Claude Code Arcane

437 skills, 109 agents, 17 hooks and 30 rules for Claude Code — selective deploy by profile.

A configuration harness installable via npx. Pick a profile that matches your stack and only the relevant tools get installed into your project's .claude/ directory.

Quick Start

# Navigate to your project
cd ~/projects/my-app

# Install a profile (no clone needed)
npx claude-code-arcane install backend-ts+agile

# Open Claude Code
claude

That's it. Your project now has skills, agents, hooks, rules, and permissions tailored for your stack.

How It Works

1. Profiles define what gets installed

Each profile is a YAML file that bundles skills, agents, rules, and permissions:

# profiles/backend-ts.yaml
name: backend-ts
category: backend
skills: [api-design, auth-strategy, jwt-strategy, ...]
rules:
  universal: [backend-code, api-code, migration-code]
agents: [engineering]
permissions:
  allow: ["Bash(npm *)", "Bash(docker ps*)"]

2. Combine profiles with +

All profiles are equal — there is no "base vs addon" distinction. Combine as many as you need:

npx claude-code-arcane install backend-ts+agile+testing

The installer merges all profiles, deduplicates skills, and installs only what's needed.

Not sure what to pick? Run install with no arguments to get an interactive picker: it detects your stack (Unity, Unreal, Flutter, Go, NestJS, Next.js, React Native, React, .NET, native Android/iOS...) and pre-selects the matching profiles, then lets you add more from a menu grouped by category. Power users can accept the detected suggestion with a single Enter — or skip the menu entirely with the a+b+c syntax above.

3. Core is always included

Every installation automatically loads core.yaml first:

• 21 essential skills (commit, create-pr, code-review, help, etc.)
• 15 lifecycle hooks (session start/stop, commit validation, secret scanning, etc.)
• 3 base rules (data-files, prototype-code, test-standards)
• 1 agent dir (quality)
• Security permissions (9 allow + 14 deny)

4. What gets generated

my-project/.claude/
├── settings.json          # Permissions + hooks + optional statusline
├── arcane-manifest.json   # Installation metadata (tracks what's installed)
├── statusline.sh          # Only if you used +statusline
├── hooks/                 # 14 lifecycle hooks
├── skills/                # Only your profile's skills
│   └── */SKILL.md         # Each skill = one directory
├── rules/                 # Stack-specific rules
├── agents/                # Agent dirs per profile
└── docs/                  # General documentation

CLI Commands

Install a profile

npx claude-code-arcane install backend-ts+agile     # Install profile combination
npx claude-code-arcane install                       # Show available profiles (interactive)
npx claude-code-arcane install unity-dev --dry-run   # Preview without installing

Add skills or profiles to an existing installation

npx claude-code-arcane add                           # Interactive picker (same wizard as install)
npx claude-code-arcane add api-design                # Add a single skill
npx claude-code-arcane add security-audit owasp      # Add multiple skills
npx claude-code-arcane add +security                 # Add an entire profile
npx claude-code-arcane add +database +testing        # Add multiple profiles

Without arguments, add opens the same interactive picker as install, restricted to what is not installed yet: profiles grouped by category, or individual skills searchable by name. Outside a TTY it prints the addable catalog instead.

Remove skills, profiles, or agents

npx claude-code-arcane remove api-design             # Remove a single skill
npx claude-code-arcane remove slack postman          # Remove multiple skills
npx claude-code-arcane remove +agile                 # Remove entire profile (skills + agents + rules)
npx claude-code-arcane remove +testing api-design    # Mix: remove a profile and a skill

When removing a profile, Arcane only deletes assets exclusive to that profile. Skills, agents, and rules shared with other active profiles are preserved.

Core skills (21) and the core profile cannot be removed.

Global hooks (worktree-isolation auto-apply)

npx claude-code-arcane global                        # Install global SessionStart hook
npx claude-code-arcane global --status               # Show global hooks status
npx claude-code-arcane global --remove               # Remove global hooks

Installs worktree-isolation scripts into ~/.claude/scripts/ and adds a SessionStart hook to ~/.claude/settings.json that auto-applies isolation on every new Claude Code session.

Other commands

npx claude-code-arcane list                          # List all profiles and skills
npx claude-code-arcane status                        # Show current installation
npx claude-code-arcane update                        # Check for updates
npx claude-code-arcane clean --force                 # Remove Arcane entirely from project

In-Session Skills (inside Claude Code)

Once installed, manage the installation from within a Claude Code session:

| Skill | Description | |-------|-------------| | /arcane-status | Show installed profiles, skills, rules, and agents | | /arcane-list | List everything available in Arcane (profiles + skills) | | /arcane-add <skill\|+profile> | Add skills or profiles without reinstalling | | /arcane-remove <skill\|+profile> | Remove skills, profiles and their agents/rules | | /arcane-clean | Uninstall Arcane from the project (asks confirmation) |

Examples from inside Claude Code

/arcane-add docker-setup              Add one skill
/arcane-add +security                 Add entire security profile
/arcane-remove +agile                 Remove agile profile + its exclusive skills/agents
/arcane-remove api-design slack       Remove specific skills
/arcane-status                        See what's installed
/arcane-list                          Browse what's available

Available Profiles

All profiles combine freely with + — there is no required "base". Grouped by category:

Backend

| Profile | Stack | Skills | Agents | |---------|-------|--------|--------| | backend-ts | Backend TypeScript — Fastify, Prisma, Zod, API design | 33 | engineering | | backend-go | Backend Go — Clean Arch, DB, auth, API, CI | 19 | engineering | | backend-dotnet | Backend .NET — ASP.NET Core, Vertical Slice/Clean, EF Core, JWT | 25 | engineering | | backend-nestjs | Backend NestJS — feature modules, DI, Prisma, JWT, microservices | 25 | engineering | | backend-nextjs | Next.js full-stack — App Router, RSC, Server Actions, SEO, AI SDK | 22 | engineering |

Frontend & Design

| Profile | Stack | Skills | Agents | |---------|-------|--------|--------| | frontend | React + Vite + TypeScript | 14 | engineering | | design | Figma, UX review, design system, handoff | 6 | product |

Mobile

| Profile | Stack | Skills | Agents | |---------|-------|--------|--------| | mobile | React Native + Expo + TypeScript | 12 | engineering | | flutter | Flutter + Dart cross-platform | 8 | engineering | | android-native | Kotlin + Jetpack Compose + Material Design 3 | 8 | engineering | | ios-native | Swift + UIKit/SwiftUI + Apple HIG | 8 | engineering |

Gamedev

| Profile | Stack | Skills | Agents | |---------|-------|--------|--------| | unity-dev | Unity programmer — C#, architecture, performance, builds | 25 | game | | unity-design | Game designer — GDDs, balance, art bible, playtesting | 17 | game | | meshy | 3D asset production with Meshy AI — credit-gated generation, single master + cheap derivatives, printability | 5 | — | | blender | Blender for game assets — tri budget and topology, materials with bake and color space, baked animation, validated export | 6 | — | | unreal-dev | Unreal Engine 5 programmer — C++, Blueprints, GAS, replication, rendering, packaging | 49 | game | | visual-novel | Visual novel developer — Ren'Py, narrative, branching | 17 | visualnovel, game | | audio | Game audio — direction, composition, sound design, middleware, VO, QA | 13 | audio |

Platform & Quality

| Profile | Adds | Skills | Agents | |---------|------|--------|--------| | infra | Terraform, observability, secrets, rollback, K8s | 17 | devops | | database | Indexing, migrations, seeding, replicas, optimization | 8 | — | | security | Audits, OWASP, secrets, backups | 5 | — | | testing | Contract, performance, regression, flakiness | 11 | quality | | ai | LLM cost optimization, RAG, ML, data engineering | 7 | ai |

Project Management

| Profile | Adds | Skills | Agents | |---------|------|--------|--------| | agile | Sprints, standups, retros, estimates | 10 | management, product | | jira | Jira via REST API — issues, sprints, boards | 3 | — | | clickup | ClickUp via MCP — tasks, docs, time tracking | 3 | — | | integrations | GitHub Projects, Slack, Postman | 3 | integrations |

Business

| Profile | Adds | Skills | Agents | |---------|------|--------|--------| | business | Contracts, customer success, revenue ops, sales | 4 | business | | clevel | C-suite advisors, board prep, strategic ops | 28 | clevel | | finance | Investment analysis, financial modeling, SaaS metrics | 3 | business | | marketing | Content, growth, SEO/CRO, strategy, analytics | 44 | marketing | | ecommerce | Commerce end-to-end agnóstico de lenguaje — data model, checkout, inventario, órdenes, pagos, promociones, shipping/tax, listings, analytics, feeds, storefront, suscripciones | 12 | ecommerce | | regulatory | ISO 13485, GDPR, FDA, SOC 2, ISMS, QMS, MDR | 13 | regulatory |

Personal

| Profile | Adds | Skills | Agents | |---------|------|--------|--------| | second-brain | Second brain en Obsidian — captura sin fricción, reviews diario/semanal/mensual, notas atómicas y hub files (PARA + Zettelkasten), búsqueda con ranking, caché de contexto entre sesiones, auditoría de salud del vault, sintaxis nativa (markdown, Bases, Canvas) | 14 | — | | job-hunt | Job search end-to-end — master profile, ATS CV with verification, job scraping with dedup, LinkedIn, portfolio, cover letters, outreach, interview prep, registry/CSV traceability, fresh-context review agents | 17 | career | | freelance | Freelance projects — keyless public-source scanning with dedup, market rate intel, client risk screening, proposals priced above your net floor rate, contracts/SOWs, registry/CSV traceability, kickoff scope validation, delivery and change orders, acquisition-cost pipeline, Fiverr gigs | 16 | freelance |

Utilities

| Profile | Adds | Skills | Agents | |---------|------|--------|--------| | docs | PDF, PPTX, XLSX, DOCX, architecture decisions | 8 | — | | self-improving | Agent self-improvement and skill extraction | 2 | — | | statusline | Claude Code status bar (branch, division, session info) | 0 | — |

Core (always included)

21 universal skills (commit, create-pr, changelog, check, code-review, context-prime, help, start, fix-issue, hotfix, brainstorm, scope-check, reverse-document, skill-improve, skill-test, tech-debt, + 5 arcane self-management), 15 hooks, 3 base rules, 1 agent dir (quality), and security permissions.

Recommended MCPs

Several profiles ship skills that drive an external tool over MCP. Arcane does not bundle any MCP server — install the ones your stack needs and Claude Code connects to them.

Game engines

| Engine | MCP server | Where it comes from | Wire it up with | |--------|------------|---------------------|-----------------| | Unreal Engine 5 | ModelContextProtocol + AllToolsets | Ships with the engine — nothing to add to the project, just enable the plugins in the .uproject | /install-mcp unreal | | Unity | CoplayDev — MCP for Unity | UPM package added to Packages/manifest.json | /install-mcp unity | | Unity (alternative) | CoderGamester — mcp-unity | UPM package, opt-in | /install-mcp unity --secondary |

Both engines need the editor open and running for the server to answer — registering the client does not start the server.

For Unreal, Epic also publishes a companion plugin: unreal-engine-skills-for-claude-code-plugin. It ships the in-editor skills that operate and extend the MCP (unreal-mcp, create-toolset, unreal-skill), which Arcane deliberately does not duplicate — see ATTRIBUTION.md.

Other integrations

| MCP server | Used by | Profile | |------------|---------|---------| | ClickUp | /clickup | +clickup | | Figma | /figma, /figma-to-code, /figma-tokens | +design | | Atlassian (Confluence) | /confluence-expert, /atlassian-templates | +agile | | TestRail + BrowserStack | /playwright-pro (ships its own .mcp.json) | +testing |

/jira-tickets is the exception: it talks to the Jira REST API v3 over curl, not MCP.

Building your own server? /mcp-server-builder scaffolds one.

Examples by Project

# Unity dev only
npx claude-code-arcane install unity-dev

# Unity with team and management
npx claude-code-arcane install unity-dev+unity-design+agile+clickup

# Go microservice with infra
npx claude-code-arcane install backend-go+infra+agile+jira

# Full-stack monorepo
npx claude-code-arcane install backend-ts+frontend+testing+database

# Mobile app with CI/CD
npx claude-code-arcane install mobile+agile+clickup+testing

# Secure backend with docs
npx claude-code-arcane install backend-ts+security+docs+database

# AI/ML project with data pipelines
npx claude-code-arcane install backend-go+ai+infra

# SaaS with full marketing stack
npx claude-code-arcane install backend-ts+marketing+business+finance

# Regulated medical device
npx claude-code-arcane install backend-ts+regulatory+security+testing

# Founder advisory setup
npx claude-code-arcane install clevel+business+finance+marketing

# With status bar
npx claude-code-arcane install backend-ts+agile+statusline

Add/Remove Workflow

# Start with a profile
npx claude-code-arcane install backend-ts

# Later, add testing and security
npx claude-code-arcane add +testing +security

# Add a specific skill you need
npx claude-code-arcane add docker-setup

# Realize you don't need testing anymore
npx claude-code-arcane remove +testing

# Remove a specific skill
npx claude-code-arcane remove docker-setup

# Check what you have now
npx claude-code-arcane status

# Start over
npx claude-code-arcane clean --force
npx claude-code-arcane install backend-ts+agile

Worktree Support

Work on multiple features in parallel using git worktrees, each with its own Arcane installation.

Create a worktree with Arcane pre-installed

# Create worktree + install Arcane in one step
npx claude-code-arcane worktree feat/new-api --profile backend-ts+agile

# Inherits profile from current installation
npx claude-code-arcane worktree feat/new-api

# With dependency install and Docker port isolation
npx claude-code-arcane worktree feat/new-api --install-deps --isolate

# Custom path and base branch
npx claude-code-arcane worktree feat/new-api --path ../my-api-worktree --base develop

# Preview without creating
npx claude-code-arcane worktree feat/new-api --dry-run

Worktree-aware installation

When you run npx claude-code-arcane install inside a git worktree, Arcane automatically:

• Detects it's in a worktree
• Finds the main worktree's Arcane installation
• Shares hooks/ and docs/ via symlink (read-only, identical across worktrees)
• Copies skills/, agents/, and rules/ independently (can diverge per worktree)

# Manual: share from a specific installation
npx claude-code-arcane install backend-ts --share-from /path/to/main/worktree

# Disable sharing
npx claude-code-arcane worktree feat/api --no-share

What gets shared vs independent

| Asset | Behavior | Why | |-------|----------|-----| | hooks/ | Shared (symlink) | Same hooks for all worktrees | | docs/ | Shared (symlink) | Documentation doesn't change per branch | | skills/ | Independent (copy) | Different worktrees may add/remove skills | | agents/ | Independent (copy) | Agent definitions could vary | | rules/ | Independent (copy) | Rules may differ per profile | | settings.json | Independent (generated) | Permissions/hooks config per profile | | arcane-manifest.json | Independent | Tracks this worktree's installation |

Status shows worktree info

npx claude-code-arcane status
# === Arcane Status ===
#   Profiles:  backend-ts + agile
#   Worktree:  yes (main: /path/to/main/checkout)
#   Shared:    hooks, docs (symlinked)
#   ...

Architecture

claude-code-arcane/
├── package.json               # npm package (bin: arcane)
├── src/                       # TypeScript CLI (15 files)
│   ├── cli.ts                 # Entry point (Commander.js)
│   ├── commands/              # 9 commands (install, add, remove, list, status, update, clean, worktree, global)
│   ├── profiles.ts            # YAML profile parser + merge
│   ├── installer.ts           # Copy logic (skills, hooks, rules, agents, docs)
│   ├── worktree.ts            # Git worktree detection, creation, sharing
│   ├── manifest.ts            # Read/write arcane-manifest.json
│   ├── types.ts               # TypeScript interfaces
│   └── utils.ts               # Cross-platform helpers
├── skills/                    # 437 skills (flat, one dir per skill)
├── profiles/                  # 38 profiles (YAML)
├── agents/                    # 17 dirs, 109 agents (Markdown)
├── hooks/                     # 17 lifecycle hooks (Bash)
├── rules/                     # 30 rules (Markdown)
├── templates/                 # Gamedev templates
├── docs/                      # Documentation
└── skills-selftest/           # QA framework

Philosophy

• Selective: install only what you need — fewer tokens, better performance
• Replaceable: switching profiles replaces the previous config (with automatic backup)
• Deduplicated: combined profiles never duplicate skills
• Self-managing: add, remove, and list from within Claude Code
• Safe removal: removing a profile only deletes assets not shared with other active profiles

Compatibility

• OS: Windows 10/11, macOS, Linux
• Node: 20+
• Claude Code: v1.0+

Attribution

Arcane is MIT licensed (see LICENSE). The ue-* skills shipped by the unreal-dev profile are derived from three upstream collections — quodsoler/unreal-engine-skills (MIT), EpicGames/unreal-engine-skills-for-claude-code-plugin (MIT), and gamedev-skills/awesome-gamedev-agent-skills (Apache-2.0). See ATTRIBUTION.md for the per-skill provenance, the changes made, and the required license notices.