Jev guard and loop watch

Irreversible calls stop before they run.

Before Claude Code or Codex runs a tool call, FlockTab checks it: known irreversible commands by rule, the rest by Jev, TypeSafe's judgment model. Watch records, ask has you confirm, deny refuses. An agent stuck repeating itself can be paused.

Start a flock Jev in the tab CLI

claude · guard: deny

● Bash pnpm test

⎿ ran · 42 passed

● Bash git push --force origin main

⎿ Blocked by FlockTab: rule: force-push. Ask the person to run it or approve it.

● Bash ssh staging 'sudo -n docker ps' (sandbox off)

⎿ FlockTab: reach: turns off the sandbox. Confirm only if you mean it.

● Bash aws s3 rm s3://backups --recursive

⎿ Blocked by FlockTab: deletes S3 data.

Jev's guard in the agent's own session: ordinary work runs; a force-push, an unsandboxed ssh and an S3 delete are stopped.

Rules first, judgment second

A force-push, DROP TABLE, a production deploy or a payment is stopped by rule. Everything else that can change something is judged by Jev.

Calls that reach past the project

ssh or scp to another machine, sudo, a database on another host, reading keys, or the harness turning its own sandbox off.

Your own patterns

Always flag "*prod*", always trust "ssh staging-bastion*": per Agent, in the console or with tab policy.

Secrets stay out

Keys, tokens and passwords are removed before a tool call is judged, and only a short summary is kept. Tool output never leaves the machine.

Also beyond the cap

Put a tab on every agent tonight.

Free for three agents. Install tab, set a cap, sleep.

Start a flock See pricing