novahiz@0.9.6
Enforce AI agent skills before every file edit: prompt classifier, skill catalog, and pre-edit gate.
AI security review
scanned · by lpm-firewall-aiSource confirms that npm postinstall can set up the package's own OpenCode integration in global user configuration without an interactive prompt. This is a warning-level agent extension lifecycle risk; the inspected source does not establish malicious behavior warranting a publish block.