affaan-m/everything-claude-code

🔥 Hot★ 174,582JavaScriptAudience · developerComplexity · 4/5ActiveLicenseSetup · moderate

Mindmap

mindmap
  root((repo))
    What it does
      Token optimization
      Memory persistence
      Security scanning
      Skill extraction
    How it works
      Manifest installer
      State tracking
      Hook system
      Git worktrees
    Supported harnesses
      Claude Code
      Cursor
      Codex
      Gemini
    Use cases
      Intensive agent workflows
      Multi-session learning
      Team operations
    Tech stack
      TypeScript
      Python
      Go
      Rust

mindmap root((repo)) What it does Token optimization Memory persistence Security scanning Skill extraction How it works Manifest installer State tracking Hook system Git worktrees Supported harnesses Claude Code Cursor Codex Gemini Use cases Intensive agent workflows Multi-session learning Team operations Tech stack TypeScript Python Go Rust

Things people build with this

USE CASE 1

Set up an AI coding agent with optimized prompts, security policies, and reusable skills without building them from scratch.

USE CASE 2

Run multiple coding sessions and automatically extract patterns into skills that the agent learns and reuses.

USE CASE 3

Manage token usage and model selection across different AI harnesses to reduce costs and latency.

USE CASE 4

Orchestrate subagents and parallelize work using git worktrees while tracking state across sessions.

Tech stack

TypeScriptPythonGoJavaPerlRustTkinter

Getting it running

Difficulty · moderate Time to first run · 30min

Multi-language support (TypeScript, Python, Go, Java, Perl, Rust) requires appropriate runtimes installed; Tkinter GUI dependency may need system-level setup on some platforms.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

In plain English

Everything Claude Code is a performance optimization system for AI agent harnesses, the wrappers people use to run AI coding agents on their machines. Rather than just shipping configs, it bundles skills, instincts, memory optimization, continuous learning, security scanning, and a research-first development workflow into one set of plug-in components, plus rules, hooks, MCP configurations, and legacy command shims. It works across multiple harnesses including Claude Code, Codex, Cursor, OpenCode, and Gemini. It works by giving you a manifest-driven installer that places agents, skills, hooks, and rules into your harness configuration, with a state store that tracks what's installed and supports incremental updates. The system covers token optimization (model selection and slimming system prompts), memory persistence across sessions through hooks, automatic extraction of patterns from sessions into reusable skills, verification loops with grader types and pass@k metrics, parallelization via git worktrees, and subagent orchestration. Recent releases added a Tkinter desktop dashboard, an operator-workflow lane (brand voice, social-graph ranker, billing ops, Google Workspace ops, etc.), media tooling (Manim video, Remotion), and an alpha Rust control-plane prototype. You'd use this if you're running an AI coding agent intensively and want a tested system layer rather than building skills, hooks, and security policies yourself. The repository is a multi-language codebase including TypeScript, Python, Go, Java, Perl, Markdown, and shell, with rules covering 12 language ecosystems. It's MIT-licensed and the README states it's evolved over 10+ months of daily use building real products. The full README is longer than what was provided.

Copy-paste prompts

Prompt 1

I'm using Claude Code / Cursor / Codex intensively. How do I install Everything Claude Code and set up the manifest to add skills and hooks to my harness?

Prompt 2

Show me how to use the token optimization and memory persistence features to reduce my AI agent's costs and improve learning across sessions.

Prompt 3

How do I extract patterns from my agent's past sessions into reusable skills using the automatic skill extraction system?

Prompt 4

Walk me through setting up the security scanning and verification loops with grader types to validate my agent's outputs.

Prompt 5

How do I use the Tkinter dashboard to monitor and manage my AI agent's performance and installed components?

Open on GitHub → Explain another repo

Generated 2026-05-21 · Model: sonnet-4-6 · Verify against the repo before relying on details.