claude-code-project-memory

Configure CLAUDE.md project memory with a 4-tier hierarchy for monorepos.

73|16|Updated Nov 14, 2025
One-click install
npx skills add https://github.com/vasilyu1983/AI-Agents-public --skill claude-code-project-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-code-project-memory
Source: https://github.com/vasilyu1983/AI-Agents-public/tree/main/frameworks/claude-code-kit/framework/skills/claude-code-project-memory
Command: npx skills add https://github.com/vasilyu1983/AI-Agents-public --skill claude-code-project-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Maintains project context, conventions, and tribal knowledge for AI agents.

Core Features & Use Cases

  • CLAUDE.md generation: Architecture and conventions.
  • Memory templates: Key-files, dependencies, and web app context.
  • Handoff-ready: Ready-to-use project context for agents.

Quick Start

Generate CLAUDE.md for a new project with architecture and conventions.

Frequently Asked Questions about claude-code-project-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up project memory to persist context across Claude Code sessions?

Project memory persists context by configuring a CLAUDE.md file in your project root. This file stores architecture, conventions, and dependencies that Claude Code automatically loads in each session, eliminating the need to re-explain your project structure repeatedly.

Can I use a memory hierarchy for monorepos and multi-repo projects?

Yes. The 4-tier memory hierarchy supports enterprise, project, and user-level overrides with recursive on-demand loading. This structure lets you define shared conventions at the enterprise level while allowing individual projects and users to customize settings as needed.

What should I include in CLAUDE.md templates?

CLAUDE.md templates include key files, dependencies, development conventions, and web app context. These templates form the foundation for handoff-ready project context that new agents can reference immediately without manual setup.

How do quick-add memory commands speed up workflow with Claude Code?

Quick-add commands let you append conventions and context to your CLAUDE.md file without manual editing. This accelerates session management by capturing tribal knowledge, architectural decisions, and project-specific patterns as you work.

What's the best way to maintain architectural knowledge in a distributed team?

Store your architecture and conventions in CLAUDE.md at the enterprise or project level so all team members and AI agents access the same context. This centralizes tribal knowledge and ensures consistency across handoffs and onboarding.

Do I need existing documentation to generate a CLAUDE.md file?

No. You can generate CLAUDE.md from scratch for a new project by defining architecture and conventions incrementally. The framework supports building memory as your project evolves rather than requiring complete documentation upfront.