Adding a Jev guardrail to Claude Code and Codex tool calls
Jev founder Diogo Amogo describes a guardrail layer that makes one typed call before each command to judge whether it is destructive, touches secrets or falls outside the task, then allows, asks or blocks.
this is pure gold for anyone running Claude Code or Codex Jev founder Diogo Amogo wrote a note on putting a Jev guardrail layer around every tool call your agent makes the problem: > your agent can run rm -rf, read your .env and force-push to main > most setups either approve everything or ask you about everything > or worse, ask the same model to judge its own command the fix is one typed call before every command: > destructive? > touches secrets? > outside the task? > how big is the blast radius? > allow, ask or block? 5 answers, 1 request, under a second the model never gets the last word. a decision table in code does - what it catches > cat .env → blocked > DROP TABLE users → blocked > rm -rf ./dist → sent to you with the reason > edit src/router.ts → runs, then checked against the diff - how to use it > drop this note into Claude Code or Codex > let it wire the guard into its own hooks one evening of setup and your agent stops asking you about ls and stops touching things it shouldn't ↓
This post quotes another post: x.com/solst1ne/status/2101724066369654935