thetacog-mcp@2.21.4
Geometric-Driven Development (GDD) toolkit: cognitive rooms + Shadow Agent hooks + Ghost-Read pipeline (6 routes, persona-monologue) + thetacog-iterate convergence loop (meta-rule-checker, auto-applies high-confidence rewrites, adaptive stall-softening) +
AI security review
scanned · by lpm-firewall-aiSource inspection does not establish malicious theft, persistence, or AI-agent hijacking. The package nevertheless executes a bundled native artifact and may compile code during postinstall, so it is unsafe to mark clean under a conservative upstream firewall.