All projects

typesafe-jev-tools

wotai-dev/typesafe-jev-tools

A Claude Code hook that asks whether the decision you are writing needs a model at all. Includes a measured 149-row comparison of TypeSafe Jev against Claude Haiku 4.5.

TypeScript
Stars
2
Forks
0

Why it is listed

This Claude Code hook screens edits with local signals and can optionally ask Jev; the README says the API judge is off unless explicitly enabled with a key.

Related projects

  • jev-skill-gate

    Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

    Shared topics: ai-agents, anthropic, claude-code, claude-code-hooks

  • claude-referee

    Evidence over eloquence. Unofficial Claude Code plugin that checks "done" claims and small judgement calls with TypeSafe Jev, and keeps receipts.

    Shared topics: ai-agents, claude-code, claude-code-hooks

  • pen-find

    Find any frame in a Pen (pen.dev) design file by describing it. Jev ranks every node by meaning; your AI agent only reads the top matches. CLI + Claude Code plugin.

    Shared topics: ai-agents, claude-code