Skip to content
Back to search

everything-claude-code

MarketplaceWorks with Claude CodeGitHub

Claude Code toolkit - agents, commands, skills, rules, and hooks for productive AI-assisted development

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/worldflowai-everything-claude-code/badge.svg)](/listings/worldflowai-everything-claude-code)

HTML

<a href="/listings/worldflowai-everything-claude-code"><img src="/api/listings/worldflowai-everything-claude-code/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Option 1: Install as Plugin (Recommended)

The easiest way to use this repo - install as a Claude Code plugin:

# 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`:

{
  "extraKnownMarketplaces": {
    "everything-claude-code": {
      "source": {
        "source": "github",
        "repo": "affaan-m/everything-claude-code"
      }
    }
  },
  "enabledPlugins": {
    "everything-claude-code@everything-claude-code": true
  }
}

This gives you instant access to all commands, agents, skills, and hooks.

---

Option 2: Manual Installation

If you prefer manual control over what's installed:

# 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 hooks from `hooks/hooks.json` to your `~/.claude/settings.json`.

Configure MCPs

Copy desired MCP servers from `mcp-configs/mcp-servers.json` to your `~/.claude.json`.

**Important:** Replace `YOUR_*_HERE` placeholders with your actual API keys.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 44 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "everything-claude-code",
  3. "owner": {
  4. "name": "Affaan Mustafa",
  5. "email": "affaan@example.com"
  6. },
  7. "metadata": {
  8. "description": "Battle-tested Claude Code configurations from an Anthropic hackathon winner"
  9. },
  10. "plugins": [
  11. {
  12. "name": "everything-claude-code",
  13. "source": "./",
  14. "description": "Complete collection of agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use",
  15. "author": {
  16. "name": "Affaan Mustafa"
  17. },
  18. "homepage": "https://github.com/affaan-m/everything-claude-code",
  19. "repository": "https://github.com/affaan-m/everything-claude-code",
  20. "license": "MIT",
  21. "keywords": [
  22. "agents",
  23. "skills",
  24. "hooks",
  25. "commands",
  26. "tdd",
  27. "code-review",
  28. "security",
  29. "best-practices"
  30. ],
  31. "category": "workflow",
  32. "tags": [
  33. "agents",
  34. "skills",
  35. "hooks",
  36. "commands",
  37. "tdd",
  38. "code-review",
  39. "security",
  40. "best-practices"
  41. ]
  42. }
  43. ]
  44. }
README.md · README · 392 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Everything Claude Code
  2. [![Stars](https://img.shields.io/github/stars/affaan-m/everything-claude-code?style=flat)](https://github.com/affaan-m/everything-claude-code/stargazers)
  3. [![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
  4. ![Shell](https://img.shields.io/badge/-Shell-4EAA25?logo=gnu-bash&logoColor=white)
  5. ![TypeScript](https://img.shields.io/badge/-TypeScript-3178C6?logo=typescript&logoColor=white)
  6. ![Markdown](https://img.shields.io/badge/-Markdown-000000?logo=markdown&logoColor=white)
  7. **The complete collection of Claude Code configs from an Anthropic hackathon winner.**
  8. Production-ready agents, skills, hooks, commands, rules, and MCP configurations evolved over 10+ months of intensive daily use building real products.
  9. ---
  10. ## The Guides
  11. This repo is the raw code only. The guides explain everything.
  12. <table>
  13. <tr>
  14. <td width="50%">
  15. <a href="https://x.com/affaanmustafa/status/2012378465664745795">
  16. <img src="https://github.com/user-attachments/assets/1a471488-59cc-425b-8345-5245c7efbcef" alt="The Shorthand Guide to Everything Claude Code" />
  17. </a>
  18. </td>
  19. <td width="50%">
  20. <a href="https://x.com/affaanmustafa/status/2014040193557471352">
  21. <img src="https://github.com/user-attachments/assets/c9ca43bc-b149-427f-b551-af6840c368f0" alt="The Longform Guide to Everything Claude Code" />
  22. </a>
  23. </td>
  24. </tr>
  25. <tr>
  26. <td align="center"><b>Shorthand Guide</b><br/>Setup, foundations, philosophy. <b>Read this first.</b></td>
  27. <td align="center"><b>Longform Guide</b><br/>Token optimization, memory persistence, evals, parallelization.</td>
  28. </tr>
  29. </table>
  30. | Topic | What You'll Learn |
  31. |-------|-------------------|
  32. | Token Optimization | Model selection, system prompt slimming, background processes |
  33. | Memory Persistence | Hooks that save/load context across sessions automatically |
  34. | Continuous Learning | Auto-extract patterns from sessions into reusable skills |
  35. | Verification Loops | Checkpoint vs continuous evals, grader types, pass@k metrics |
  36. | Parallelization | Git worktrees, cascade method, when to scale instances |
  37. | Subagent Orchestration | The context problem, iterative retrieval pattern |
  38. ---
  39. ## Cross-Platform Support
  40. This plugin now fully supports **Windows, macOS, and Linux**. All hooks and scripts have been rewritten in Node.js for maximum compatibility.
  41. ### Package Manager Detection
  42. The plugin automatically detects your preferred package manager (npm, pnpm, yarn, or bun) with the following priority:
  43. 1. **Environment variable**: `CLAUDE_PACKAGE_MANAGER`
  44. 2. **Project config**: `.claude/package-manager.json`
  45. 3. **package.json**: `packageManager` field
  46. 4. **Lock file**: Detection from package-lock.json, yarn.lock, pnpm-lock.yaml, or bun.lockb
  47. 5. **Global config**: `~/.claude/package-manager.json`
  48. 6. **Fallback**: First available package manager
  49. To set your preferred package manager:
  50. ```bash
  51. # Via environment variable
  52. export CLAUDE_PACKAGE_MANAGER=pnpm
  53. # Via global config
  54. node scripts/setup-package-manager.js --global pnpm
  55. # Via project config
  56. node scripts/setup-package-manager.js --project bun
  57. # Detect current setting
  58. node scripts/setup-package-manager.js --detect
  59. ```
  60. Or use the `/setup-pm` command in Claude Code.
  61. ---
  62. ## What's Inside
  63. This repo is a **Claude Code plugin** - install it directly or copy components manually.
  64. ```
  65. everything-claude-code/
  66. |-- .claude-plugin/ # Plugin and marketplace manifests
  67. | |-- plugin.json # Plugin metadata and component paths
  68. | |-- marketplace.json # Marketplace catalog for /plugin marketplace add
  69. |
  70. |-- agents/ # Specialized subagents for delegation
  71. | |-- planner.md # Feature implementation planning
  72. | |-- architect.md # System design decisions
  73. | |-- tdd-guide.md # Test-driven development
  74. | |-- code-reviewer.md # Quality and security review
  75. | |-- security-reviewer.md # Vulnerability analysis
  76. | |-- build-error-resolver.md
  77. | |-- e2e-runner.md # Playwright E2E testing
  78. | |-- refactor-cleaner.md # Dead code cleanup
  79. | |-- doc-updater.md # Documentation sync
  80. |
  81. |-- skills/ # Workflow definitions and domain knowledge
  82. | |-- coding-standards/ # Language best practices
  83. | |-- backend-patterns/ # API, database, caching patterns
  84. | |-- frontend-patterns/ # React, Next.js patterns
  85. | |-- continuous-learning/ # Auto-extract patterns from sessions (Longform Guide)
  86. | |-- strategic-compact/ # Manual compaction suggestions (Longform Guide)
  87. | |-- tdd-workflow/ # TDD methodology
  88. | |-- security-review/ # Security checklist
  89. | |-- eval-harness/ # Verification loop evaluation (Longform Guide)
  90. | |-- verification-loop/ # Continuous verification (Longform Guide)
  91. |
  92. |-- commands/ # Slash commands for quick execution
  93. | |-- tdd.md # /tdd - Test-driven development
  94. | |-- plan.md # /plan - Implementation planning
  95. | |-- e2e.md # /e2e - E2E test generation
  96. | |-- code-review.md # /code-review - Quality review
  97. | |-- build-fix.md # /build-fix - Fix build errors
  98. | |-- refactor-clean.md # /refactor-clean - Dead code removal
  99. | |-- learn.md # /learn - Extract patterns mid-session (Longform Guide)
  100. | |-- checkpoint.md # /checkpoint - Save verification state (Longform Guide)
  101. | |-- verify.md # /verify - Run verification loop (Longform Guide)
  102. | |-- setup-pm.md # /setup-pm - Configure package manager (NEW)
  103. |
  104. |-- rules/ # Always-follow guidelines (copy to ~/.claude/rules/)
  105. | |-- security.md # Mandatory security checks
  106. | |-- coding-style.md # Immutability, file organization
  107. | |-- testing.md # TDD, 80% coverage requirement
  108. | |-- git-workflow.md # Commit format, PR process
  109. | |-- agents.md # When to delegate to subagents
  110. | |-- performance.md # Model selection, context management
  111. |
  112. |-- hooks/ # Trigger-based automations
  113. | |-- hooks.json # All hooks config (PreToolUse, PostToolUse, Stop, etc.)
  114. | |-- memory-persistence/ # Session lifecycle hooks (Longform Guide)
  115. | |-- strategic-compact/ # Compaction suggestions (Longform Guide)
  116. |
  117. |-- scripts/ # Cross-platform Node.js scripts (NEW)
  118. | |-- lib/ # Shared utilities
  119. | | |-- utils.js # Cross-platform file/path/system utilities
  120. | | |-- package-manager.js # Package manager detection and selection
  121. | |-- hooks/ # Hook implementations
  122. | | |-- session-start.js # Load context on session start
  123. | | |-- session-end.js # Save state on session end
  124. | | |-- pre-compact.js # Pre-compaction state saving
  125. | | |-- suggest-compact.js # Strategic compaction suggestions
  126. | | |-- evaluate-session.js # Extract patterns from sessions
  127. | |-- setup-package-manager.js # Interactive PM setup
  128. |
  129. |-- tests/ # Test suite (NEW)
  130. | |-- lib/ # Library tests
  131. | |-- hooks/ # Hook tests
  132. | |-- run-all.js # Run all tests
  133. |
  134. |-- contexts/ # Dynamic system prompt injection contexts (Longform Guide)
  135. | |-- dev.md # Development mode context
  136. | |-- review.md # Code review mode context
  137. | |-- research.md # Research/exploration mode context
  138. |
  139. |-- examples/ # Example configurations and sessions
  140. | |-- CLAUDE.md # Example project-level config
  141. | |-- user-CLAUDE.md # Example user-level config
  142. |
  143. |-- mcp-configs/ # MCP server configurations
  144. | |-- mcp-servers.json # GitHub, Supabase, Vercel, Railway, etc.
  145. |
  146. |-- marketplace.json # Self-hosted marketplace config (for /plugin marketplace add)
  147. ```
  148. ---
  149. ## Installation
  150. ### Option 1: Install as Plugin (Recommended)
  151. The easiest way to use this repo - install as a Claude Code plugin:
  152. ```bash
  153. # Add this repo as a marketplace
  154. /plugin marketplace add affaan-m/everything-claude-code
  155. # Install the plugin
  156. /plugin install everything-claude-code@everything-claude-code
  157. ```
  158. Or add directly to your `~/.claude/settings.json`:
  159. ```json
  160. {
  161. "extraKnownMarketplaces": {
  162. "everything-claude-code": {
  163. "source": {
  164. "source": "github",
  165. "repo": "affaan-m/everything-claude-code"
  166. }
  167. }
  168. },
  169. "enabledPlugins": {
  170. "everything-claude-code@everything-claude-code": true
  171. }
  172. }
  173. ```
  174. This gives you instant access to all commands, agents, skills, and hooks.
  175. ---
  176. ### Option 2: Manual Installation
  177. If you prefer manual control over what's installed:
  178. ```bash
  179. # Clone the repo
  180. git clone https://github.com/affaan-m/everything-claude-code.git
  181. # Copy agents to your Claude config
  182. cp everything-claude-code/agents/*.md ~/.claude/agents/
  183. # Copy rules
  184. cp everything-claude-code/rules/*.md ~/.claude/rules/
  185. # Copy commands
  186. cp everything-claude-code/commands/*.md ~/.claude/commands/
  187. # Copy skills
  188. cp -r everything-claude-code/skills/* ~/.claude/skills/
  189. ```
  190. #### Add hooks to settings.json
  191. Copy the hooks from `hooks/hooks.json` to your `~/.claude/settings.json`.
  192. #### Configure MCPs
  193. Copy desired MCP servers from `mcp-configs/mcp-servers.json` to your `~/.claude.json`.
  194. **Important:** Replace `YOUR_*_HERE` placeholders with your actual API keys.
  195. ---
  196. ## Key Concepts
  197. ### Agents
  198. Subagents handle delegated tasks with limited scope. Example:
  199. ```markdown
  200. ---
  201. name: code-reviewer
  202. description: Reviews code for quality, security, and maintainability
  203. tools: Read, Grep, Glob, Bash
  204. model: opus
  205. ---
  206. You are a senior code reviewer...
  207. ```
  208. ### Skills
  209. Skills are workflow definitions invoked by commands or agents:
  210. ```markdown
  211. # TDD Workflow
  212. 1. Define interfaces first
  213. 2. Write failing tests (RED)
  214. 3. Implement minimal code (GREEN)
  215. 4. Refactor (IMPROVE)
  216. 5. Verify 80%+ coverage
  217. ```
  218. ### Hooks
  219. Hooks fire on tool events. Example - warn about console.log:
  220. ```json
  221. {
  222. "matcher": "tool == \"Edit\" && tool_input.file_path matches \"\\\\.(ts|tsx|js|jsx)$\"",
  223. "hooks": [{
  224. "type": "command",
  225. "command": "#!/bin/bash\ngrep -n 'console\\.log' \"$file_path\" && echo '[Hook] Remove console.log' >&2"
  226. }]
  227. }
  228. ```
  229. ### Rules
  230. Rules are always-follow guidelines. Keep them modular:
  231. ```
  232. ~/.claude/rules/
  233. security.md # No hardcoded secrets
  234. coding-style.md # Immutability, file limits
  235. testing.md # TDD, coverage requirements
  236. ```
  237. ---
  238. ## Running Tests
  239. The plugin includes a comprehensive test suite:
  240. ```bash
  241. # Run all tests
  242. node tests/run-all.js
  243. # Run individual test files
  244. node tests/lib/utils.test.js
  245. node tests/lib/package-manager.test.js
  246. node tests/hooks/hooks.test.js
  247. ```
  248. ---
  249. ## Contributing
  250. **Contributions are welcome and encouraged.**
  251. This repo is meant to be a community resource. If you have:
  252. - Useful agents or skills
  253. - Clever hooks
  254. - Better MCP configurations
  255. - Improved rules
  256. Please contribute! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
  257. ### Ideas for Contributions
  258. - Language-specific skills (Python, Go, Rust patterns)
  259. - Framework-specific configs (Django, Rails, Laravel)
  260. - DevOps agents (Kubernetes, Terraform, AWS)
  261. - Testing strategies (different frameworks)
  262. - Domain-specific knowledge (ML, data engineering, mobile)
  263. ---
  264. ## Background
  265. I've been using Claude Code since the experimental rollout. Won the Anthropic x Forum Ventures hackathon in Sep 2025 building [zenith.chat](https://zenith.chat) with [@DRodriguezFX](https://x.com/DRodriguezFX) - entirely using Claude Code.
  266. These configs are battle-tested across multiple production applications.
  267. ---
  268. ## Important Notes
  269. ### Context Window Management
  270. **Critical:** Don't enable all MCPs at once. Your 200k context window can shrink to 70k with too many tools enabled.
  271. Rule of thumb:
  272. - Have 20-30 MCPs configured
  273. - Keep under 10 enabled per project
  274. - Under 80 tools active
  275. Use `disabledMcpServers` in project config to disable unused ones.
  276. ### Customization
  277. These configs work for my workflow. You should:
  278. 1. Start with what resonates
  279. 2. Modify for your stack
  280. 3. Remove what you don't use
  281. 4. Add your own patterns
  282. ---
  283. ## Star History
  284. [![Star History Chart](https://api.star-history.com/svg?repos=affaan-m/everything-claude-code&type=Date)](https://star-history.com/#affaan-m/everything-claude-code&Date)
  285. ---
  286. ## Links
  287. - **Shorthand Guide (Start Here):** [The Shorthand Guide to Everything Claude Code](https://x.com/affaanmustafa/status/2012378465664745795)
  288. - **Longform Guide (Advanced):** [The Longform Guide to Everything Claude Code](https://x.com/affaanmustafa/status/2014040193557471352)
  289. - **Follow:** [@affaanmustafa](https://x.com/affaanmustafa)
  290. - **zenith.chat:** [zenith.chat](https://zenith.chat)
  291. ---
  292. ## License
  293. MIT - Use freely, modify as needed, contribute back if you can.
  294. ---
  295. **Star this repo if it helps. Read both guides. Build something great.**

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.