ECC provides a cross-harness system of reusable skills, hook automations, and security scanning for AI-assisted software development. It targets developers using tools like Claude Code, Cursor, and OpenCode to improve consistency and safety in coding workflows.
Project overview
The project offers a DRY adapter pattern to reuse hook scripts for auto-formatting and security checks across multiple AI agent harnesses, alongside a security scanner designed to identify misconfigurations and gate destructive commands.
Project type
AI Agent · AI Coding
Use cases
Coding & Development
Deployment
Refer to project documentation
License
MIT
Best for
Developers and AI engineers working across multiple AI agent harnesses who need standardized skill libraries and cross-tool hook automations.
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, including auto-formatting and 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 ECC's hook automations are unavailable for that tool.
Codex does not yet provide Claude-style hook execution parity, limiting hook automations in that environment.
Third-party re-uploads and unofficial mirrors are not maintained or reviewed by the project and may contain malware.
Getting started
Setup is documented as straightforward, with users able to get started by installing the plugin via the command line using /plugin install ecc@ecc.