Claude Jev Mod

A Claude Code plugin that adds five Jev tools — jev_choice, jev_noul, jev_score, jev_ask and jev_doctor — so small decisions like safety checks, tool choices and review verdicts come back as typed answers with calibrated confidence, labelled auto or escalate.

An OpenCode V2 plugin that asks TypeSafe Jev whether a prompt is deterministic before the LLM reasons, injecting a JEV PRE-ANALYSIS block and temperature 0 for deterministic turns so simple prompts skip chain-of-thought. Jev failures fail open and the session continues normally.

A host-agnostic routing layer that sits between a coding harness and its models, choosing capacity per round from trajectory evidence like tool calls, failures and context pressure, running as a user-scoped daemon and local OpenAI-compatible proxy.

A Claude Code plugin that picks the model tier and thinking effort for every turn with Jev and weighs each switch against what it costs, since moving a long conversation to another model rewrites its prompt cache and can cost more than it saves.

A pi coding-agent extension that compacts long transcripts without rewriting them: Jev answers only keep/kind questions about chunked history, original lines go into a verbatim ledger, and compaction is a deterministic render plus durable topic files. Calls the TypeSafe System One endpoint directly.

A Claude Code mod that adds $.jev to the engine so other mods can ask TypeSafe Jev typed Choice, Score and Noul questions and get calibrated probabilities back. Answers are validated against their questions, keys are kept in the keychain, and calls time out at 4 seconds by default.