Everything Claude Code

Active
GitHub JavaScript MIT

Description

The agent harness performance optimization system with skills, instincts, memory, security and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Key Features

  • Cross-harness compatibility - Works with Codex, Claude Code, Cursor, OpenCode, Gemini, Zed, GitHub Copilot, and more
  • Skills and instincts system - 63 agents, 251 skills, and 79 legacy command shims as reusable behavior modules
  • Memory persistence - Hooks automatically save and load context across sessions for continuous memory
  • Security scanning - Built-in AgentShield module with attack vector detection, sandboxing, and input sanitization
  • Continuous learning - Auto-extracts patterns from sessions into reusable skills; agent improves over time
  • Token optimization - Model selection strategies, system prompt slimming, and background process management

Use Cases

💡 Add memory persistence to Claude Code or Codex so the agent retains project context across sessions
💡 Use security scanning to automatically detect vulnerabilities and dangerous operations during coding
💡 Accumulate best practices from daily development via continuous learning for a team-specific knowledge base
💡 Share unified skill configurations across multiple AI coding tools for consistent workflows

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (246.4k stars)
  • Permissive open-source license (MIT)
  • Responsive to issues, low backlog

Quick Start

# Install ECC universal package via npm
npm install -g ecc-universal

# Load ECC skills in Claude Code
# Copy skill files from skills/ to .claude/skills/
# The agent will automatically detect and apply skill modules

# Or clone the repo for full configuration
git clone https://github.com/affaan-m/everything-claude-code.git
cd everything-claude-code

Related Projects

Get Shit Done

64.6k · JavaScript
Stale B

A light-weight and powerful meta-prompting, context engineering, and spec-driven development system for AI coding agents like Claude Code.

codingagenttools +1
  • · Context engineering framework - Fresh-context subagents solve context rot (quality degradation as context window fills)
  • · Five-phase development loop - Disciplined Discuss → Plan → Execute → Verify → Ship iteration cycle
  • · Multi-runtime compatible - Supports Claude Code, OpenCode, Gemini CLI, Codex, Cursor, Windsurf and other AI coding tools

Costrict

4.4k · TypeScript
Active A+

Strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, and AI Completion.

typescriptcodingagent +2
  • · Strict Mode: standardizes AI code generation with requirements analysis, architecture design, task planning, and test generation
  • · Code Review: repository-wide RAG-based code analysis with multi-expert model verification
  • · Code Completion: context-aware code generation in seconds with multi-language support