Gives Claude Code quick reflexes: Jev scores the possible next steps and hands back the best one.
@itspur4vClaude is careful but slow and costly. jeveloper adds Jev as its reflexes: cheap, near-instant judgments that fire automatically while Claude works.
When Claude has several possible next moves, Jev scores each and returns the best as a clear "do next" instruction, so Claude spends its effort on the actual work instead of on deciding.
Agent skills and a coding harness where Jev picks the relevant files, so your coding model only reads what matters.
Jev
Python
Codex
Claude CodeA Claude Code plugin that hides the parts of big tool results you do not need, and brings them back on request.
JevPythonClaude CodeScores each action an agent wants to take against the job it was given: allow, ask a person, or block.
JevPythonClaude CodeCodexA Claude Code hook that asks Jev about every shell command and blocks the ones that would delete something that matters.
JevPythonClaude CodeTurns any open-weight LLM into a Jev-style decision model, reading typed choices and calibrated probabilities straight from its logits or hidden states.
JevPython
vLLMTrims long command output with Jev before Claude Code reads it, so later turns carry less noise.
Jev
TypeScriptClaude Code
CodeRabbit Top10
