centminmod/my-claude-code-setup

Shared starter template configuration and CLAUDE.md memory bank system for Claude Code

What it solves

This project provides a structured configuration and template system to help Claude Code better retain context across multiple chat sessions. It solves the problem of AI "forgetfulness" by implementing a memory bank system that organizes project history, patterns, and decisions into dedicated files.

How it works

Users copy the provided templates into their project directory. The core component is the CLAUDE.md file, which acts as a central hub for the memory bank. When you run the /init command, Claude Code analyzes your codebase and populates these files. The setup includes advanced features like dual-memory architecture (combining shared git files with local memory), progressive disclosure to manage context window usage, and custom status lines to monitor token costs and progress in real-time.

Who it’s for

This is for developers who use Claude Code and want a more organized, persistent, and efficient AI coding experience. It is particularly useful for those managing complex projects who want to maintain consistent behavior and context across long-term development sessions.

Highlights

  • Includes three modernized CLAUDE.md templates based on official Anthropic best practices.
  • Provides a migration guide to update existing setups to the new memory bank architecture.
  • Offers shell functions for managing Git worktrees, allowing you to run multiple isolated AI coding sessions in parallel.
  • Includes configuration for custom status lines to track token usage, costs, and Git branch status directly in your terminal.
  • Supports modular documentation templates for specific platforms like Cloudflare, ClerkOS, and Convex.

Related

  • Project
    google/mantis

    Mantis is an open‑source, AI‑driven toolkit that automates security reviews of code. It uses LLM agents to build threat models, generate exploit tests, and suggest patches, all within a sandboxed, configurable workflow. The project is experimental and intended only for isolated environments; all findings require manual verification.

  • Project
    cisco-ai-defense/skill-scanner

    Skill Scanner is a Python‑based security scanner for AI agent “skills” (e.g., OpenAI Codex or Cursor agents). It combines static signatures, AST data‑flow analysis, and an optional LLM judge, with a CEL‑based decision layer, to detect prompt‑injection, data‑exfiltration, and malicious code patterns. It offers preset policies, CI/CD integration (SARIF, GitHub Actions, pre‑commit), and extensibility via custom rule packs and cloud‑LLM providers.

  • Project
    itayinbarr/little-coder

    A coding agent tuned for small local models that provides advanced planning, research, and implementation capabilities directly on a laptop.

  • Project
    brennercruvinel/CCPlugins

    CCPlugins provides 24 ready‑made Claude Code CLI commands (e.g., /cleanproject, /commit, /security-scan, /scaffold) that automate repetitive dev tasks, add git safety checkpoints, and deliver fast, deterministic results. Install with a one‑liner script; commands work on any language or OS and can be chained in CI/CD pipelines. The project is actively maintained and MIT‑licensed.