affaan-m/ECC

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

What it solves

ECC provides a coordinated engineering system and toolbox for AI agents, transforming them from simple code writers into structured software engineers. It solves the problem of agents repeating the same basic engineering processes (planning, testing, reviewing) in every prompt by providing a persistent, reusable system of skills and workflows.

How it works

ECC acts as an "agent harness operating system" that integrates into various AI coding assistants (like Claude Code, Codex, Cursor, and others). It implements a structured engineering cycle: plan -> test -> implement -> review -> verify -> remember -> improve.

It provides a massive library of specialized resources:

  • Agents: 68 specialized agents for planning, security, architecture, and domain work.
  • Skills: 286 skills covering TDD, research, frontend, ML, and operations.
  • Hooks and Memory: Runtime systems for enforcement, session summaries, and continuous learning.
  • AgentShield: A security scanner for prompts, hooks, and secrets.
  • Rules: Selective standards based on language or project.

Who it’s for

Developers using AI agents for coding (specifically those using Claude Code, Codex, Cursor, and other LLM-powered editors) who want to move beyond basic prompting and implement a professional engineering workflow.

Highlights

  • Extensive Library: Includes 68 agents and 286 skills for diverse engineering tasks.
  • Broad Platform Support: Works with Claude Code, Codex, and provides adapters for Cursor, Gemini, Zed, and others.
  • Multi-stage Workflow: Enforces a rigorous cycle of planning, testing, and verification.
  • Integrated Security: Includes AgentShield for scanning agent files and permissions.

Written about in

Related

  • Project
    Chachamaru127/claude-code-harness

    Claude Code Harness is a Go‑native plugin that orchestrates Claude‑based (or compatible) AI agents through a disciplined loop—plan, work, review, sync, release—while enforcing strong guardrails and human approvals at each step. It supports Claude Code, Codex CLI, Cursor, and Grok, generating specs, running AI‑driven implementations, independently reviewing changes, and packaging verified releases.

  • Dispatch
    Beyond the Model: The Rise of Harness Engineering for AI Agents

    Explore the concept of Harness Engineering, a systematic approach to making AI coding agents reliable through environment design, state management, and explicit constraints.

  • Project
    muratcankoylan/Agent-Skills-for-Context-Engineering

    A collection of platform-agnostic Agent Skills focused on context engineering to optimize how AI agents manage their limited attention budget and context windows.

  • Project
    AMAP-ML/LongHorizon-Harness

    A loop engineering framework that turns existing AI agents into long-running computer-use systems by wrapping them in a structured plan-act-verify cycle across GUI and CLI environments.

  • Project
    kdcokenny/opencode-workspace

    A bundled multi-agent orchestration harness for OpenCode that provides a curated collection of agents, plugins, and MCP servers for AI-driven development.