claude-hangar

Claude Hangar — Development skill for Claude Code

Development community

Production-grade configuration management for Claude Code.

How to install Claude Hangar

This entry records only its repository, not the path inside it, so there is no exact command to give. Open claude-hangar/claude-hangar and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Hangar does

Production-grade configuration management for Claude Code. Hooks, agents, skills, multi-project orchestration.

Alternatives in Development

  • IPolloWork — Enterprise-grade, local-first Agent Workbench for people and agent teams 4.9k ★
  • Claude Hooks Mastery — 3,300+ Complete mastery guide for Claude Code hooks with production-ready scripts 3.4k ★
  • Meta Prompt Generator — You are a prompt engineering specialist who builds production-grade system 1.4k ★

README

Claude Hangar

Claude Hangar

Production-grade configuration management for Claude Code.
Hooks, agents, skills, multi-project orchestration — open source.

CI License: MIT Release


Why Claude Hangar?

Most Claude Code configs are personal dotfiles — useful to read, hard to reuse. Claude Hangar is different:

  • One command deploys a complete, tested setup to ~/.claude/
  • Multi-project orchestration — manage configs for multiple repos from one place
  • Modular stacks — pick only what you need (bash integrate.sh ) with --with/--without component control
  • Battle-tested hooks that prevent real incidents (secret leaks, destructive commands, context overflow)
  • 42 skills from project scanning to pre-PR verification, context optimization, session recap, effort tuning, stack lenses, and meta-governance
  • 31 lifecycle hooks with 4-level quality gates, config protection, MCP health checks, design quality guards, permission-request inspection, budget caps, and smart context preservation
  • 22 agents for specialized tasks (code review, TDD enforcement, performance analysis, MCP server development, autonomous workflows) — deep-reasoning agents run at effort: xhigh (v2.1.111+)
  • 20 governance rules (common + language-specific) always-on code quality
  • 3 context modes — dev, research, review
  • Cross-platform — Linux, m