What is geeklego CLAUDE.md?

Repository instructions for GeekLego, an open-source React component library built around Tailwind CSS, ShadCN, and Radix UI, with a two-level design-token system.

Use them when building or modifying GeekLego components, design tokens, or the Token Editor.

They explain the current token architecture and the reference component so changes follow the repository's established rules.

How GeekyAnts/geeklego configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to GeekyAnts/geeklego. 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/GeekyAnts/geeklego/geeklego-v2-beta/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/GeekyAnts/geeklego

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/geekyants/geeklego/claude-md/github.svg)](https://agentmods.dev/instructions/geekyants/geeklego/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/geekyants/geeklego/claude-md"><img src="https://agentmods.dev/badge/instructions/geekyants/geeklego/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/geekyants/geeklego/claude-md"><img src="https://agentmods.dev/badge/instructions/geekyants/geeklego/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,756 This file is loaded in full into every session.

When invoked 6,756 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.

Model	Per session	Once invoked
Fable 5.1	$0.06756	$0.06756
Opus 5.5	$0.02702	$0.02702
Sonnet 5.5	$0.01351	$0.01351
Haiku 4.5	$0.00676	$0.00676

Measured 2mo ago against content hash aaa2a8f10753, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

geeklego 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 2mo 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 · 355 lines

How it starts

The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

This is the GeekLego v2 system: 2-tier tokens (primitives → semantics) + ShadCN/Radix components. It replaces the old 3-tier (primitive → semantic → component-token) architecture. The 2-tier cut has landed and the Token Editor app/ has been rebuilt on v2 — see "Repo state" below. The reference implementation for every v2 rule in this file is the Button slice at components/v2/Button/ — read it before building anything.

This file is the authoritative source for v2 rules. Read it together with the reference component above.

What is GeekLego (v2)?

GeekLego is an open-source, design-system-first React component library built on Tailwind CSS v4 + ShadCN/Radix UI.

It ships:

A 2-tier design system — design-system/v2/ — primitives (geeklego's brand palette/scales, unchanged) aliased to a standard ShadCN/Tailwind semantic vocabulary (--primary, --background, --border, --ring, …). Components consume the semantics directly.
A component library — components/v2/ — ShadCN-pattern React components (cva variants + cn() + Radix primitives) styled with standard semantic utilities (bg-primary text-primary-foreground).
An AI generation skill — component-builder-v2 — generates new v2 components following the rules below.
A token editor → cockpit (app/) — edit primitives + semantics, manage themes, export to CSS / IR / design.md. (Being adapted from 3-tier; see brief §4.)

Design-system-first means: the token system (primitives + semantics) is the source of truth. Components are an expression of it — you never hardcode a value or invent vocabulary. You consume the standard semantics, and only reach for namespaced --ext-* tokens for genuine brand-custom variants.

Why standard ShadCN vocabulary? Industry-standard, in every LLM's training set, native Tailwind v4 utilities, paste-and-go. The only geeklego-specific layer is the primitive palette (the brand seam) — the semantic interface is deliberately standard.

Read the full file on GitHub · 355 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.

2mo ago First seen · 355 lines · 6,756 tokens per session scan A aaa2a8f10753

Subscribe to this mod's changes

geeklego CLAUDE.md is an instructions file published in the GitHub repository GeekyAnts/geeklego (7 stars, last pushed 9d ago), licensed MIT. It adds 6,756 tokens to every session, about $0.0270 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 2026-08-31.

geeklego CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
geeklego CLAUDE.mdGeekyAnts/geeklego	Instructions file	7	9d ago	MIT	A	6,756	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

geeklego: Instructions file for Claude Code