brandkit-mcp: Instructions file for Claude Code

CLAUDE.md

brandkit-mcp CLAUDE.md is an instructions file for Claude Code from ejwhite7/brandkit-mcp. It costs 1,859 tokens per session, scanned A, original, MIT.

A project guide for BrandKit MCP, a TypeScript server that gives AI tools access to a company’s written and visual brand rules. MCP is a standard way for AI tools to use external data and actions.

In plain words
What is it for?
Use it when working on BrandKit MCP or building branded digital and marketing assets with an AI coding agent.
Why use it?
It helps a coding agent understand the project structure and follow the brand’s language and visual guidelines when creating websites, apps, or marketing materials.

Instructions file for Claude Code

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

This is ejwhite7/brandkit-mcp's own configuration. It tells Claude Code how to work on brandkit-mcp 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 brandkit-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ejwhite7/brandkit-mcp. 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/ejwhite7/brandkit-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ejwhite7/brandkit-mcp

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 brandkit-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ejwhite7/brandkit-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ejwhite7/brandkit-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ejwhite7/brandkit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ejwhite7/brandkit-mcp/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 brandkit-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ejwhite7/brandkit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ejwhite7/brandkit-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,859 This file is loaded in full into every session.
When invoked 1,859 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 $0.01859 $0.01859
Opus 5 $0.00929 $0.00929
Sonnet 5 $0.00372 $0.00372
Haiku 4.5 $0.00186 $0.00186

Measured 8d ago against content hash a349c1fc54be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

brandkit-mcp 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 · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md -- BrandKit MCP

What is this file? This is the project intelligence document for BrandKit MCP. It tells Claude (and any other LLM-based coding agent) everything it needs to know to work effectively in this codebase.


Project Overview

BrandKit MCP is an open-source TypeScript server that exposes a company's complete brand atomic system -- verbal identity and visual identity -- to Claude and other AI tools via the Model Context Protocol (MCP).

The v2 atom-typed layout is the canonical model. The brand root contains two trees: agent/verbal/ (language identity) and agent/visual/ (visual identity), plus a human-authored taste primer at magic_trick.md and a human/ directory for PDF materials the MCP intentionally ignores.

The goal: when an LLM helps build a website, app, or marketing asset, it has instant structured access to the exact brand language and visual rules it needs -- including the brand's instincts, not just its specs.

Key Concepts

Term Meaning
Atomic system The full v2 layout under <brand-root>/: readme, magic_trick, human/, agent/.
Verbal Brand language: positioning, audience, messaging, differentiation, concepts, voice. Single source of truth -- no context overrides.
Visual Brand visual atoms: colors_and_type, fonts, assets, components, tokens, motion. Context overrides live under artifacts/.
Context base, web, or product. Visual content can be overridden per context; verbal cannot.
Artifact A context-specific visual override layer (agent/visual/artifacts/{web,product}/).
Magic trick Human-authored taste primer at <brand-root>/magic_trick.md. Read by creative/verbal tools and injected into their responses. Never written by AI.
Taste primer The _taste_primer field added by creative/verbal tools, carrying magic_trick.md verbatim.
Token specimen One markdown file per token in agent/visual/tokens/. Frontmatter carries the canonical value.
MCP Tool A function exposed over the Model Context Protocol that an LLM can call.
MCP Resource A static or dynamic data endpoint exposed as a brand:// URI.

Read the full file on GitHub · 167 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 First seen · 167 lines · 1,859 tokens per session scan A a349c1fc54be

Subscribe to this mod's changes

brandkit-mcp CLAUDE.md is an instructions file published in the GitHub repository ejwhite7/brandkit-mcp (4 stars, last pushed 10d ago), licensed MIT. It adds 1,859 tokens to every session, about $0.0093 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 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens