everything-claude-code-zh

**Language:** [English](README.md) | [简体中文](README.zh-CN.md) | [繁體中文](docs/zh-TW/README.md) | [日本語](docs/ja-JP/README.md) # Everything Claude Code [](https://github.com/affaan-m/everything-claude-code/stargazers) [](https://github.com/affaan-m/everything-claude-code/network/members) [](https://github.com/affaan-m/everything-claude-code/graphs/contributors) [](LICENSE)       > **50K+ stars** | **6K+ forks** | **30 contributors** | **6 languages supported** | **Anthropic Hackathon Winner** --- <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) | [日本語](docs/ja-JP/README.md) </div> --- **A performance optimization system for AI agents (Agents) frameworks. Born out of an Anthropic hackathon-winning project.** This is not just a configuration file. It is a complete system with skills, instincts, memory optimizations, continuous learning, security scans, and a research-prioritized development mode. These production-grade agents, hooks, commands, rules, and MCP configurations have evolved over 10+ months of intense daily usage while building real products. Suitable for **Claude Code**, **Codex**, **Cowork**, and other AI agents frameworks. --- ## The Guides This repository contains only the raw code. The guides section explains all the details. <table> <tr> <td width="50%"> <a href="https://x.com/affaanmustafa/status/2012378465664745795"> <img src="https://github.com/user-attachments/assets/1a471488-59cc-425b-8345-5245c7efbcef" alt="Everything Claude Code Brief Guide" /> </a> </td> <td width="50%"> <a href="https://x.com/affaanmustafa/status/2014040193557471352"> <img src="https://github.com/user-attachments/assets/c9ca43bc-b149-427f-b551-af6840c368f0" alt="Everything Claude Code Longform Guide" /> </a> </td> </tr> <tr> <td align="center"><b>Brief Guide</b><br/>Setup, 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 | What you'll learn | |-------|-------------------| | Token optimization | Model selection, system prompt slimming, background processes | | Memory persistence | Auto-save/load context hooks across sessions | | Continuous learning | Auto-convert sessions into reusable skills | | Validation loop | Checkpoint vs continuous evals, scorer types, pass@k metrics | | Parallelization | Git worktrees, cascading methods, when to scale instances | | Sub-agent orchestration | Contextual issues, iterative retrieval patterns | --- ## What's New ### v1.7.0 — Cross-Platform Extensions & Presentation Generator (February 2026) - **Codex App + CLI Support** — Direct support for `AGENTS.md`-based Codex, installer targeting, and Codex documentation - **`frontend-slides` Skill** — Dependency-free HTML presentation generator with PPTX conversion guide and strict viewport adaptive rules - **5 New General-Purpose Business/Content Skills** — `article-writing`, `content-engine`, `market-research`, `investor-materials`, `investor-outreach` - **Broader Tooling Coverage** — Enhanced support for Cursor, Codex, and OpenCode, enabling seamless operation across all major frameworks - **992 Internal Tests** — Extended validation and regression coverage for plugins, hooks, skills, and packaging ### v1.6.0 — Codex CLI, AgentShield & Marketplace (February 2026) - **Codex CLI Support** — Introduced `/codex-setup` command to generate OpenAI Codex CLI-compatible `codex.md` - **7 New Skills** — `search-first`, `swift-actor-persistence`, `swift-protocol-di-testing`, `regex-vs-llm-structured-text`, `content-hash-cache-pattern`, `cost-aware-llm-pipeline`, `skill-stocktake` - **AgentShield Integration** — `/security-scan` skill directly runs AgentShield from Claude Code; includes 1282 tests, 102 rules - **GitHub Marketplace** — ECC Tools GitHub app launched at [github.com/marketplace/ecc-tools](https://github.com/marketplace/ecc-tools), offering free/professional/enterprise plans - **Merged 30+ Community PRs** — Contributions from 30 contributors across 6 languages - **978 Internal Tests** — Extended validation suite covering agents, skills, commands, hooks, and rules ### v1.4.1 — Bug Fixes (February 2026) - **Fixed Instinct Import Loss** — `parse_instinct_file()` silently discarded post-Frontmatter content (Action, Evidence, Examples sections) when executing `/instinct-import`. Fixed by community contributor @ericcai0814 ([#148](https://github.com/affaan-m/everything-claude-code/issues/148), [#161](https://github.com/affaan-m/everything-claude-code/pull/161)) ### v1.4.0 — Multilingual Rules, Setup Wizard & PM2 (February 2026) - **Interactive Setup Wizard** — Introduced `configure-ecc` skill with guided setup and merge/override detection - **PM2 & Multi-Agent Orchestration** — 6 new commands (`/pm2`, `/multi-plan`, `/multi-execute`, `/multi-backend`, `/multi-frontend`, `/multi-workflow`) for managing complex multi-service workflows - **Multilingual Rules Architecture** — Rules refactored from flat files to `common/` + `typescript/` + `python/` + `golang/` directories. Install only needed languages - **Chinese (zh-CN) Translation** — Completed translation of all agents, commands, skills, and rules (80+ files) - **GitHub Sponsors Support** — Enabled GitHub Sponsors for the project - **Enhanced CONTRIBUTING.md** — Detailed PR templates for each contribution type ### v1.3.0 — OpenCode Plugin Support (February 2026) - **Comprehensive OpenCode Integration** — 12 agents, 24 commands, 16 skills, and hooks supported via OpenCode's plugin system (20+ event types) - **3 Native Custom Tools** — `run-tests`, `check-coverage`, `security-audit` - **LLM Documentation** — Provided `llms.txt` for comprehensive OpenCode documentation ### v1.2.0 — Unified Commands & Skills (February 2026) - **Python/Django Support** — Django patterns, security, TDD, and validation skills - **Java Spring Boot Skills** — Spring Boot patterns, security, TDD, and validation - **Session Management** — `/sessions` command for viewing session history - **Continuous Learning v2** — Instinct-based learning system with confidence scoring, import/export, and evolution See the full changelog in [Releases](https://github.com/affaan-m/everything-claude-code/releases). --- ## 🚀 Quick Start Get started and running in 2 minutes: ### Step 1: Install Plugin ```bash # Add marketplace /plugin marketplace add affaan-m/everything-claude-code # Install plugin /plugin install everything-claude-code@everything-claude-code ``` ### Step 2: Install Rules (Mandatory) > ⚠️ **Important:** Claude Code plugin cannot auto-distribute `rules`. Please install manually: ```bash # Clone repository git clone https://github.com/affaan-m/everything-claude-code.git cd everything-claude-code # Recommended: Use installation script (handles common & language-specific rules) ./install.sh typescript # or python or golang # You can pass multiple languages: # ./install.sh typescript python golang # or target cursor installation: # ./install.sh --target cursor typescript ``` For manual installation instructions, see the README in the `rules/` folder. ### Step 3: Get Started ```bash # Try a command (use namespace form with plugin installed) /everything-claude-code:plan "Add user authentication" # Manual installation (option 2) uses shorthand form: # /plan "Add user authentication" # List available commands /plugin list everything-claude-code@everything-claude-code ``` ✨ **Done!** You now have access to 13 agents, 56 skills, and 32 commands. --- ## 🌐 Cross-Platform Support The plugin now fully supports **Windows, macOS, and Linux**. All hooks and scripts have been rewritten using 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**: Detection from 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. ## 📦 What's Inside This repository is a **Claude Code plugin** - you can install it directly or copy the components manually. ``` everything-claude-code/ |-- .claude-plugin/ # Plugin and marketplace manifest files | |-- plugin.json # Plugin metadata and component paths | |-- marketplace.json # Marketplace directory for /plugin marketplace add | |-- agents/ # 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 security review | |-- security-reviewer.md # Vulnerability analysis | |-- build-error-resolver.md # Build error fixing | |-- e2e-runner.md # Playwright E2E testing | |-- refactor-cleaner.md # Deprecated code cleanup | |-- doc-updater.md # Document synchronization update | |-- go-reviewer.md # Go code review | |-- go-build-resolver.md # Go build error fixing | |-- python-reviewer.md # Python code review (new) | |-- database-reviewer.md # Database/Supabase review (new) | |-- skills/ # Workflow definitions and domain knowledge | |-- coding-standards/ # Language best practices | |-- clickhouse-io/ # ClickHouse analysis, queries, data engineering | |-- backend-patterns/ # API, database, caching patterns | |-- frontend-patterns/ # React, Next.js patterns | |-- frontend-slides/ # HTML slides and PPTX to web demo workflow (new) | |-- article-writing/ # Long-form writing with specified tone, no AI jargon (new) | |-- content-engine/ # Multi-platform social content and reuse workflow (new) | |-- market-research/ # Market, competitor, and investor research with code references (new) | |-- investor-materials/ # Business plans, one-pagers, memos, and financial models (new) | |-- investor-outreach/ # Personalized fundraising outreach and follow-up (new) | |-- continuous-learning/ # Automatic pattern extraction from conversations (detailed guide) | |-- continuous-learning-v2/ # Instinct-based learning system with confidence scoring | |-- iterative-retrieval/ # Progressive context refinement for subagents | |-- strategic-compact/ # Manual compaction suggestions (detailed guide) | |-- tdd-workflow/ # TDD methodology | |-- security-review/ # Security self-audit checklist | |-- eval-harness/ # Validation loop evaluation (detailed guide) | |-- verification-loop/ # Continuous verification (detailed guide) | |-- golang-patterns/ # Go idioms and best practices | |-- golang-testing/ # Go testing patterns, TDD, benchmarking | |-- cpp-coding-standards/ # C++ coding standards from C++ Core Guidelines (new) | |-- cpp-testing/ # C++ testing with GoogleTest, CMake/CTest (new) | |-- django-patterns/ # Django patterns, models, views (new) | |-- django-security/ # Django security best practices (new) | |-- django-tdd/ # Django TDD workflow (new) | |-- django-verification/ # Django validation loop (new) | |-- python-patterns/ # Python idioms and best practices (new) | |-- python-testing/ # Python testing with pytest (new) | |-- springboot-patterns/ # Java Spring Boot patterns (new) | |-- springboot-security/ # Spring Boot security (new) | |-- springboot-tdd/ # Spring Boot TDD (new) | |-- springboot-verification/ # Spring Boot verification (new) | |-- configure-ecc/ # Interactive setup wizard (new) | |-- security-scan/ # AgentShield security audit integration (new) | |-- java-coding-standards/ # Java coding standards (new) | |-- jpa-patterns/ # JPA/Hibernate patterns (new) | |-- postgres-patterns/ # PostgreSQL optimization patterns (new) | |-- nutrient-document-processing/ # Document processing with Nutrient API (new) | |-- project-guidelines-example/ # Project-specific skill templates | |-- database-migrations/ # Migration patterns (Prisma, Drizzle, Django, Go) (new) | |-- api-design/ # REST API design, pagination, error responses (new) | |-- deployment-patterns/ # CI/CD, Docker, health checks, rollbacks (new) | |-- docker-patterns/ # Docker Compose, networking, volumes, container security (new) | |-- e2e-testing/ # Playwright E2E patterns and page object model (POM) (new) | |-- content-hash-cache-pattern/ # SHA-256 content hash cache for file processing (new) | |-- cost-aware-llm-pipeline/ # LLM cost optimization, model routing, budget tracking (new) | |-- regex-vs-llm-structured-text/ # Decision framework: regex vs LLM text parsing (new) | |-- swift-actor-persistence/ # Thread-safe Swift data persistence with actors (new) | |-- swift-protocol-di-testing/ # Protocol-based DI for testable Swift code (new) | |-- search-first/ # Pre-coding research workflow (new) | |-- skill-stocktake/ # Skill and command quality audit (new) | |-- liquid-glass-design/ # iOS 26 Liquid Glass design system (new) | |-- foundation-models-on-device/ # Apple on-device LLM with FoundationModels (new) | |-- swift-concurrency-6-2/ # Swift 6.2 concurrency (new) | |-- autonomous-loops/ # Autonomous loop patterns: sequential pipelines, PR loops, DAG orchestration (new) | |-- plankton-code-quality/ # Code quality enforcement with Plankton hooks (new) | |-- commands/ # Slash commands for quick execution | |-- tdd.md # /tdd - Test-Driven Development | |-- plan.md # /plan - Implementation planning | |-- e2e.md # /e2e - E2E testing generation | |-- code-review.md # /code-review - Quality review | |-- build-fix.md # /build-fix - Build error fixing | |-- refactor-clean.md # /refactor-clean - Deprecated code removal | |-- learn.md # /learn - Conversation-based pattern extraction (detailed guide) | |-- learn-eval.md # /learn-eval - Pattern extraction, evaluation, and saving (new) | |-- checkpoint.md # /checkpoint - Save validation state (detailed guide) | |-- verify.md # /verify - Run validation loop (detailed guide) | |-- setup-pm.md # /setup-pm - Package manager configuration | |-- go-review.md # /go-review - Go code review (new) | |-- go-test.md # /go-test - Go TDD workflow (new) | |-- go-build.md # /go-build - Go build error fixing (new) | |-- skill-create.md # /skill-create - Skill creation 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 related instincts into skills | |-- pm2.md # /pm2 - PM2 service lifecycle management (new) | |-- multi-plan.md # /multi-plan - Multi-agent task decomposition (new) | |-- multi-execute.md # /multi-execute - Orchestrated multi-agent workflow (new) | |-- multi-backend.md # /multi-backend - Multi-service backend orchestration (new) | |-- multi-frontend.md # /multi-frontend - Multi-service frontend orchestration (new) | |-- multi-workflow.md # /multi-workflow - General multi-service workflow (new) | |-- orchestrate.md # /orchestrate - Multi-agent coordination | |-- sessions.md # /sessions - Session history management | |-- eval.md # /eval - Evaluation based on guidelines | |-- test-coverage.md # /test-coverage - Test coverage analysis | |-- update-docs.md # /update-docs - Document update | |-- update-codemaps.md # /update-codemaps - Code map update | |-- python-review.md # /python-review - Python code review (new) | |-- rules/ # Guidelines to follow (copy to ~/.claude/rules/) | |-- README.md # Structure overview and installation guide | |-- common/ # Language-agnostic principles | | |-- coding-style.md # Immutability, file organization | | |-- git-workflow.md # Commit format, PR process | | |-- testing.md # TDD, 80% coverage requirement | | |-- performance.md # Model selection, context management | | |-- patterns.md # Design patterns, skeleton projects | | |-- hooks.md # Hook architecture, TodoWrite | | |-- agents.md # When to delegate to subagents | | |-- security.md # Mandatory security checks | |-- typescript/ # TypeScript/JavaScript specific | |-- python/ # Python specific | |-- golang/ # Go specific | |-- hooks/ # Trigger-based automation | |-- README.md # Hook documentation, recipes, and customization guide | |-- hooks.json # All hook configurations (PreToolUse, PostToolUse, Stop, etc.) | |-- memory-persistence/ # Session lifecycle hooks (detailed guide) | |-- strategic-compact/ # Compaction suggestions (detailed guide) | |-- scripts/ # Cross-platform Node.js scripts (new) | |-- lib/ # Shared utilities | | |-- utils.js # Cross-platform file/path/system utilities | | |-- 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 # Save state before compaction | | |-- suggest-compact.js # Strategic compaction suggestions | | |-- evaluate-session.js # Pattern extraction from conversations | |-- setup-package-manager.js # Interactive PM setup | |-- tests/ # Test suite (new) | |-- lib/ # Library tests | |-- hooks/ # Hook tests | |-- run-all.js # Run all tests | |-- contexts/ # Dynamic system prompts injection context (detailed guide) | |-- dev.md # Development mode context | |-- review.md # Code review mode context | |-- research.md # Research/exploration mode context | |-- examples/ # Example configurations and sessions | |-- CLAUDE.md # Example project-level configuration | |-- user-CLAUDE.md # Example user-level configuration | |-- saas-nextjs-CLAUDE.md # Real SaaS (Next.js + Supabase + Stripe) | |-- go-microservice-CLAUDE.md # Real Go microservice (gRPC + PostgreSQL) | |-- django-api-CLAUDE.md # Real Django REST API (DRF + Celery) | |-- rust-api-CLAUDE.md # Real Rust API (Axum + SQLx + PostgreSQL) (new) | |-- mcp-configs/ # MCP server configurations | |-- mcp-servers.json # GitHub, Supabase, Vercel, Railway, etc. | |-- marketplace.json # Self-hosted marketplace configuration (for /plugin marketplace add) ``` --- ## 🛠️ Ecosystem Tools ### Skill Creator There are two ways to generate Claude Code skills from your repository: #### Option A: Local Analysis (built-in) Use the `/skill-create` command for local analysis without external services: ```bash /skill-create # Analyze the current repository /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 GitHub App](https://github.com/apps/skill-creator) | [ecc.tools](https://ecc.tools) ```bash # Comment on any issue: /skill-creator analyze ``` # Tool List ## Or Automatically Trigger on Push to Default Branch Both options will create: - **SKILL.md files** - directly usable by Claude Code - **Instinct collections** - for continuous-learning-v2 - **Pattern extraction** - learn from your commit history ### AgentShield — Security Auditor > Built during Claude Code hackathon (Cerebral Valley x Anthropic, Feb 2026). Contains 1282 tests, 98% coverage, 102 static analysis rules. Scan your Claude Code configuration for vulnerabilities, misconfigurations, and injection risks. ```bash # Quick scan (no installation) npx ecc-agentshield scan # Automatically fix security issues npx ecc-agentshield scan --fix # Deep analysis with three Opus 4.6 agents npx ecc-agentshield scan --opus --stream # Generate a secure configuration from scratch npx ecc-agentshield init ``` **Scan scope:** CLAUDE.md, settings.json, MCP configurations, Hooks, Agent definitions, and 5 categories of skills — key detection (14 patterns), permissions audit, hook injection analysis, MCP server risk analysis, and agent configuration review. The **`--opus` flag** runs three Claude Opus 4.6 agents in a red-team/blue-team/auditor pipeline. Attackers look for attack chains, defenders assess defenses, and auditors integrate both into a prioritized risk assessment. This is adversarial reasoning, not just pattern matching. **Output formats:** Terminal (colored grading A-F), JSON (for CI pipelines), Markdown, HTML. Exit code 2 on severe findings for build gates. Use in Claude Code with `/security-scan`, or add to CI via [GitHub Action](https://github.com/affaan-m/agentshield). [GitHub](https://github.com/affaan-m/agentshield) | [npm](https://www.npmjs.com/package/ecc-agentshield) ### 🔬 Plankton — Code Quality Enforcement at Write-Time Plankton (thanks to @alxfazio) is a recommended code quality enforcement companion. It runs formatters and 20+ linters on every file edit via the PostToolUse hook, then spawns Claude sub-processes (routed to Haiku/Sonnet/Opus based on violation complexity) to fix missing issues in the main agent. Three-stage architecture: silent auto-formatting (solves 40-50% of issues), collects remaining violations into structured JSON, and delegates fixes to sub-processes. Includes configuration protection hooks to prevent agents from modifying linter configurations for passing checks. Supports Python, TypeScript, Shell, YAML, JSON, TOML, Markdown, and Dockerfile. Use with AgentShield for security + quality coverage. See `skills/plankton-code-quality/` for full integration guide. ### 🧠 Continuous Learning v2 The learning-based system automatically learns your patterns: ```bash /instinct-status # Show learned instincts and their confidence /instinct-import <file> # Import other's instincts /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** Due to changes in how the plugin system handles hooks, this plugin requires Claude Code CLI v2.1.0+. Check your version: ```bash claude --version ``` ### Important Note: Hook Auto-Loading Behavior > ⚠️ **To contributors:** Do not add the `"hooks"` field in `.claude-plugin/plugin.json`. This is enforced by regression tests. Claude Code v2.1+ automatically loads `hooks/hooks.json` from any installed plugin. Explicitly declaring it causes duplicate detection errors: ``` Duplicate hooks file detected: ./hooks/hooks.json resolves to already-loaded file ``` **Background:** This caused repeated fix/re-roll 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)). We've added regression tests to prevent such issues. ## 📥 Installation ### Option 1: Install as a Plugin (Recommended) The easiest way to use this repo is to 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 it 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 } } ``` This gives you immediate access to all commands, agents, skills, and hooks. > **Note:** The Claude Code plugin system currently doesn't support distributing `rules` via plugins ([upstream limitation](https://code.claude.com/docs/en/plugins-reference)). You need to install rules manually: > > ```bash > # Clone the repo first > git clone https://github.com/affaan-m/everything-claude-code.git > > # Option A: User-level rules (apply to all projects) > mkdir -p ~/.claude/rules > cp -r everything-claude-code/rules/common/* ~/.claude/rules/ > cp -r everything-claude-code/rules/typescript/* ~/.claude/rules/ # Pick your tech stack > cp -r everything-claude-code/rules/python/* ~/.claude/rules/ > cp -r everything-claude-code/rules/golang/* ~/.claude/rules/ > > # Option B: Project-level rules (only for the current project) > mkdir -p .claude/rules > cp -r everything-claude-code/rules/common/* .claude/rules/ > cp -r everything-claude-code/rules/typescript/* .claude/rules/ # Pick your tech stack > ``` ### 🔧 Option 2: Manual Installation If you prefer manual control over the installation: ```bash # Clone the repo git clone https://github.com/affaan-m/everything-claude-code.git # Copy agents to your Claude config dir cp everything-claude-code/agents/*.md ~/.claude/agents/ # Copy rules (common + language-specific) cp -r everything-claude-code/rules/common/* ~/.claude/rules/ cp -r everything-claude-code/rules/typescript/* ~/.claude/rules/ # Pick your tech stack cp -r everything-claude-code/rules/python/* ~/.claude/rules/ cp -r everything-claude-code/rules/golang/* ~/.claude/rules/ # Copy commands cp everything-claude-code/commands/*.md ~/.claude/commands/ # Copy skills (core vs. niche) # Recommended (new users): Install only core/general skills cp -r everything-claude-code/.agents/skills/* ~/.claude/skills/ cp -r everything-claude-code/skills/search-first ~/.claude/skills/ # Optional: Add niche/framework-specific skills only as needed # for s in django-patterns django-tdd springboot-patterns; do # cp -r everything-claude-code/skills/$s ~/.claude/skills/ # done ``` #### Add Hooks to settings.json Copy hooks from `hooks/hooks.json` into your `~/.claude/settings.json`. #### Configure MCPs Copy required MCP servers from `mcp-configs/mcp-servers.json` into your `~/.claude.json`. **Important:** Replace `YOUR_*_HERE` placeholders with your actual API keys. ## 🎯 Key Concepts ### Agents Subagents handle scoped, delegated tasks. Example: ```markdown --- name: code-reviewer description: Review code quality, security, and maintainability tools: ["Read", "Grep", "Glob", "Bash"] model: opus --- You are a seasoned code reviewer... ``` ### Skills Skills are workflow definitions invoked by commands or agents: ```markdown # TDD workflow 1. Define the interface 2. Write a failing test (RED) 3. Implement minimal code (GREEN) 4. Refactor (IMPROVE) 5. Verify 80%+ coverage ``` ### Hooks Hooks trigger on tool events. Example — warn on console.log: ```json { "matcher": "tool == \"Edit\" && tool_input.file_path matches \"\\\\.(ts|tsx|js|jsx)$\"", "hooks": [{ "type": "command", "command": "#!/bin/bash\ngrep -n 'console\\.log' \"$file_path\" && echo '[Hook] Remove console.log' >&2" }] } ``` ### Rules Rules are guidelines to follow, organized in `common/` (language-agnostic) + language-specific dirs: ``` rules/ common/ # General principles (always install) typescript/ # TS/JS specific patterns and tools python/ # Python specific patterns and tools golang/ # Go specific patterns and tools ``` See [`rules/README.md`](rules/README.md) for installation and structure details. ## 🗺️ Which Agent Should I Use? Unsure where to start? Refer to this quick guide: | I want to... | Use this command | Use agent | |--------------|-----------------|------------| | Plan a new feature | `/everything-claude-code:plan "Add authentication"` | planner | | Design system architecture | `/everything-claude-code:plan` + architect agent | architect | | Write tests before code | `/tdd` | tdd-guide | | Review my code | `/code-review` | code-reviewer | | Fix build failures | `/build-fix` | build-error-resolver | | Run end-to-end (E2E) tests | `/e2e` | e2e-runner | | Find security vulnerabilities | `/security-scan` | security-reviewer | | Remove deprecated code | `/refactor-clean` | refactor-cleaner | | Update documentation | `/update-docs` | doc-updater | | Review Go code | `/go-review` | go-reviewer | | Review Python code | `/python-review` | python-reviewer | | Audit database queries | *(auto-delegate)* | database-reviewer | ### Common Workflows **Start a new feature:** ``` /everything-claude-code:plan "Add user authentication with OAuth" → planner creates an implementation blueprint /tdd → tdd-guide enforces test-first /code-review → code-reviewer checks your work ``` **Fix a bug:** ``` /tdd → tdd-guide: write a failing test reproducing the issue → implement fix, verify test passes /code-review → code-reviewer: catch regression issues ``` **Prepare for production release:** ``` /security-scan → security-reviewer: OWASP Top 10 audit /e2e → e2e-runner: critical user flow testing /test-coverage → verify 80%+ coverage ``` ## ❓ FAQ <details> <summary><b>How to check which agents/commands are installed?</b></summary> ```bash /plugin list everything-claude-code@everything-claude-code ``` This will show all available agents, commands, and skills in the plugin. </details> <details> <summary><b>My hooks aren't working / I see a "Duplicate hooks file" error</b></summary> This is the most common issue. **Do not add the `"hooks"` field in `.claude-plugin/plugin.json`.** Claude Code v2.1+ automatically loads `hooks/hooks.json` from installed plugins. Explicit declaration causes duplicate detection errors. See [#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). </details> <details> <summary><b>My context window is shrinking / Claude runs out of context</b></summary> Excessive MCP servers consume your context. Each MCP tool description consumes tokens from your 200k window, potentially reducing it to ~70k. **Solution:** Disable unused MCPs per project: ```json // In project's .claude/settings.json { "disabledMcpServers": ["supabase", "railway", "vercel"] } ``` Keep fewer than 10 MCPs enabled and fewer than 80 active tools. </details> <details> <summary><b>Can I use only some components (e.g., just agents)?</b></summary> Yes. Use option 2 (manual installation) and copy only what you need: ```bash # Only agents cp everything-claude-code/agents/*.md ~/.claude/agents/ ``` # Tool List ## Only Rules cp -r everything-claude-code/rules/common/* ~/.claude/rules/ Each component is completely independent. </details> <details> <summary><b>Does this apply to Cursor / OpenCode / Codex?</b></summary> Yes. ECC is cross-platform: - **Cursor**: Pre-translated configurations are located in `.cursor/`. See [Cursor IDE Support](#cursor-ide-support). - **OpenCode**: Full plugin support is located in `.opencode/`. See [OpenCode Support](#-opencode-support). - **Codex**: First-class support with adapter offset protection and SessionStart downgrade. See PR [#257](https://github.com/affaan-m/everything-claude-code/pull/257). - **Claude Code**: Native support — this is the primary target. </details> <details> <summary><b>How to contribute new skills or agents?</b></summary> See [CONTRIBUTING.md](CONTRIBUTING.md). Short version: 1. Fork this repository 2. Create your skill in `skills/your-skill-name/SKILL.md` (with YAML Frontmatter) 3. Or create an agent in `agents/your-agent.md` 4. Submit a PR with a clear description of its functionality and use cases </details> --- ## 🧪 Running Tests The plugin includes a comprehensive test suite: ```bash # Run all tests node tests/run-all.js # Run individual test files node tests/lib/utils.test.js node tests/lib/package-manager.test.js node tests/hooks/hooks.test.js ``` --- ## 🤝 Contributing **Contributions are welcome and encouraged.** This repository aims to be a community resource. If you have: - Useful agents or skills - Clever hooks - Better MCP configurations - Improved rules Please contribute! Guidelines are in [CONTRIBUTING.md](CONTRIBUTING.md). ### Contribution Ideas - Language-specific skills (Rust, C#, Swift, Kotlin) — already includes Go, Python, Java - Framework-specific configurations (Rails, Laravel, FastAPI, NestJS) — already includes Django, Spring Boot - DevOps agents (Kubernetes, Terraform, AWS, Docker) - Testing strategies (different frameworks, visual regression) - Domain-specific knowledge (machine learning, data engineering, mobile) --- ## Cursor IDE Support ECC provides **complete Cursor IDE support**, including hooks, rules, agents, skills, commands, and MCP configurations tailored for Cursor's native format. ### Quick Start (Cursor) ```bash # Install for your language ./install.sh --target cursor typescript ./install.sh --target cursor python golang swift ``` ### Included Content | Component | Quantity | Details | |-----------|-------|---------| | Hook Events | 15 | sessionStart, beforeShellExecution, afterFileEdit, beforeMCPExecution, beforeSubmitPrompt, and 10 more | | Hook Scripts | 16 | Minimalist Node.js scripts that delegate to `scripts/hooks/` via shared adapters | | Rules | 29 | 9 general rules (alwaysApply) + 20 language-specific rules (TypeScript, Python, Go, Swift) | | Agents | Shared | via root AGENTS.md (native Cursor reads) | | Skills | Shared + Packaged | via root AGENTS.md and translated supplements in `.cursor/skills/` | | Commands | Shared | if installed, in `.cursor/commands/` | | MCP Config | Shared | if installed, in `.cursor/mcp.json` | ### Hook Architecture (DRY Adapter Pattern) Cursor has **more hook events than Claude Code** (20 vs 8). The `.cursor/hooks/adapter.js` module converts Cursor's stdin JSON into Claude Code's format, allowing reuse of existing `scripts/hooks/*.js` without duplication. ``` Cursor stdin JSON → adapter.js → conversion → scripts/hooks/*.js (shared with Claude Code) ``` Key Hooks: - **beforeShellExecution** — prevent development servers from running outside tmux (exit 2), review git push - **afterFileEdit** — auto-formatting + TypeScript checks + console.log warnings - **beforeSubmitPrompt** — detect keys in prompts (sk-, ghp_, AKIA patterns) - **beforeTabFileRead** — prevent Tab from reading .env, .key, .pem files (exit 2) - **beforeMCPExecution / afterMCPExecution** — MCP audit logging ### Rules Format Cursor rules use YAML Frontmatter with `description`, `globs`, and `alwaysApply`: ```yaml --- description: "Extend general rules with TypeScript coding style" globs: ["**/*.ts", "**/*.tsx", "**/*.js", "**/*.jsx"] alwaysApply: false --- ``` --- ## Codex CLI Support ECC provides **first-class Codex CLI support**, including reference configurations, Codex-specific AGENTS.md supplements, and 16 ported skills. ### Quick Start (Codex) ```bash # Copy reference config to your user directory cp .codex/config.toml ~/.codex/config.toml # Run Codex in the repository — it will auto-detect AGENTS.md codex ``` ### Included Content | Component | Quantity | Details | |-----------|-------|---------| | Config | 1 | `.codex/config.toml` — models, permissions, MCP server, persistence instructions | | AGENTS.md | 2 | root (general) + `.codex/AGENTS.md` (Codex-specific supplements) | | Skills | 16 | `.agents/skills/` — each skill contains SKILL.md + agents/openai.yaml | | MCP Servers | 4 | GitHub, Context7, Memory, Sequential Thinking (command-based) | | Profiles | 2 | `strict` (read-only sandbox) and `yolo` (fully automated confirmations) | ### Skills Skills under `.agents/skills/` are automatically loaded by Codex: | Skill | Description | |-------|-------------| | tdd-workflow | 80%+ coverage test-driven development | | security-review | comprehensive security checklist | | coding-standards | general coding standards | | frontend-patterns | React/Next.js patterns | | frontend-slides | HTML slides, PPTX conversion, visual style exploration | | article-writing | long-form writing based on notes and voice references | | content-engine | platform-native social content and reuse | | market-research | market and competitor research with source code references | | investor-materials | business plans, memos, models, and one-pagers | | investor-outreach | personalized outreach, follow-ups, and intro blurbs | | backend-patterns | API design, databases, caching | | e2e-testing | Playwright E2E testing | | eval-harness | evaluation-driven development | | strategic-compact | context management | | api-design | REST API design patterns | | verification-loop | build, test, lint, type check, security | ### Key Limitations Codex CLI **currently does not support hooks** (OpenAI Codex Issue #2109, 430+ upvotes). Security enforcement is achieved through config.toml's `persistent_instructions` and a sandbox permission system. --- ## 🔌 OpenCode Support ECC provides **complete OpenCode support**, including plugins and hooks. ### Quick Start ```bash # Install OpenCode npm install -g opencode # Run in the repository root opencode ``` Configurations are detected automatically from `.opencode/opencode.json`. ### Feature Parity | Feature | Claude Code | OpenCode | Status | |---------|-------------|----------|--------| | Agents | ✅ 13 | ✅ 12 | **Claude Code leads** | | Commands | ✅ 33 | ✅ 24 | **Claude Code leads** | | Skills | ✅ 50+ | ✅ 37 | **Claude Code leads** | | Hooks | ✅ 8 event types | ✅ 11 events | **OpenCode has more!** | | Rules | ✅ 29 rules | ✅ 13 instructions | **Claude Code leads** | | MCP Servers | ✅ 14 | ✅ Full support | **Feature parity** | | Custom Tools | ✅ via hooks | ✅ 6 native tools | **OpenCode is better** | ### Hooks via Plugins OpenCode's plugin system is more complex, with 20+ event types: | Claude Code Hook | OpenCode Plugin Events | |-----------------|----------------------| | PreToolUse | `tool.execute.before` | | PostToolUse | `tool.execute.after` | | Stop | `session.idle` | | SessionStart | `session.created` | | SessionEnd | `session.deleted` | **Additional OpenCode events**: `file.edited`, `file.watcher.updated`, `message.updated`, `lsp.client.diagnostics`, `tui.toast.show`, etc. ### Available Commands (32) | Command | Description | |---------|-------------| | `/plan` | create implementation plan | | `/tdd` | enforce TDD workflow | | `/code-review` | review code changes | | `/build-fix` | fix build errors | | `/e2e` | generate E2E tests | | `/refactor-clean` | remove deprecated code | | `/orchestrate` | multi-agent workflow | | `/learn` | extract patterns from sessions | | `/checkpoint` | save verification state | | `/verify` | run verification loop | | `/eval` | evaluate against guidelines | | `/update-docs` | update documentation | | `/update-codemaps` | update codemaps | | `/test-coverage` | analyze coverage | | `/go-review` | Go code review | | `/go-test` | Go TDD workflow | | `/go-build` | fix Go build errors | | `/python-review` | Python code review (PEP 8, type hints, security) | | `/multi-plan` | multi-model collaborative planning | | `/multi-execute` | multi-model collaborative execution | | `/multi-backend` | backend-focused multi-model workflow | | `/multi-frontend` | frontend-focused multi-model workflow | | `/multi-workflow` | comprehensive multi-model development workflow | | `/pm2` | auto-generate PM2 service commands | | `/sessions` | manage session history | | `/skill-create` | generate skills from git | | `/instinct-status` | view learned instincts | | `/instinct-import` | import instincts | | `/instinct-export` | export instincts | | `/evolve` | cluster instincts into skills | | `/promote` | promote project instincts to global scope | | `/projects` | list known projects and instinct statistics | | `/learn-eval` | extract and evaluate patterns before saving | | `/setup-pm` | configure package manager | ### Plugin Installation **Option 1: Direct Usage** ```bash cd everything-claude-code opencode ``` **Option 2: Install as npm package** ```bash npm install ecc-universal ``` Then add to your `opencode.json`: ```json { "plugin": ["ecc-universal"] } ``` ### Documentation - **Migration Guide**: `.opencode/MIGRATION.md` - **OpenCode Plugin README**: `.opencode/README.md` - **Integration Instructions**: `.opencode/instructions/INSTRUCTIONS.md` - **LLM Documentation**: `llms.txt` (complete OpenCode documentation for LLMs) --- ## Cross-Tool Feature Parity ECC is **the first plugin to maximize utilization across major AI coding tools**. Here's a comparison across frameworks: | Feature | Claude Code | Cursor IDE | Codex CLI | OpenCode | |---------|------------|------------|-----------|----------| | **Agents** | 13 | Shared (AGENTS.md) | Shared (AGENTS.md) | 12 | | **Commands** | 33 | Shared | Instruction-based | 24 | | **Skills** | 50+ | Shared | 10 (native format) | 37 | | **Hook Events** | 8 types | 15 types | None | 11 types | | **Hook Scripts** | 9 scripts | 16 scripts (DRY adapter) | N/A | Plugin hooks | | **Rules** | 29 (general+language) | 29 (YAML Frontmatter) | Instruction-based | 13 instructions | | **Custom Tools** | via hooks | via hooks | N/A | 6 native tools | | **MCP Servers** | 14 | Shared (mcp.json) | 4 (command-based) | Full support | | **Config Format** | settings.json | hooks.json + rules/ | config.toml | opencode.json | | **Context Files** | CLAUDE.md + AGENTS.md | AGENTS.md | AGENTS.md | AGENTS.md | | **Key Detection** | via hooks | beforeSubmitPrompt hook | via sandbox | via hooks | | **Auto-Formatting** | PostToolUse hook | afterFileEdit hook | N/A | file.edited hook | | **Version** | Plugin | Plugin | Reference config | 1.6.0 | **Key Architectural Decisions:** - Root **AGENTS.md** is a universal, cross-tool file (read by all 4 tools) - **DRY Adapter Pattern** lets Cursor reuse Claude Code's hook scripts without duplication - **Skill Format** (SKILL.md with YAML Frontmatter) is reusable across Claude Code, Codex, and OpenCode - Codex's lack of hooks is mitigated by `persistent_instructions` and sandbox permissions --- ## 📖 Background I've been using Claude Code since its experimental release. In September 2025, I, along with [@DRodriguezFX](https://x.com/DRodriguezFX), developed [zenith.chat](https://zenith.chat) using Claude Code exclusively and won the Anthropic x Forum Ventures hackathon. These configurations have been battle-tested in multiple production-grade applications. --- ## Token Optimization If you're not managing token consumption, using Claude Code can be expensive. The following settings can significantly reduce costs without sacrificing quality. ### Recommended Settings Add to `~/.claude/settings.json`: ```json { "model": "sonnet", "env": { "MAX_THINKING_TOKENS": "10000", "CLAUDE_AUTOCOMPACT_PCT_OVERRIDE": "50" } } ``` | Setting | Default | Recommended | Impact | |---------|---------|-------------|--------| | `model` | opus | **sonnet** | ~60% cost reduction; can handle 80%+ of coding tasks | | `MAX_THINKING_TOKENS` | 31,999 | **10,000** | ~70% reduction in hidden thinking cost per request | | `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` | 95 | **50** | Compacting earlier - better quality in long conversations | Switch to Opus only when deep architecture reasoning is needed: ``` /model opus ``` ### Daily Workflow Commands | Command | When to Use | |---------|-------------| | `/model sonnet` | Default for most tasks | | `/model opus` | Complex architectures, debugging, deep reasoning | | `/clear` | Between unrelated tasks (free, instant reset) | | `/compact` | At logical task breakpoints (research completed, milestones achieved) | | `/cost` | Monitor token spend during a conversation | ### Strategic Compaction The `strategic-compact` skill suggests performing `/compact` at logical breakpoints rather than relying on automatic compaction at 95% context. See `skills/strategic-compact/SKILL.md` for the full decision guide. **When to compact:** - After research/exploration, before implementing code - After completing a milestone, before starting the next - After debugging, before continuing feature development - After a failed approach, before trying a new one **When not to compact:** - During implementation (you'll lose variable names, file paths, partial state) ### Context Window Management **Critical:** Don't enable all MCPs at once. Each MCP tool consumes tokens from your 200k window, potentially reducing it to ~70k. - Keep fewer than 10 MCPs enabled per project - Keep fewer than 80 active tools - Use `disabledMcpServers` in project configurations to disable unused services ### Agent Teams Cost Warning Agent teams incur multiple context windows. Each team member consumes tokens independently. Use parallelization only for tasks where it adds significant value (multi-module work, parallel reviews). For simple sequential tasks, subagents are more token-efficient. --- ## ⚠️ Important Notes ### Token Optimization Hit your daily limit? See **[Token Optimization Guide](docs/token-optimization.md)** for recommended settings and workflow suggestions. Quick wins: ```json // ~/.claude/settings.json { "model": "sonnet", "env": { "MAX_THINKING_TOKENS": "10000", "CLAUDE_AUTOCOMPACT_PCT_OVERRIDE": "50", "CLAUDE_CODE_SUBAGENT_MODEL": "haiku" } } ``` Use `/clear` between unrelated tasks, `/compact` at logical breakpoints, and `/cost` to monitor spend. ### Customization These configurations are tailored to my workflow. You should: 1. Start with what resonates 2. Adapt to your tech stack 3. Remove unused parts 4. Add your own patterns --- ## 💜 Sponsors This project is free and open-source. Sponsor support helps sustain its maintenance and growth. [**Become a Sponsor**](https://github.com/sponsors/affaan-m) | [Sponsor Tiers](SPONSORS.md) --- ## 🌟 Star History [](https://star-history.com/#affaan-m/everything-claude-code&Date) --- ## 🔗 Links - **Quick Start Guide (from here):** [Everything Claude Code Quick Start](https://x.com/affaanmustafa/status/2012378465664745795) - **Detailed Guide (advanced):** [Everything Claude Code Detailed Guide](https://x.com/affaanmustafa/status/2014040193557471352) - **Follow:** [@affaanmustafa](https://x.com/affaanmustafa) - **zenith.chat:** [zenith.chat](https://zenith.chat) - **Skills Catalog:** awesome-agent-skills (community-maintained catalog of agent skills) --- ## 📄 License MIT - Use freely, modify as needed, and contribute back if possible. --- **If this project helps you, star it. Read both guides. Build great products.**