All projects

JevFlow

Parth1811/JevFlow

A Claude Code plugin that keeps your AI agents honest. Claude plans tasks as phases with checks, and when it tries to stop, Jevflow runs them and asks Jev if the work is really done. Many agents, one plan, with a live viewer to watch it all.

Python
Stars
12
Forks
0

Why it is listed

A Claude Code planning/completion plugin that runs phase checks and asks Jev to judge completion when the agent tries to stop. The plugin is not proof that every task is correctly completed.

Related projects

  • jev-usher

    The doorman for Claude’s context window. JEV-powered model routing and recoverable context filtering for Claude Code.

    Shared topics: claude, claude-code, claude-code-plugin

  • toolgate

    A measured tool-call firewall for AI agents: allow, ask or deny before the agent acts. Claude Code mod and hook, MCP proxy. Built on TypeSafe Jev, measured on real sessions with a blind second labeler.

    Shared topics: claude-code, claude-code-plugin, claude-code-plugins

  • jev-use

    Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

    Shared topics: claude-code, claude-code-hooks, claude-code-plugin