Claude Code Hub: Pricing, Permissions, Plugins and Setup Guide
Understand Claude Code's subscription and API quota rules, Windows/WSL setup, sandbox and permission modes, and explore catalogued memory plugins, multi-agent orchestrators and provider switchers.
Key takeaways
- Claude Code works with Claude Pro, Max, Team or Enterprise subscriptions or pay-as-you-go Anthropic Console API billing; custom endpoints can be routed via environment variables or CC Switch.
- By default it asks before editing files or running shell commands; configure sandbox rules and allow/deny lists before using auto-approve modes.
- The public anthropics/claude-code repository is source-available under Anthropic's commercial terms rather than an OSI open-source license.
- Its ecosystem centers on cross-session memory (claude-mem), workflow packs (ECC), provider switchers (CC Switch) and MCP/hook extensions.
Key facts: pricing, models, surfaces & safety
Sign in with Claude Pro, Max, Team or Enterprise for rolling subscription quota, or connect an Anthropic Console API key billed per token. No permanent free tier.
Natively runs Claude Sonnet, Opus and Haiku models, with first-party support for Amazon Bedrock and Google Vertex AI, plus custom endpoints via ANTHROPIC_BASE_URL.
Terminal CLI at its core, paired with official VS Code and JetBrains extensions, GitHub Actions, and remote cloud sessions.
Read-only actions run directly while file edits and shell commands prompt for approval. Fine-grained rules live in settings.json; reserve --dangerously-skip-permissions for isolated containers.
Extension points: CLAUDE.md, Hooks, Subagents and Plugins
Tools in the Claude Code ecosystem plug into one of four official extension mechanisms:
CLAUDE.md
Project or user instruction file loaded into context with build commands, conventions and repo architecture.
Hooks & Settings
Deterministic PreToolUse, PostToolUse and Stop shell hooks declared in `.claude/settings.json` for linting, auditing and guardrails.
Subagents & Slash Commands
Markdown role definitions in `.claude/agents/` and workflow templates in `.claude/commands/` with isolated context windows.
MCP Servers & Plugins
External tool servers and bundled skill/hook plugins installed via `claude mcp` or plugin marketplaces.
Setup & troubleshooting guides
Claude Code on Windows: setup and troubleshooting
Install Claude Code on Windows: native or WSL 2, PowerShell / CMD / WinGet commands, whether you need Git for Windows, fixes for 'claude' is not recognized and other errors, sign-in and permission modes.
Setup and troubleshooting guideCC Switch guide
Install CC Switch from official sources, switch API providers for Claude Code, Codex, OpenCode and more, understand what routing mode writes to your config, and the risks of key storage and third-party relays.
Companion tool guideClaude Code ecosystem & extensions
Plugins, config packs, switchers and orchestration layers in the directory built for Claude Code, by stars; each has its own FARS review.
Multi-agent orchestration, parallel sessions & workbenches
Claude Code Best Practices
From vibe coding to agentic engineering: a structured guide to configuring and mastering Claude Code.
Oh My ClaudeCode
Team-first multi-agent orchestration for Claude Code, from planning through verification and repair.
Claude Code Skills & Plugins
A library of 362 production-ready skills, plugins, and agent skills for 13 AI coding tools, covering engineering, marketing, product, compliance, C-level advisory, and more.
Obsidian Second Brain
Turn your Obsidian vault into persistent memory for Claude Code, Codex, and 6 other AI agents: plain markdown storage, 48 commands, self-rewriting notes, and a shared multi-agent logbook.
Cross-session memory & context tools
Claude-Mem
Persistent, searchable project memory for coding agents across sessions.
Claude Context — Semantic Code Search MCP for AI Coding Agents
Make your entire codebase the context for any coding agent with semantic code search.
Plugins, routing & companion extensions
Ponytail
Guides coding agents to reuse what already exists and write the smallest implementation that preserves safety boundaries.
Learn Claude Code: Harness Engineering for Real Agents
Go from 0 to 1 building a nano Claude Code–like agent harness that turns any trained model into a working agent product.
I Have ADHD Skill
Stop your coding agent from burying the answer: action first, numbered steps, no fluff.
Agentic Plugin Marketplace
Composable developer-workflow plugins for multiple coding-agent harnesses.
Claude Code Game Studio
A structured Claude Code team for planning, building, testing, and releasing games.
Claude Code Router (CCR)
One local control plane for every AI agent: route, fail over, extend, and observe from a single app.
Cognee Memory Platform
Persistent, self-hosted graph and vector memory for AI agents across sessions.
Frontend Slides — Web Slide Generation Skill
Create beautiful HTML presentations with a coding agent, no design or coding skills required.
Planning with Files
Persistent disk-backed plans for coding agents that must survive context loss.
Elephant-Goldfish Model (EGM)
Draft specs with a deep-context 'Elephant' agent, then stress-test the design with zero-context 'Goldfish' reviewers to expose unstated assumptions before you write code.
ARIS ⚔️🌙 Auto-Research-In-Sleep
Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation.
Claude Skills for Full-Stack Developers
67 specialized skills for Claude Code that turn it into an expert pair programmer for full-stack development.
Claude Code Tips & Workflows
40+ practical tips for Claude Code, from basics to advanced, including a custom status line and containerized self-running demos.
Ralph for Claude Code
Run Claude Code in a safeguarded autonomous loop that keeps developing until its work is explicitly complete.
OH Story — All-in-One Skill Pack for Chinese Web Fiction
Covers trend scanning, story breakdown, writing, de-AI-ifying, and cover art for Chinese web novels, adapted for multiple AI coding tools.
Claude Agent SDK for Python
Call Claude Code from Python to build asynchronous and interactive agent workflows with extensible tools.
Internet Court Skill
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegations, x402 payments, escrow, and dispute resolution in one open skill.
Claude Scholar
Semi-automated research assistant for academic research and software development, supporting multiple AI CLI backends.
Browse Claude Code skills on FollowSkills → Switching Claude Code between model providers? Read the CC Switch guide →
Claude Code comparisons & rankings
AI coding agents, ranked
Gemini CLI, Cline, OpenCode, Kilo Code, Aider, Qwen Code and more ranked by one FARS source review, with license, stars and maintenance; Claude Code and Codex CLI are listed but unscored.
View full category ranking →Claude Code Agents, Compared
Claude Code agents ranked by FARS review — compatibility is read from each agent's own AGENTS.md and documentation, not assumed, and only full support is listed.
12 reviewed agents comparedRelated concepts
Frequently asked questions
Is Claude Code open source?
No. While anthropics/claude-code is a public repository on GitHub, it is distributed under Anthropic's proprietary commercial license rather than an OSI-approved open-source license.
Should I run Claude Code natively on Windows or inside WSL 2?
Claude Code supports both native Windows (via Git for Windows / Git Bash) and WSL 2. Choose WSL 2 if your toolchain relies on Linux-only binaries or containers; otherwise native Windows works directly.
How do I switch model providers or relay endpoints in Claude Code?
Claude Code reads ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN. Companion tools like CC Switch can swap these profiles in one click, though third-party relays carry key and code privacy risks.