-in-JS with Wonder Blocks tokens (@khanacademy/wonder-blocks-tokens)
  • State Management: Local state (useState) and React Context API (useContext)
  • Data Fetching: There should be no data fetching in the design system UI components
  • Routing: Design system components with link functionality should also support React-Router routes
  • Testing: Jest, React Testing Library (RTL), @testing-library/user-event, Storybook
  • Package Manager: pnpm

Coding Conventions

File & Export Naming

  • Use kebab-case for files and directories (e.g., activity-button.tsx, utils.ts)
  • Test files: *.test.ts(x)
  • Storybook files: *.stories.tsx
  • PascalCase for React components and types (e.g., Button, type ButtonProps)
  • camelCase for functions, variables, hooks (e.g., getButtonProps, useButtonFunctionality)

TypeScript

  • Use strict mode
  • Define clear interfaces/types. Use type for props and state, interface for shared structures where appropriate
  • Use utility types (Partial, Omit, Pick, Readonly, etc.)
  • Use the satisfies operator for type-safe object literals
  • Prefer type-only imports: import type {...} for types
  • Avoid any; use unknown or specific types instead

React

  • Imports: Always use import * as React from "react" (required for JSX transformation)
  • Use functional components and hooks (useState, useEffect, useContext, useCallback, useMemo)
  • Define explicit Props types with object destructuring. Pass complex objects/callbacks with stable references (useCallback, useMemo) if they are dependencies of effects or memoized children
  • Keep component state minimal. Lift state up when necessary
  • Provide stable key props for lists (use item IDs if available)
  • Build complex UI by composing smaller Wonder Blocks when possible
  • Use React.forwardRef when components need to expose DOM refs
  • Extract reusable logic into custom hooks (e.g., useFieldValidation, useIsMounted from @khanacademy/wonder-blocks-core)
  • Event Handlers: Internal handlers prefixed with handle (e.g., handleClick), callback props prefixed with on (e.g., onClick)
  • Don't use React.FC<Props>, use (props: Props) => instead
  • Avoid creating new class components

Read the full file on GitHub · 324 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. 8d ago Changed · +8 lines · +211 tokens per session b1bbfecb2a9c
  2. 2mo ago First seen · 316 lines · 3,823 tokens per session scan A e70379b60e56

Subscribe to this mod's changes

wonder-blocks CLAUDE.md is an instructions file published in the GitHub repository Khan/wonder-blocks (163 stars, last pushed yesterday), licensed MIT. It adds 4,034 tokens to every session, about $0.0161 per session on Opus 5.5. 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 2026-08-30.

Related

wonder-blocks CLAUDE.md compared with instructions from other repositories

wonder-blocks CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
wonder-blocks CLAUDE.mdKhan/wonder-blocksInstructions file163yesterdayMITA4,034Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode