.claude

🚀 What Is This?

A drop-in configuration layer for Claude Code that transforms it from a capable AI assistant into an enterprise-grade development powerhouse.

One git clone gives you 123 domain skills, 86 specialist agents, 109 community marketplaces with 11,700+ additional skills, 30 slash commands, 8 lifecycle hooks, 12 MCP server configs, and the GSD (Get Shit Done) project management framework — all auto-activating based on what you're working on. No manual configuration required.

How it works: Describe what you want in plain language. The toolkit's dynamic router detects context from your prompt and loads the right skills, agents, rules, and checklists automatically. No slash commands needed (though they're available if you prefer).

Who it's for: Developers who use Claude Code and want deeper domain expertise, structured workflows, and quality guardrails without manual setup.

⚡ Quick Start

Use as GitHub Template (Recommended)

Click the green "Use this template" button at the top of this repo to create your own copy with a clean commit history. Then clone your new repo to ~/.claude/.

One-Line Install

Or clone directly if you prefer:

git clone --recurse-submodules https://github.com/travisjneuman/.claude.git ~/.claude

Manual Clone (if submodules fail)

git clone https://github.com/travisjneuman/.claude.git ~/.claude
cd ~/.claude
git submodule update --init --recursive

Verify Installation

# Start Claude Code — the toolkit loads automatically
claude

# Run diagnostics
/health-check

# Start a structured project with GSD (flagship workflow tool)
/gsd:new-project

That's it. The toolkit auto-activates from ~/.claude/ on every Claude Code session.

📦 What's Included

See MASTER_INDEX.md for the full listing with descriptions.

⚙️ How It Works

Dynamic Routing

Every prompt flows through a routing system that loads the best-fit resources on-demand — drawing from 123 built-in skills, 86 agents, 9 rules + 10 checklists, the GSD framework (57 commands), and 11,700+ community marketplace skills across 109 repos:

 Your prompt
     │
     ▼
 ┌──────────────────────────────┐
 │  CLAUDE.md Auto-Routing      │  ← Keyword detection table
 │  (always loaded)             │
 └──────────┬───────────────────┘
            │
   ┌────────┼────────┬──────────┬────────────┐
   ▼        ▼        ▼          ▼            ▼
┌──────┐ ┌──────┐ ┌──────┐ ┌───────┐ ┌────────────┐
│Skills│ │Rules │ │Agents│ │  GSD  │ │ Marketplace│
│(123) │ │& Chk │ │ (86) │ │  (57) │ │  110 repos│
│      │ │      │ │      │ │       │ │ 11,700+ more│
└──────┘ └──────┘ └──────┘ └───────┘ └────────────┘

Example: Type "review this React component for security issues" and the router automatically loads the React/TypeScript stack guide, the security hardening checklist, and spawns the code reviewer agent — without any slash commands.

Auto-Routing Table (from CLAUDE.md)

CLAUDE.md routes to docs and checklists on keyword match. Skills and agents auto-match from their descriptions — no explicit routing needed.

Hook Lifecycle

Hooks run automatically at key points in every session:

Session Start
  ├── Pull all repos (background, 60s timeout)
  └── Load previous session context

Every Prompt
  └── Inject git branch + status into context

Before Bash Commands
  ├── Block dangerous commands (rm -rf /, force push, etc.)
  └── Update doc counts before git commit

After File Edits
  └── Scan for leaked secrets

Session Stop
  └── Save session summary for next time

Session End (exit/clear/logout)
  └── Final session summary on exit

See hooks/README.md for the full hook reference.

🚢 GSD — Get Shit Done (Flagship)

The GSD Framework is the most powerful component of this toolkit. It transforms Claude Code from a task-runner into a full project management system with multi-phase planning, autonomous execution, verification loops, and session continuity.

Quick start:

/gsd:new-project          # Initialize a new project with deep context gathering
/gsd:plan-phase 1         # Create a detailed plan for phase 1
/gsd:execute-phase 1      # Execute with atomic commits and checkpoints
/gsd:verify-work           # Validate against success criteria
/gsd:next                  # Automatically advance to the next step

What makes it special:

• 30 slash commands covering the full project lifecycle — from idea capture to PR shipping
• Autonomous mode (/gsd:autonomous) — runs discuss → plan → execute per phase without interaction
• Session continuity — pause mid-phase, come back later, /gsd:resume-work picks up exactly where you left off
• Milestone tracking — multi-milestone projects with requirements tracing and coverage gates
• Agent orchestration — spawns specialized subagents for research, planning, execution, and verification

Key commands: /gsd:new-project, /gsd:progress, /gsd:next, /gsd:autonomous, /gsd:debug, /gsd:ship, /gsd:fast (quick inline tasks)

See docs/GSD-TUTORIAL.md for the full guide. GSD activates automatically when you describe multi-phase work — no need to invoke it manually.

🔑 Key Features

The toolkit aggregates 109 community skill repositories as git submodules in plugins/marketplaces/. All are read-only (fetch but never push). Skills span security (Trail of Bits), full-stack development, scientific computing, SAP/enterprise, Elixir, Terraform, creative writing, and more. Some marketplace repos are installed as plugins, making their agents, commands, and skills fully active in the routing system alongside built-in resources. Non-installed repos contribute discoverable skills via keyword search.

# Search marketplace skills
find ~/.claude/plugins/marketplaces -name "SKILL.md" | xargs grep -li "kubernetes"

# Update all marketplace repos
bash ~/.claude/_pull-all-repos.sh

See docs/MARKETPLACE-GUIDE.md for the full catalog.

The guard-dangerous.sh hook blocks dangerous commands before execution:

Additional safety: pre-write-validate.sh blocks writes to .env, .ssh, .gnupg, *.pem, and *.key files. secret-scan.sh scans every file edit for leaked API keys and tokens.

All hooks use a Node.js-based runner (hooks/run-hook.js) that resolves paths via os.homedir(). This avoids WSL path issues on Windows where ~ resolves to /root/ instead of the Windows user home.

On Windows, the runner explicitly prefers Git Bash (C:\Program Files\Git\usr\bin\bash.exe) over WSL bash to prevent drive mount failures on network drives.

For complex tasks, spawn multiple specialist agents to work in parallel:

• Code review from multiple angles — security, performance, tests
• Cross-layer features — frontend + backend + database agents
• Competing hypotheses — debug with parallel investigation

Agent types include architecture analysts, debugging specialists, performance optimizers, security auditors, test generators, and 50+ more. See agents/README.md.

12 MCP server configurations available (all disabled by default for token efficiency):

Enable on-demand via /mcp. See docs/MCP-SERVERS.md.

The toolkit maintains context between sessions automatically:

1. Session stop — session-stop-summary.sh saves working directory, branch, recent commits, active tasks, and pending todos to ~/.claude/last-session.md
2. Session start — session-start-context.sh injects the previous session context (if < 72 hours old)
3. Repo sync — session-start-pull.sh pulls all repos in the background on startup

🛠️ Configuration

Key Files

Common Customizations

Add your own project directories to auto-pull:

cp ~/.claude/.env.example ~/.claude/.env.local
# Edit CUSTOM_PROJECT_DIRS="/path/to/your/projects"

Switch action mode between proactive (default) and conservative — see docs/reference/workflows/action-policy.md.

Disable a hook — edit settings.json and remove the hook entry.

🖥️ Multi-Machine Setup

The toolkit uses a two-layer architecture:

1. This repo (~/.claude/) — Shared configuration, cloned on every machine
2. Machine-specific (.env.local, known_marketplaces.json) — Gitignored, per-device

New Device Setup

git clone --recurse-submodules https://github.com/travisjneuman/.claude.git ~/.claude
cp ~/.claude/.env.example ~/.claude/.env.local
# Edit .env.local with machine-specific paths
bash ~/.claude/scripts/fix-marketplace-paths.sh

See docs/NEW-DEVICE-SETUP.md for the full walkthrough.

💻 Platform Support

Requirements: Node.js (comes with Claude Code), Git, bash (Git Bash on Windows).

🆕 What's New

March 2026 — Comprehensive audit, GSD promotion, new repos, full domain coverage

• GSD (Get Shit Done) promoted: Now the flagship feature with dedicated README section, Quick Start integration, and routing diagram inclusion. 57 commands for full project lifecycle management.
• 6 new marketplace repos: blader/humanizer (11.4K stars), phuryn/pm-skills (8.3K stars, 100+ PM skills), Lum1104/Understand-Anything (6.6K stars), SawyerHood/dev-browser (4.9K stars), slavingia/skills (4.5K stars), millionco/expect (2.3K stars). Now 109 repos total.
• Submodule cleanup: Fixed orphaned directories, standardized all .gitmodules naming, verified no_push protection on 100% of marketplace repos
• Full domain coverage: New skills and agents for blockchain/Web3, data engineering, embedded/IoT, edge computing, compliance, and more
• New stack rules: Added Go, Rust, Java/Kotlin, C/C++, Swift/iOS, Flutter/Dart rules — path-scoped for zero token cost when not relevant
• Count synchronization: All counts now accurate across README, plugin.json, counts.json (127 skills, 86 agents, 94 commands, 110 repos)

Earlier in March 2026:

• Marketplace routing: All repos now surface naturally by domain — routing coverage went from 23% to 100%
• CLAUDE.md condensed: Auto-routing table reduced from 72 to 29 rows, saving ~600 tokens per conversation
• start-task trimmed: 156 → 82 lines, removed duplication with CLAUDE.md

See CHANGELOG.md for the full history.

📚 Documentation

💡 Philosophy

This toolkit follows three core principles:

1. Everything activates dynamically. Describe what you want — the system loads what's needed. No memorizing commands.
2. Token efficiency over completeness. Domain content loads on-demand, not upfront. Unused skills cost zero tokens.
3. Safety by default. Dangerous commands are blocked, secrets are scanned, protected files are guarded — all before you make a mistake.

Maintained by Travis Neuman · claude.travisjneuman.com · MIT License