project-memory

Initialize and maintain project memory files under docs/project_notes.

46|8|Updated Jan 22, 2026
One-click install
npx skills add https://github.com/SpillwaveSolutions/code_agent_context_hooks --skill project-memory-spillwavesolutions
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: project-memory
Source: https://github.com/SpillwaveSolutions/code_agent_context_hooks/tree/main/.opencode/skill/project-memory
Command: npx skills add https://github.com/SpillwaveSolutions/code_agent_context_hooks --skill project-memory-spillwavesolutions

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill helps teams establish and maintain a structured project memory system that persists across AI tools and coding sessions.

Core Features & Use Cases

  • Creates and maintains memory files in docs/project_notes/ (bugs.md, decisions.md, key_facts.md, issues.md) and configures CLAUDE.md and AGENTS.md for memory-aware workflows.
  • Enables cross-tool memory: Claude Code, Cursor, Copilot, and other agents can reference past decisions, bugs, and configurations to prevent duplication and drift.
  • Provides a templated, human-readable format for recurring entries (bugs, ADRs, facts, work logs).

Quick Start

In Claude Code, type /project-memory to initialize memory infrastructure in your project.

Frequently Asked Questions about project-memory

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

FAQPage Schema
How do I preserve project knowledge across AI coding tools and sessions?

To preserve project knowledge across AI coding tools and sessions, you can establish a structured memory system using CLAUDE.md and AGENTS.md. This logs decisions, bugs, and facts to prevent duplication and drift across Claude Code, Cursor, and Copilot.

What's the best way to document recurring bugs and architecture decisions for AI agents?

Documenting recurring bugs and architecture decisions for AI agents is best handled by maintaining templated memory files in a docs/project_notes directory. This provides a human-readable format for logging bugs, ADRs, and key facts that agents can reference.

How do I configure CLAUDE.md and AGENTS.md for memory-aware workflows?

You configure CLAUDE.md and AGENTS.md for memory-aware workflows by initializing a project memory infrastructure that points to structured notes. This setup allows agents to reference past work logs and decisions during active coding sessions.

Can I use a shared project memory system across Claude Code and Cursor?

Yes, you can use a shared project memory system across Claude Code and Cursor. By storing memory files under docs/project_notes, multiple AI tools can reference the same past decisions, bugs, and configurations to prevent drift.

When do I need to initialize a project memory system?

You need to initialize a project memory system when starting new projects, documenting recurring bugs, or logging completed work. This ensures that structured knowledge is captured from the beginning for future AI coding sessions.

What files are created when initializing a project memory structure?

Initializing a project memory structure creates memory files in docs/project_notes, specifically bugs.md, decisions.md, key_facts.md, and issues.md. It also configures CLAUDE.md and AGENTS.md to enable cross-tool memory references.