everything-claude-code-zh

**Language:** [English](README.md) | **Simplified Chinese** | [Traditional Chinese](docs/zh-TW/README.md) # Everything Claude Code [](https://github.com/affaan-m/everything-claude-code/stargazers) [](LICENSE)     --- <div align="center"> **🌐 Language / 语言 / 語言** [**English**](README.md) | [简体中文](README.zh-CN.md) | [繁體中文](docs/zh-TW/README.md) </div> --- **The complete Claude Code setup from an Anthropic hackathon winner.** Includes production-grade Agents, Skills, Hooks, Commands, Rules, and MCP configs, battle-tested and evolved over 10+ months of daily, high-intensity use building real products. --- ## Guides This repo contains only raw code. The following guides explain everything in detail: <table> <tr> <td width="50%"> <a href="https://x.com/affaanmustafa/status/2012378465664745795"> <img src="https://github.user-attachments.assets/1a471488-59cc-425b-8345-5245c7efbcef" alt="Everything Claude Code Shorthand Guide" /> </a> </td> <td width="50%"> <a href="https://x.com/affaanmustafa/status/2014040193557471352"> <img src="https://github.user-attachments.assets/c9ca43bc-b149-427f-b551-af6840c368f0" alt="Everything Claude Code Longform Guide" /> </a> </td> </tr> <tr> <td align="center"><b>Shorthand Guide</b><br/>Installation, basics, philosophy. <b>Read this first.</b></td> <td align="center"><b>Longform Guide</b><br/>Token optimization, memory persistence, evals, parallelization.</td> </tr> </table> | Topic | You'll Learn | |-------|-------------------| | Token Optimization | Model selection, prompt compression, background processes | | Memory Persistence | Hooks to auto-save/load context across sessions | | Continuous Learning | Auto-extract patterns from sessions into reusable Skills | | Verification Loops | Checkpoints vs continuous evals, scorer types, pass@k metric | | Parallelization | Git worktrees, cascading methods, when to scale instances | | Subagent Orchestration | Context problems, iterative retrieval patterns | --- ## 🚀 Quickstart Get set up in < 2 minutes: ### Step 1: Install the plugin ```bash # Add the marketplace /plugin marketplace add affaan-m/everything-claude-code # Install the plugin /plugin install everything-claude-code@everything-claude-code ``` ### Step 2: Install the rules (required) > ⚠️ **Important:** Claude Code plugins can't distribute `rules` automatically. Install manually: ```bash # First clone the repo git clone https://github.com/affaan-m/everything-claude-code.git # Copy the rules (applies to all projects) cp -r everything-claude-code/rules/* ~/.claude/rules/ ``` ### Step 3: Start using it ```bash # Try a command /plan "Add user authentication" # See available commands /plugin list everything-claude-code@everything-claude-code ``` ✨ **That's it!** You now have 15+ agents, 30+ skills, and 20+ commands. --- ## 🌐 Cross-Platform Support This plugin is now fully supported on **Windows, macOS, and Linux**. All hooks and scripts have been rewritten in Node.js for maximum compatibility. ### Package Manager Detection The plugin automatically detects your preferred package manager (npm, pnpm, yarn, or bun) with the following priority: 1. **Environment Variable**: `CLAUDE_PACKAGE_MANAGER` 2. **Project Config**: `.claude/package-manager.json` 3. **package.json**: `packageManager` field 4. **Lockfile**: Detect based on package-lock.json, yarn.lock, pnpm-lock.yaml, or bun.lockb 5. **Global Config**: `~/.claude/package-manager.json` 6. **Fallback**: First available package manager Set your preferred package manager: ```bash # Via environment variable export CLAUDE_PACKAGE_MANAGER=pnpm # Via global config node scripts/setup-package-manager.js --global pnpm # Via project config node scripts/setup-package-manager.js --project bun # Detect current setting node scripts/setup-package-manager.js --detect ``` Or use the `/setup-pm` command in Claude Code. --- ## 📦 Contents This repo is a **Claude Code plugin** -- you can install it directly, or copy the components manually. ``` everything-claude-code/ |-- .claude-plugin/ # Plugin and marketplace manifest | |-- plugin.json # Plugin metadata and component paths | |-- marketplace.json # Marketplace listing for /plugin marketplace add | |-- agents/ # Specialized subagents for task delegation | |-- planner.md # Feature implementation planning | |-- architect.md # System design decisions | |-- tdd-guide.md # Test-driven development (TDD) | |-- code-reviewer.md # Quality and safety review | |-- security-reviewer.md # Vulnerability analysis | |-- build-error-resolver.md # Build error fixing | |-- e2e-runner.md # Playwright end-to-end (E2E) testing | |-- refactor-cleaner.md # Dead code removal | |-- doc-updater.md # Documentation syncing | |-- go-reviewer.md # Go code review (new) | |-- go-build-resolver.md # Go build error fixing (new) | |-- skills/ # Workflow definitions and domain knowledge | |-- coding-standards/ # Language best practices | |-- backend-patterns/ # API, database, caching patterns | |-- frontend-patterns/ # React, Next.js patterns | |-- continuous-learning/ # Auto-extract patterns from sessions (longform guide) | |-- continuous-learning-v2/ # "Instinct"-based learning with confidence scores | |-- iterative-retrieval/ # Progressive context refinement for subagents | |-- strategic-compact/ # Manual compression suggestions (longform guide) | |-- tdd-workflow/ # TDD methodology | |-- security-review/ # Security checklist | |-- eval-harness/ # Verification loop evals (longform guide) | |-- verification-loop/ # Continuous verification (longform guide) | |-- golang-patterns/ # Go idioms and best practices (new) | |-- golang-testing/ # Go testing patterns, TDD, benchmarks (new) | |-- commands/ # Slash commands for quick execution | |-- tdd.md # /tdd - Test-driven development | |-- plan.md # /plan - Implementation planning | |-- e2e.md # /e2e - Generate E2E tests | |-- code-review.md # /code-review - Quality review | |-- build-fix.md # /build-fix - Fix build errors | |-- refactor-clean.md # /refactor-clean - Remove dead code | |-- learn.md # /learn - Extract patterns mid-session (longform guide) | |-- checkpoint.md # /checkpoint - Save verification state (longform guide) | |-- verify.md # /verify - Run verification loop (longform guide) | |-- setup-pm.md # /setup-pm - Configure package manager | |-- go-review.md # /go-review - Go code review (new) | |-- go-test.md # /go-test - Go TDD workflow (new) | |-- go-build.md # /go-build - Fix Go build errors (new) | |-- skill-create.md # /skill-create - Generate skills from Git history (new) | |-- instinct-status.md # /instinct-status - View learned instincts (new) | |-- instinct-import.md # /instinct-import - Import instincts (new) | |-- instinct-export.md # /instinct-export - Export instincts (new) | |-- evolve.md # /evolve - Cluster instincts into skills (new) | |-- rules/ # Guidelines to enforce (copy to ~/.claude/rules/) | |-- security.md # Mandatory security checks | |-- coding-style.md # Immutability, file organization | |-- testing.md # TDD, 80% coverage required | |-- git-workflow.md # Commit format, PR process | |-- agents.md # When to delegate to subagents | |-- performance.md # Model selection, context management | |-- hooks/ # Triggers for automation | |-- hooks.json # All hook configurations (PreToolUse, PostToolUse, Stop, etc.) | |-- memory-persistence/ # Session lifecycle hooks (longform guide) | |-- strategic-compact/ # Compression suggestions (longform guide) | |-- scripts/ # Cross-platform Node.js scripts (new) | |-- lib/ # Shared utilities | | |-- utils.js # Cross-platform file/path/system utils | | |-- package-manager.js # Package manager detection and selection | |-- hooks/ # Hook implementations | | |-- session-start.js # Load context at session start | | |-- session-end.js # Save state at session end | | |-- pre-compact.js # State saving before compression | | |-- suggest-compact.js # Strategic compression suggestions | | |-- evaluate-session.js # Extract patterns from sessions | |-- setup-package-manager.js # Interactive package manager setup | |-- tests/ # Test suite (new) | |-- lib/ # Library tests | |-- hooks/ # Hook tests | |-- run-all.js # Run all tests | |-- contexts/ # Dynamic system prompt injection (longform guide) | |-- dev.md # Development mode context | |-- review.md # Code review mode context | |-- research.md # Research/exploration mode context | |-- examples/ # Example configs and sessions | |-- CLAUDE.md # Project-level config example | |-- user-CLAUDE.md # User-level config example | |-- mcp-configs/ # MCP Server configs | |-- mcp-servers.json # GitHub, Supabase, Vercel, Railway, etc. configs | |-- marketplace.json # Self-hosted marketplace config (for /plugin marketplace add) ``` --- ## 🛠️ Ecosystem Tools ### Skill Creator There are two ways to generate Claude Code skills from your repo: #### Option A: Local Analysis (Built-in) Use the `/skill-create` command for local analysis, no external services required: ```bash /skill-create # Analyze the current repo /skill-create --instincts # Also generate "Instincts" for continuous learning ``` This will analyze your Git history locally and generate a SKILL.md file. #### Option B: GitHub App (Advanced) For advanced features (10k+ commits, automated PRs, team sharing): [Install the GitHub App](https://github.com/apps/skill-creator) | [ecc.tools](https://ecc.tools) ```bash # Reply to any Issue with: /skill-creator analyze # Or trigger automatically on push to default branch ``` Both options create: - **SKILL.md files** - Skills directly usable by Claude Code - **Instinct collections** - For continuous-learning-v2 - **Pattern extraction** - Learning from your commit history ### 🧠 Continuous Learning v2 The "Instinct"-based learning system automatically learns your patterns: ```bash /instinct-status # Show learned instincts and their confidence /instinct-import <file> # Import instincts from others /instinct-export # Export your instincts for sharing /evolve # Cluster related instincts into skills ``` See `skills/continuous-learning-v2/` for full documentation. --- ## 📋 Requirements ### Claude Code CLI Version **Minimum version: v2.1.0 or higher** This plugin requires Claude Code CLI v2.1.0+ due to changes in how the plugin system handles Hooks. Check your version: ```bash claude --version ``` ### Important: Hook Autoloading Behavior > ⚠️ **To contributors:** Do NOT add a `"hooks"` field to `.claude-plugin/plugin.json`. This is enforced via regression test. By convention, Claude Code v2.1+ **automatically loads** `hooks/hooks.json` from any installed plugin. Explicitly declaring it in `plugin.json` will cause a duplicate detection error: ``` Duplicate hooks file detected: ./hooks/hooks.json resolves to already-loaded file ``` **Background:** This issue has caused multiple fix/revert cycles in this repo ([#29](https://github.com/affaan-m/everything-claude-code/issues/29), [#52](https://github.com/affaan-m/everything-claude-code/issues/52), [#103](https://github.com/affaan-m/everything-claude-code/issues/103)). Due to confusing behavior changes between Claude Code versions, we now prevent this via regression test. --- ## 📥 Installation ### Option 1: Install as a plugin (recommended) The easiest way to use this repo -- install it as a Claude Code plugin: ```bash # Add this repo as a marketplace /plugin marketplace add affaan-m/everything-claude-code # Install the plugin /plugin install everything-claude-code@everything-claude-code ``` Or add directly to your `~/.claude/settings.json`: ```json { "extraKnownMarketplaces": { "everything-claude-code": { "source": { "source": "github", "repo": "affaan-m/everything-claude-code" } } }, "enabledPlugins": { "everything-claude-code@everything-claude-code": true } } ``` All commands, agents, skills, and hooks are immediately available after installation. > **Note:** The Claude Code plugin system does not currently support distributing `rules` via plugins ([upstream limitation](https://code.claude.com/docs/en/plugins-reference)). You will need to install the rules manually: > > ```bash > # First clone the repo > git clone https://github.com/affaan-m/everything-claude-code.git > > # Option A: User-level rules (applies to all projects) > cp -r everything-claude-code/rules/* ~/.claude/rules/ > > # Option B: Project-level rules (applies to current project only) > mkdir -p .claude/rules > cp -r everything-claude-code/rules/* .claude/rules/ > ``` --- ### 🔧 Option 2: Manual Install If you prefer to manually control what gets installed: ```bash # Clone the repo git clone https://github.com/affaan-m/everything-claude-code.git # Copy Agents to your Claude config cp everything-claude-code/agents/*.md ~/.claude/agents/ # Copy Rules cp everything-claude-code/rules/*.md ~/.claude/rules/ # Copy Commands cp everything-claude-code/commands/*.md ~/.claude/commands/ # Copy Skills cp -r everything-claude-code/skills/* ~/.claude/skills/ ``` #### Add Hooks to settings.json Copy the contents of the hooks in `hooks/hooks.json` to your `~/.claude/settings.json`. #### Configure MCP Copy the MCP server configs you want from `mcp-configs/mcp-servers.json` to your `~/.claude.json`. **Important:** Replace the `YOUR_*_HERE` placeholders with your actual API keys. --- ## 🎯 Core Concepts ### Agents Subagents handle delegated tasks with a specific scope. Example: ```markdown --- name: code-reviewer description: Reviews code for quality, security, and maintainability tools: ["Read", "Grep", "Glob", "Bash"] model: opus --- You are a senior code reviewer... ``` ### Skills Skills are workflow definitions that can be invoked by commands or agents: ```markdown # TDD Workflow 1. Define the interface first 2. Write a failing test (RED) 3. Implement the simplest code (GREEN) 4. Refactor (IMPROVE) 5. Verify 80%+ coverage ``` ### Hooks Hooks trigger on tool events. Example - warn about `console.log` usage: ```json { "matcher": "tool == \"Edit\" && tool_input.file_path matches \"\\.(ts|tsx|js|jsx)$\"", "hooks": [{ "type": "command", "command": "#!/bin/bash\ngrep -n 'console\\.log' \"$file_path\" && echo '[Hook] Remove console.log' >&2" }] } ``` ### Rules Rules are guidelines that must always be followed. Keep them modular: ``` ~/.claude/rules/ security.md # No hardcoded secrets coding-style.md # Immutability, file limits testing.md # TDD, coverage requirements ``` --- ## 🧪 Run Tests This plugin includes a comprehensive test suite: ```bash # Run all tests node tests/run-all.js # Run a single test file node tests/lib/utils.test.js node tests/lib/package-manager.test.js node tests/hooks/hooks.test.js ``` --- ## 🤝 Contributing **Contributions of all kinds are welcome and encouraged.** This repo is intended to be a community resource. If you have: - Useful agents or skills - Clever hooks - Better MCP configs - Improved rules Please contribute! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines. ### Contribution Ideas - Language-specific skills (Python, Rust patterns) - Go already included! - Framework-specific configs (Django, Rails, Laravel) - DevOps agents (Kubernetes, Terraform, AWS) - Testing strategies (different frameworks) - Domain-specific knowledge (ML, data engineering, mobile) --- ## 📖 Project Background I've been using Claude Code since the experimental days. In Sept 2025, [@DRodriguezFX](https://x.com/DRodriguezFX) and I won the Anthropic x Forum Ventures hackathon with [zenith.chat](https://zenith.chat) - built entirely with Claude Code. These configs have been battle-tested across multiple production apps. --- ## ⚠️ Important Notes ### Context Window Management **Critical:** Do not enable all MCPs at once. Too many tools will shrink the 200k context window to 70k. Rule of thumb: - Configure 20-30 MCPs - Keep < 10 enabled per project - Keep total active tools < 80 Use `disabledMcpServers` in your project config to disable servers you don't use often. ### Customization These configs work for my workflow. You should: 1. Start with what resonates 2. Adapt to your tech stack 3. Remove what you don't need 4. Add your own patterns --- ## 🌟 Star History [](https://star-history.com/#affaan-m/everything-claude-code&Date) --- ## 🔗 Related Links - **Quickstart (start here):** [Everything Claude Code Quickstart](https://x.com/affaanmustafa/status/2012378465664745795) - **Deep Dive (read next):** [Everything Claude Code Deep Dive](https://x.com/affaanmustafa/status/2014040193557471352) - **Follow me:** [@affaanmustafa](https://x.com/affaanmustafa) - **zenith.chat:** [zenith.chat](https://zenith.chat) --- ## 📄 License MIT - use freely, modify as needed, attribution appreciated. --- **Star this repo if it helps you. Read the two guides. Go build great products.**