Back to directory

My Claude Code Project's Starter Settings

A starter template of CLAUDE.md memory-bank files, hooks and slash commands for Claude Code projects, offered with three CLAUDE.md templates that follow a dual-memory, progressive-disclosure design.

My Claude Code Project's Starter Settings

This repository provides starter settings for Claude Code projects: a CLAUDE.md "memory bank" system of files meant to keep context across many chat sessions, plus example hooks and slash commands. It ships three CLAUDE.md templates built around progressive disclosure and a dual-memory architecture, along with a migration guide for moving an existing CLAUDE.md to one of the new templates while keeping its project-specific content.

The README itself is provided in four alternate versions generated with Claude Code: the original, a progressive-disclosure guide split into beginner, intermediate and advanced sections, a task-based guide, and a chapter-based technical reference manual.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.