maket: Instructions file for Claude Code

CLAUDE.md

maket CLAUDE.md is an instructions file for Claude Code from ng-galien/maket. It costs 2,226 tokens per session, scanned A, original, MIT.

A set of instructions for developing Maket, a visual design tool for Claude that composes HTML and CSS documents with a live preview. It also covers assets, brand guidelines, PDF export, Gmail delivery, and the tool’s development setup.

In plain words
What is it for?
Use it when changing Maket, running its development or quality checks, working with its HTTP-based MCP server, or adding services, tools, and routes.
Why use it?
It gives contributors the project’s required development commands and architectural rules, including how dependencies are supplied and separated.

Instructions file for Claude Code

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

This is ng-galien/maket's own configuration. It tells Claude Code how to work on maket 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 maket configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ng-galien/maket. 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/ng-galien/maket/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ng-galien/maket

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 maket CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ng-galien/maket/claude-md.svg)](https://agentmods.dev/instructions/ng-galien/maket/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ng-galien/maket/claude-md"><img src="https://agentmods.dev/badge/instructions/ng-galien/maket/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,226 This file is loaded in full into every session.
When invoked 2,226 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 $0.02226 $0.02226
Opus 5 $0.01113 $0.01113
Sonnet 5 $0.00445 $0.00445
Haiku 4.5 $0.00223 $0.00223

Measured 8d ago against content hash 5975d5df538a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

maket 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maket

Visual design tool for Claude — compose HTML/CSS documents with live preview, manage assets, apply brand chartes, export PDF, send via Gmail. MCP server exposed over Streamable HTTP at POST /mcp.

Quickstart

npm run dev       # server --watch + Vite HMR (the one you want 95 % of the time)
npm run dev:watch # server --watch + vite build --watch → public/ (prod-like preview on :24843)
npm run quality   # lint + typecheck + test — same gate as pre-commit
npm run lint:fix  # biome check --write

Node >=22. The server must be running before Claude Code connects (MCP is HTTP-based). The human usually runs it themselves; don't spawn a second dev server.

Coding principles

These aren't style preferences — they're the invariants the codebase depends on. Breaking any of them reliably breaks boot, tests, or the refactor safety net.

Dependency injection via Awilix — no exceptions

  • Every service, tool pack, and HTTP route is a factory registered in bootstrap.ts. Consumers resolve by destructured param name. No module-level singletons, no new, no direct imports of concrete implementations.
  • Interface first — declare export interface Foo { … } above createFoo. Consumers type against the interface; the factory implements it.
  • Factories over classes everywhere — no class keyword in domain code (DocumentStore is the lone exception — a legitimate DB wrapper). Private state lives in factory closures.
  • PROXY destructure trap — every destructured name on deps triggers a container lookup. Put optional test overrides on a separate opts arg (see LayoutService, PdfService).
  • Container self-referencebootstrap.ts registers container: asValue(container) so factories that need the container itself (createMcpRoutermountTools) resolve it via DI.

Separation of concerns is hard-enforced

  • If you catch yourself adding a runtime field to a persistence type (the old Document._pending shape), that's a new service. Persistence models hold persistent state; transient state gets its own home. packages/server/src/services/pending.ts is the template — factory + interface + private closures + bus-driven side effects.
  • No deprecation shims — when moving state, remove the old field in the same diff and migrate every call site. "No baby-step migrations."

Read the full file on GitHub · 106 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 · 106 lines · 2,226 tokens per session scan A 5975d5df538a

Subscribe to this mod's changes

maket CLAUDE.md is an instructions file published in the GitHub repository ng-galien/maket (19 stars, last pushed 9d ago), licensed MIT. It adds 2,226 tokens to every session, about $0.0111 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 2026-08-30.

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

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