affaan-m/ECC

Project overview

A system of over 260 reusable skills, rules, and hooks designed to standardize AI-assisted software development across multiple agent harnesses. It provides cross-harness automations, a security scanner for agent configurations, and an experimental desktop dashboard.

Project type

MCP · AI Agent · AI Coding

Use cases

Coding & Development

Deployment

Refer to project documentation

License

MIT

Best for

• Developers and AI engineers using Claude Code, Cursor, Codex, OpenCode, Gemini, Zed, or GitHub Copilot who want to standardize AI coding workflows.
• Teams seeking to automate auto-formatting and security checks across different AI harnesses using a shared hook architecture.

Key capabilities

• Provides over 260 reusable skills, rules, and command shims across 12+ language ecosystems to enhance AI coding workflows.
• Provides a DRY adapter pattern hook architecture to reuse hook scripts (auto-formatting, security checks) across Claude Code, Cursor, OpenCode, and others.
• Scans AI agent configurations for vulnerabilities, misconfigurations, and injection risks. Includes GateGuard to gate destructive shell commands.
• A desktop application providing a GUI dashboard with dark/light themes.
• A Rust control-plane prototype that exposes dashboard, start, sessions, status, and daemon commands.

Limitations and risks

• GitHub Copilot does not have a hook system or a subagent API, so the project's hook automations are unavailable in that environment.
• Codex does not yet provide Claude-style hook execution parity.
• Third-party re-uploads and unofficial mirrors are not maintained or reviewed by the project and may contain malware.

Getting started

• Coding requirement is optional. Users can install the plugin via the command `/plugin install ecc@ecc` and can get up and running in under 2 minutes.

Evidence and sources

• GitHub project description: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
• README: A complete system: skills, instincts, memory optimization, continuous learning, security scanning, and research-first development. Production-ready agents, skills, hooks, rules, M…
• README: Stable graduation of the 2.0 line: 261 skills, the control-pane substrate (session adapters + MCP inventory), the worktree-lifecycle service
• README: Cursor has more hook events than Claude Code (20 vs 8). The .cursor/hooks/adapter.js module transforms Cursor's stdin JSON to Claude Code's format, allowing existing scripts/hooks…
• README: Scan your Claude Code configuration for vulnerabilities, misconfigurations, and injection risks.

Reviewed at: 2026-07-16T06:39:21Z