10 repos that add a Jev decision layer to Claude Code

Asteri @Asteri_ethOriginally posted 2026.10.09

Open original on X

Opus 5.5 + Jev make Claude Code look f…cking illegal 10 GitHub repos that wrap a decision layer around every Claude Code session 01 toolgate ▸ http://github.com/RiskAverseTech/toolgate → a tool-call firewall: Jev answers 7 yes/no risk questions per call, code maps them to allow, ask or deny, and it fails closed 02 Switchboard ▸ http://github.com/ruban-24/switchboard → Jev sizes up the task, code picks the model and reasoning effort, then pins the pair so the prompt cache stays warm 03 spending-effort-with-jev ▸ http://github.com/Yaxin9Luo/spending-effort-with-jev → a UserPromptSubmit hook that asks Jev which /effort level each prompt actually needs 04 winnow ▸ http://github.com/GhalebDweikat/winnow → judges every tool result before it's allowed anywhere near Claude Code's context 05 fast-jev-compaction ▸ http://github.com/tamaratran/fast-jev-compaction → scores old tool calls for deletion, and whatever it keeps stays word for word 06 Canny ▸ http://github.com/qkal/Canny → an evidence ledger that challenges every "done" your coding agent can't back up 07 Médula ▸ http://github.com/JoaquinRuiz/medula → several Claude Code agents on one repo: before every write Jev scores the chance of a collision, then the agent goes, waits or escalates 08 jevwire ▸ http://github.com/Brainwires/jevwire → MCP tools plus advisory or restrictive Claude Code hooks, all running on typed Jev decisions 09 skillranker ▸ http://github.com/Dicklesworthstone/skillranker → a Rust CLI that ranks your skills against the live session and abstains when nothing fits 10 wakegate ▸ http://github.com/shitianfang/wakegate → Jev decides if a timer or event is worth waking the LLM, and only skips it when it's sure opus thinks. jev decides. code enforces. Copy any of these Jev builds, then read the full Jev setup below ↓

This post quotes another post: x.com/asteri_eth/status/2104901781725598103