affaan-m/everything-claude-code
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Implements a modular skill and hook system with persistent memory across sessions via SQLite state stores, along with language-specific agents and rules for TypeScript, Python, Go, Java, Kotlin, Rust, and others. The architecture uses manifest-driven selective installation, runtime hook gating (`ECC_HOOK_PROFILE`), and harness commands (`/harness-audit`, `/loop-status`) for deterministic orchestration across Claude Code, Cursor, Codex, and OpenCode. AgentShield provides attack surface scanning and sanitization guards integrated into the verification loop alongside checkpoint and continuous evaluation strategies.
74,013 stars. Actively maintained with 577 commits in the last 30 days.
Stars
74,013
Forks
9,261
Language
JavaScript
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
577
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/affaan-m/everything-claude-code"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
bobmatnyc/claude-mpm
Claude Multi-Agent Project Manager — multi-channel orchestration, GitHub-first SDK mode, and...
VoltAgent/awesome-claude-code-subagents
A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code
nyldn/claude-octopus
Multi-LLM orchestration plugin for Claude Code — 8 providers (Codex, Gemini, Claude, Perplexity,...
wakehacker/wake-ai
AI orchestration framework for structured multi-step workflows with validation - build reliable...