What is projectx CLAUDE.md?

Project instructions for ProjectX, a full-stack online shop built as a monorepo, meaning one code repository containing several related applications and services.

Working on authentication, orders, products, React pages, databases, payments, email, background workflows, and shared development practices.

They give the coding agent the project's structure, tools, and service boundaries so changes fit the existing e-commerce system.

projectx CLAUDE.md — Instructions file by proyecto26

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/proyecto26/projectx/claude-md

Clone the repo

git clone --depth 1 https://github.com/proyecto26/projectx

Per session 1,379 This file is loaded in full into every session.

When invoked 1,379 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.01379	$0.01379
Opus 5	$0.00690	$0.00690
Sonnet 5	$0.00276	$0.00276
Haiku 4.5	$0.00138	$0.00138

Measured 3d ago against content hash 6bb6bf13963f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

projectx 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 3d 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 · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ProjectX - Full-Stack E-Commerce Platform

Project Overview

This is a modern full-stack e-commerce platform built with a microservices architecture using TypeScript throughout.

Tech Stack

Monorepo

Turborepo for build orchestration and caching
pnpm (v9.12.3) as package manager
Node.js v25

Backend (NestJS Microservices)

auth - Authentication service (JWT, Passport)
order - Order management with Temporal workflows
product - Product catalog service

Frontend

React Router v7 - Full-stack React with SSR
Tailwind CSS v4 with DaisyUI
TanStack Query for data fetching
Framer Motion for animations

Database

PostgreSQL with PostGIS extension
Prisma ORM (v7)

Workflow Orchestration

Temporal for durable execution

Payments

Stripe integration

Email

SendGrid with MJML templates

Spec-Driven Development

OpenSpec for structured AI-assisted development

Project Structure

projectx/
├── apps/
│   ├── auth/           # NestJS auth microservice
│   ├── order/          # NestJS order microservice
│   ├── product/        # NestJS product microservice
│   ├── storybook/      # Component documentation
│   └── web/            # React Router v7 frontend
├── packages/
│   ├── cli/            # ProjectX interactive CLI
│   ├── core/           # Shared NestJS modules
│   ├── db/             # Prisma schema and client
│   ├── email/          # Email templates (MJML + SendGrid)
│   ├── models/         # Shared TypeScript models
│   ├── payment/        # Stripe integration
│   ├── ui/             # React component library
│   └── workflows/      # Temporal workflow definitions
├── openspec/
│   ├── changes/        # Active OpenSpec changes (gitignored)
│   └── specs/          # Committed specifications
├── docs/               # Project documentation
└── docker-compose.yml

Common Commands

# Development
pnpm dev                    # Run all services in parallel
pnpm dev:web               # Run frontend only
pnpm dev:auth              # Run auth service only

# Building
pnpm build                 # Build all packages
pnpm build:web            # Build frontend

# Database
pnpm prisma:generate      # Generate Prisma client
pnpm prisma:migrate:dev   # Run migrations (dev)
pnpm prisma:seed          # Seed database

# Testing
pnpm test                  # Run all tests

# Linting
pnpm lint:fix             # Fix lint issues with Biome
pnpm check                # Run Biome check

# ProjectX CLI
pnpm cli                   # Interactive mode
pnpm cli generate service  # Create a basic NestJS microservice
pnpm cli generate temporal-service  # Create a Temporal-enabled service
pnpm cli generate workflow  # Add workflow to existing service
pnpm cli init              # Initialize/customize the project
pnpm cli info              # Display project information

# Code Generators (Turbo)
pnpm gen:service           # Basic NestJS service generator
pnpm gen:temporal-service  # Temporal NestJS service generator
pnpm gen:workflow          # Add workflow to existing service

# OpenSpec (Spec-Driven Development)
openspec new change "<name>"        # Create a new change
openspec status --change "<name>"   # Check change status
openspec instructions <id> --change "<name>"  # Get artifact instructions

Read the full file on GitHub · 173 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.

3d ago First seen · 173 lines · 1,379 tokens per session scan A 6bb6bf13963f

Subscribe to this mod's changes

projectx CLAUDE.md is an instructions file published in the GitHub repository proyecto26/projectx (83 stars, last pushed 4mo ago), licensed MIT. It adds 1,379 tokens to every session, about $0.0069 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.

Backend and APIs E-commerce event-driven-architecture event-driven-microservices full-stack full-stack-application full-stack-developer full-stack-development

projectx CLAUDE.md