Shareable instruction files for Cursor, Claude Code, Copilot, Windsurf, and more — installed alongside your existing agent rules.
Test Types (ALL required): 1. **Unit Tests** - Individual functions, utilities, components 2. **Integration Tests** - API endpoints, database operations 3. **E2E Tests** - Critical user flows (framework chosen per language)
Read [AGENTS.md](AGENTS.md) for repository work. For installation, follow [INSTALL.md](INSTALL.md): show only the target agent's supported options directly in the conversation and use its [selection procedure](INSTALL.md#choose-options), preferring native multi-select questions. Export a selection document only when requested.
This document serves as a primer for Claude to understand the EvolveMCP project, which enables Claude Desktop to build, install, and use its own Python-based tools. When starting a new session with this project, Claude should:
You are an AI coding assistant working with projects that use a structured context system for AI-assisted development. This system provides organized documentation, templates, and guidelines to ensure consistent and high-quality development.
> **Purpose**: This file guides AI assistants and developers working on HealthChain. It encodes coding standards, constraints, and workflows to keep architecture and domain judgment in human hands. It's a working document that will be updated as the project evolves.
vibecheck is a vibe-themed CLI tool for running language model evaluations. This is the open source CLI tool (MIT licensed) that connects to the vibecheck API at vibescheck.io. **Get your API key at [vibescheck.io](https://vibescheck.io)**