</>MCP Agents Market
Plugin

claude-code-infrastructure-showcase

by diet10310kTypeScriptUpdated 2026-07-13

Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents

Claude CodeCodex

claude-code-infrastructure-showcase is a production-tested reference library for building sophisticated Claude Code infrastructure with auto-activating skills, hooks, and specialized agents. Born from six months of managing complex TypeScript microservices, it solves the core problem that skills don't activate automatically by providing a hooks-based system that analyzes prompts and suggests relevant skills contextually. The showcase includes modular skill patterns, AI-powered classification, session documentation systems, and eight specialized agents for tasks like architecture review and refactoring. Developers can integrate the infrastructure in 15-30 minutes using the setup wizard or manual installation.

Key Features

Auto-activating skills via UserPromptSubmit hooks that analyze prompts and file context to suggest relevant skills automatically
AI-powered skill classification with fallback to regex matching, supporting Gemini, OpenAI, Anthropic, and local Ollama models
Modular skill pattern with progressive disclosure keeping files under 500 lines to avoid context limits
Two-try blocking model via PreToolUse hooks that enforces mandatory skill activation before code edits
Production-tested skills for backend (Express/Prisma), frontend (React/MUI), error tracking (Sentry), and skill development
Eight specialized agents for complex tasks including code architecture review, refactoring, debugging, and documentation
Dev docs pattern that preserves project context across Claude Code session resets
Cross-agent support for Codex CLI with shared hooks, skills, and state tracking

Use Cases

  • 01Automatically activating React component development guidelines when editing frontend files
  • 02Enforcing backend API patterns when creating Express routes or Prisma repositories
  • 03Maintaining consistent error tracking practices across a microservices architecture
  • 04Preserving development context and decisions across Claude Code session resets
  • 05Using specialized agents to review code architecture or plan refactoring strategies
  • 06Building custom skills that auto-activate based on file patterns or prompt intent

Related Plugins

View more

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Plugin216.1k

claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Plugin95k

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Plugin84.9k

rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Plugin82.1k

claude-code-infrastructure-showcase — FAQ

What is claude-code-infrastructure-showcase?+

It's a reference library of production-tested Claude Code infrastructure including hooks that auto-activate skills, modular skill patterns, specialized agents, and session documentation systems. It's designed to be copied into your own projects, not used as a standalone application.

How do I install claude-code-infrastructure-showcase in my project?+

Clone the repository, then run the setup wizard with 'npx tsx setup.ts ~/your-project' which copies the .claude/ directory, detects your tech stack, configures activation modes, and verifies the installation. Alternatively, manually copy the .claude/ directory and run 'npm install' in .claude/hooks/.

Which AI clients work with this infrastructure?+

Primarily designed for Claude Code, with full cross-agent support for Codex CLI. The skills follow the Agent Skills standard, making them compatible with 30+ tools that support the standard.

Do I need API keys to use the skill auto-activation?+

No, the default mode uses regex and keyword matching which is free and works offline. AI-powered classification is optional and supports free tiers from Gemini or local Ollama models, with paid options for OpenAI and Anthropic.

What are the prerequisites for installation?+

Node.js 18+ (20+ recommended), npm, macOS/Linux/WSL2 (hooks are bash scripts), and optionally jq for Stop hooks. Windows users must use WSL2 since plain cmd/PowerShell won't run the bash-based hooks.

Is claude-code-infrastructure-showcase free to use?+

Yes, it's released under the MIT License for free commercial and personal use. Optional AI classification features may incur costs depending on your chosen provider, though Gemini's free tier and local Ollama are zero-cost options.

How do I install claude-code-infrastructure-showcase?+

Open the source repository on GitHub and follow its README. claude-code-infrastructure-showcase is a plugin — MCP Agents Market links you directly to the official repo.

Is claude-code-infrastructure-showcase free?+

claude-code-infrastructure-showcase is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Developer Tools PluginsProductivity & Workflow PluginsCode Review PluginsBest MCP ServersBest SkillsBest AgentsTop rated listingsClaude Code toolsBrowse all categories