The author nearly wiped a Kubernetes namespace after approving an agent’s `oc delete --all` without reading it, then built a suite of 11 Claude Code plugins using the new function hooks API. The main mod, guardrails, blocks destructive commands like mass kubectl/oc deletes, rm -rf, force-push, and secret reads, and tells Claude the user blocked it. Other mods cover activity monitoring, desktop notifications, context tracking, usage limits, prompt coaching, command discovery, and a mod manager. Nine of eleven never call a model, there is no telemetry, and the project is free and MIT licensed.
claude / I approved an agent’s “oc
❯ /I▰▰▰▰▰▰▰▰ Security & privacy
✳︎ I approved an agent’s “oc delete —all” without reading it, so I built guardrails (and 10 other mods) with Claude Code’s new function hooks
└─ Make every conversation easier
Text preview · Not a project screenshot✳︎ I approved an agent’s “oc delete —all” without reading it, so I built guardrails (and 10 other mods) with Claude Code’s new function hooks
└─ Make every conversation easier
I approved an agent’s “oc delete —all” without reading it, so I built guardrails (and 10 other mods) with Claude Code’s new function hooks
Stars 0Permission footprint Not scanned