very-happy-cli@0.2.79
Remote multi-agent workspace CLI with deep Claude integration, native terminal streaming, and self-hosting.
AI security review
scanned · by lpm-firewall-aiSource inspection confirms credential relay and explicit Claude hook installation, but not covert exfiltration or an unconsented install-time mutation of Claude or another agent's control surface. This is a transparent but high-impact agent integration, so it warrants a warning rather than a publish block.