Skip to main content

Everything Claude Code

The performance optimization system for AI agent harnesses. From an Anthropic hackathon winner. Not just configs. A complete system: skills, instincts, memory optimization, continuous learning, security scanning, and research-first development. Production-ready agents, hooks, commands, rules, and MCP configurations evolved over 10+ months of intensive daily use building real products. Works across Claude Code, Cursor, Codex, OpenCode, and other AI agent harnesses.
This repo is the raw code only. The Shorthand Guide and Longform Guide explain everything.

Key Features

13 Specialized Agents

Production-ready agents for planning, architecture, TDD, code review, security, build fixing, E2E testing, refactoring, and documentation.

56+ Skills

Workflow definitions and domain knowledge covering coding standards, backend/frontend patterns, security, testing, continuous learning, and framework-specific best practices.

33 Commands

Slash commands for quick execution: /plan, /tdd, /code-review, /build-fix, /e2e, /security-scan, /orchestrate, and more.

Automated Hooks

Trigger-based automations for memory persistence, strategic compaction, security warnings, format-on-save, and session management.

Multi-Language Rules

Always-follow guidelines organized into common (language-agnostic) + language-specific directories for TypeScript, Python, Go, Swift, Java, and C++.

Cross-Platform

Full support for Windows, macOS, and Linux with automatic package manager detection (npm, pnpm, yarn, bun).

What’s Inside

Agents

14 specialized subagents handle delegated tasks with limited scope:
  • planner - Feature implementation planning
  • architect - System design decisions
  • tdd-guide - Test-driven development enforcement
  • code-reviewer - Quality and security review
  • security-reviewer - Vulnerability analysis
  • build-error-resolver - Build and type error fixing
  • e2e-runner - Playwright E2E testing
  • refactor-cleaner - Dead code cleanup
  • doc-updater - Documentation synchronization
  • go-reviewer - Go code review
  • go-build-resolver - Go build error resolution
  • python-reviewer - Python code review (PEP 8, type hints, security)
  • database-reviewer - Database/Supabase review
  • chief-of-staff - Multi-agent orchestration

Skills (56+)

Workflow definitions invoked by commands or agents: Core Skills:
  • coding-standards, tdd-workflow, security-review, eval-harness, verification-loop
  • continuous-learning, continuous-learning-v2, strategic-compact, iterative-retrieval
Backend/Frontend:
  • backend-patterns, frontend-patterns, frontend-slides, api-design, e2e-testing
Framework-Specific:
  • django-patterns, django-security, django-tdd, django-verification
  • springboot-patterns, springboot-security, springboot-tdd, springboot-verification
  • golang-patterns, golang-testing, swift-actor-persistence, swift-protocol-di-testing
Business/Content:
  • article-writing, content-engine, market-research, investor-materials, investor-outreach
Infrastructure:
  • deployment-patterns, docker-patterns, database-migrations, postgres-patterns

Commands (33)

Slash commands for instant execution:
  • /plan - Implementation planning
  • /tdd - Test-driven development
  • /code-review - Quality review
  • /build-fix - Fix build errors
  • /e2e - E2E test generation
  • /refactor-clean - Dead code removal
  • /orchestrate - Multi-agent workflow
  • /learn - Extract patterns mid-session
  • /checkpoint - Save verification state
  • /verify - Run verification loop
  • /eval - Evaluate against criteria
  • /update-docs - Update documentation
  • /test-coverage - Analyze coverage
  • /go-review, /go-test, /go-build - Go workflows
  • /python-review - Python code review
  • /multi-plan, /multi-execute, /multi-backend, /multi-frontend, /multi-workflow - Multi-agent orchestration
  • /pm2 - PM2 service management
  • /sessions - Session history
  • /skill-create - Generate skills from git
  • /instinct-status, /instinct-import, /instinct-export, /evolve - Continuous learning
  • /setup-pm - Configure package manager

Hooks

Trigger-based automations:
  • Session lifecycle - Load/save context automatically
  • Strategic compaction - Suggest compaction at logical breakpoints
  • Security warnings - Detect hardcoded secrets, prevent credential commits
  • Format-on-save - Auto-format TypeScript/Python/Go files
  • Dev server guards - Block dev servers outside tmux
  • Git push review - Reminder before pushing changes

Rules

Always-follow guidelines organized by language: Common (9 rules):
  • coding-style, git-workflow, testing, performance, patterns, hooks, agents, security
Language-Specific:
  • TypeScript/JavaScript (7 rules)
  • Python (5 rules)
  • Go (4 rules)
  • Swift (3 rules)
  • Java (2 rules)

Get Started

Quick Start

Get up and running in under 2 minutes

Installation

Detailed installation options and platform-specific notes

Key Concepts

Learn about agents, skills, hooks, and rules

Cross-Platform Support

Everything Claude Code works across all major AI coding tools:
FeatureClaude CodeCursor IDECodex CLIOpenCode
Agents✅ 13 agentsShared (AGENTS.md)Shared (AGENTS.md)✅ 12 agents
Commands✅ 33 commandsSharedInstruction-based✅ 24 commands
Skills✅ 50+ skillsShared10 (native format)✅ 37 skills
Hook Events8 types15 typesNone yet11 types
Rules29 (common + lang)29 (YAML frontmatter)Instruction-based13 instructions
Custom ToolsVia hooksVia hooksN/A✅ 6 native tools
MCP Servers✅ 14 serversShared (mcp.json)4 (command-based)✅ Full

Why Everything Claude Code?

Evolved over 10+ months of intensive daily use building real products. Won the Anthropic x Forum Ventures hackathon in Sep 2025 building zenith.chat.
Not theoretical configs - these are the actual agents, skills, hooks, and rules used to ship production applications. Every component has been refined through real-world use.
Not just prompts or configs. A complete system with memory optimization, continuous learning, security scanning, verification loops, and multi-agent orchestration.
Includes search-first workflow, iterative retrieval patterns, and eval harness for verification. Learn from your sessions with continuous learning v2.
30+ contributors, 50K+ stars, 6K+ forks, 6 languages supported. Active development with regular updates and new features.

What’s New

v1.7.0 — Cross-Platform Expansion & Presentation Builder (Feb 2026)

  • Codex app + CLI support — Direct AGENTS.md-based Codex support, installer targeting, and Codex docs
  • frontend-slides skill — Zero-dependency HTML presentation builder with PPTX conversion guidance
  • 5 new generic business/content skillsarticle-writing, content-engine, market-research, investor-materials, investor-outreach
  • Broader tool coverage — Cursor, Codex, and OpenCode support tightened
  • 992 internal tests — Expanded validation and regression coverage

v1.6.0 — Codex CLI, AgentShield & Marketplace (Feb 2026)

  • Codex CLI support — New /codex-setup command generates codex.md
  • 7 new skillssearch-first, swift-actor-persistence, swift-protocol-di-testing, and more
  • AgentShield integration/security-scan skill runs AgentShield directly
  • GitHub Marketplace — ECC Tools GitHub App live with free/pro/enterprise tiers
  • 978 internal tests — Expanded validation suite
See the full changelog in Releases.

Requirements

Minimum version: Claude Code CLI v2.1.0 or laterThis plugin requires Claude Code CLI v2.1.0+ due to changes in how the plugin system handles hooks.Check your version:
claude --version

Next Steps

1

Quick Start

Follow the Quick Start Guide to get up and running in under 2 minutes.
2

Installation

Review the Installation Guide for detailed installation options.
3

Learn Concepts

Understand the Key Concepts behind agents, skills, hooks, and rules.
4

Explore Features

Dive into specific features like Continuous Learning and Token Optimization.