danielrosehill/Claude-Code-Projects-Index

An index of my Claude Code related repos including a wide variety of starter templates for using Claude Code for common and more imaginative purposes!

What it solves

It solves the problem of figuring out how to use Claude Code (Anthropic's agentic AI command-line tool) for tasks beyond software development. Instead of starting from scratch, users can browse and reuse pre-built "agent workspaces" — self-contained repositories that turn a terminal into a conversational interface for specific activities like legal research, system administration, health documentation, or even book writing.

How it works

The index organizes dozens of repositories by category. Each repository is described as either an agent workspace (a pre-configured repo that uses Claude Code as a UI for a specific workflow), a template (a forkable starting point), or just non-code tooling. The workspaces share a common pattern: they use a defined folder structure, a CLAUDE.md file for agent instructions, slash commands, and MCP configurations. The author has also consolidated the tooling into 28 "cluster plugins" that install domain-specific commands and can provision a scaffold on demand. A companion plugin, the Marketplace Guide, lets you query the full marketplace by theme (like Israel & Hebrew, homelab, or Linux desktop) directly through Claude Code's chat.

Who it's for

It's for anyone already using Claude Code — or interested in agentic AI CLIs — who wants to apply it to a long tail of non-coding use cases, such as purchase decision-making, KDE Plasma desktop management, legal case file organization, or personal therapy tracking. It's also for developers looking for maintainable, reproducible ways to scaffold new agent-driven projects using templates and plugins rather than building everything manually.

Highlights

  • Curated by a human (Daniel Rosehill), though the repos are generated with Claude Code's help.
  • Covers a wide range of domains: system admin, legal, health, finance, writing, and more.
  • Introduces the "Agent Workspace" pattern, where a Git repo itself acts as a complete workspace for any activity.
  • Includes 28 consolidated cluster plugins that ship domain primitives (commands, skills, agents) and provision project scaffolds on demand.
  • Offers a plugin marketplace and a Marketplace Guide plugin to browse it via Claude Code directly.
  • Comes with dedicated sub-indexes (e.g., Sysadmin Workspaces) and a chart tracking repository growth.

Related

  • Project
    rsmdt/the-startup

    The Agentic Startup is a multi-agent AI framework for Claude Code that enforces spec-driven development: you create detailed requirements and plans, then a team of specialized agents builds, tests, reviews, and documents your code with quality gates and parallel execution. It solves the problems of unclear requirements, context limits, and inconsistent code quality.

  • Project
    bex-co/bex

    An open-source, AI-native alternative to Render that allows developers and coding agents to deploy applications from Git to HTTPS on self-owned infrastructure.

  • Project
    microsoft/DebugMCP

    DebugMCP is a Microsoft‑maintained VS Code extension (and npm CLI) that runs a local MCP server exposing full debugger controls—start/stop, step, breakpoints, variable inspection, expression evaluation—to any MCP‑compatible AI coding assistant (Copilot, Claude Code, Codex, etc.). It works with all languages that have a VS Code Debug Adapter Protocol implementation and runs entirely locally for security.

  • Project
    karanb192/awesome-claude-skills

    A community directory of Claude Code skills — ready-made capabilities for tasks like testing, debugging, PDF extraction, and security that you can install and use with Claude.