Gives AI coding agents on-demand security playbooks, a code scanner they can run on their own output, and live lookups against CISA KEV, NVD and OSV so they verify threats instead of guessing. Runs locally with no API keys or accounts, exposing skills, tools and a secure-build prompt to Claude Code, Codex, Cursor or any MCP client.

Enables MCP clients to create and control persistent, PTY-backed terminal sessions on macOS: launch commands and interactive programs, read output incrementally via byte cursors, send keystrokes, wait on conditions, and detect running/awaiting-input/exited states. Sessions run inside a Seatbelt sandbox with command policies, human approvals, secret redaction, and hash-chained audit logging.

Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.