Skip to content
JevHub

[ Builds · Coding agents ]

Jev for coding agents

Plugins, guards and routers that put Jev inside coding agents like Claude Code, Codex and Pi: approving commands, picking skills and trimming output. 20 entries, each credited to its author.

[ Sponsors ]Launch price

These products help pay for JevHub. Want yours up here?

Sort

20 results in Coding agents

jev-review

devagrawal09

GitHub preview of devagrawal09/jev-review

A code-review workflow for diffs or whole codebases, with a quiet local dashboard.

dsh-jev-plugin

luobosibing2

GitHub preview of luobosibing2/dsh-jev-plugin

A native DeepSeek Harness plugin with twelve Jev-powered features.

building-with-typesafe-jev

aaddrick

GitHub preview of aaddrick/building-with-typesafe-jev

An unofficial skill that teaches coding agents to design for Jev, with prior art from community projects.

quicksilver

UditAkhourii

GitHub preview of UditAkhourii/quicksilver

A Claude Code skill that offloads 'which of these matter?' questions to Jev.

claude-x-jev

charlesdove977

GitHub preview of charlesdove977/claude-x-jev

A free Claude Code skill that pairs Jev's fast decisions with Claude's writing.

gatekeeper

AgriciDaniel

GitHub preview of AgriciDaniel/gatekeeper

Decides which AI agent or skill should handle a request before your AI guesses.

jev-harness

TypeSafeAI

GitHub preview of TypeSafeAI/jev-harness

A research-stage coding harness where an LLM proposes and Jev reviews.

Roshan Chandna

@roshanchandna

Your coding agent is one bad instruction away from running rm -rf ~/.aws. I built Auto-Guard with Jev (@typesafeai) to check every tool call before it runs. Here it stops a credentials delete but lets the build cleanup through. It's open source! Install in the replies 👇

24likes on X

jev-use

shitianfang

GitHub preview of shitianfang/jev-use

A plugin for Claude Code, Codex and Pi that hands decision-only steps to Jev.

jev-pruner

tamaratran

GitHub preview of tamaratran/jev-pruner

A Claude Code plugin that trims noisy Bash output before the model reads it.

stanley-code

devagrawal09

GitHub preview of devagrawal09/stanley-code

A command-line tool for checking and understanding code changes, described in plain words.

jev-review

NiazMorshed2007

GitHub preview of NiazMorshed2007/jev-review

A local MCP server that gives coding agents continuous quality scores while they work.

pi-jev-auto-mode

jomatsu

GitHub preview of jomatsu/pi-jev-auto-mode

Auto-approves routine bash, write and edit calls in Pi and fails closed when unsure.

hermes-jev-approvals

anpicasso

GitHub preview of anpicasso/hermes-jev-approvals

Replaces Hermes Agent's command reviewer with Jev: approve, deny or ask the user.

skillranker

Dicklesworthstone

GitHub preview of Dicklesworthstone/skillranker

A Rust CLI that ranks an agent's installed skills for the next step of a session.

pi-jev

TheoOliveira

GitHub preview of TheoOliveira/pi-jev

Activates only the tools and skills a Pi agent needs for the current prompt.

jevify

altryne

GitHub preview of altryne/jevify

An agent skill that finds work a fast decision model can handle and helps design the questions.

building-with-jev-skill

dbreunig

GitHub preview of dbreunig/building-with-jev-skill

A skill that helps coding agents write and improve programs that call Jev.

pi-jev

y0usaf

GitHub preview of y0usaf/pi-jev

Adds Jev to the Pi coding agent as a gate on risky tool calls and a fast way to ask typed questions.

Canny

qkal

GitHub preview of qkal/Canny

A supervision layer for Claude Code and Codex that won't let an agent finish on an unproven claim.