DoGMaTiiC

TypeSafe Jev as a judgment layer — a pre-tool gate (shadow by default, enforce escalates) on terminal, write_file and patch asking destructive / exfiltration / impact, plus a jev_ask tool for typed judgments. Thresholds in code, one JSONL line per decision, fail-open on every error path. Stdlib only, no Node; works with TYPESAFE_API_KEY or AI_GATEWAY_API_KEY. Disclosure — each judged call sends the tool name and its redacted arguments (≤600 chars each, ≤12 args) to TypeSafe or your configured gateway, using your key; shadow mode only logs.

Names the one skill from your live roster that fits the turn, before the model call — typed routing via TypeSafe Jev (one choice over the roster plus gate booleans, then a re-read of the shortlist with per-candidate fits), with both thresholds applied in code. Says nothing when nothing fits; opt-in, fail-open, stdlib only, no Node. Disclosure — on eligible turns it sends your message (up to 4,000 chars) plus skill names and short SKILL.md excerpts from your local roster to TypeSafe or your configured gateway, using your key.