---
title: "Comment by Mihai_LeanZero on \"Put Your Real-Time Voice Agent on a Skill Roster, Not Under Constant Review\" | Hashnode"
description: "The one gap I'd want closed before promoting anything past speak: the code enforces authority going in — checking the proposed skill against the roster — but th"
url: "https://hashnode.com/posts/put-your-real-time-voice-agent-on-a-skill-roster-not-under-constant-review/6aaf42a8900c482fa6e812f7/comment/6aaf952d3ec55f01f5e01eee"
---

[Discussion](https://hashnode.com/posts/put-your-real-time-voice-agent-on-a-skill-roster-not-under-constant-review/6aaf42a8900c482fa6e812f7)

Comment [Put Your Real-Time Voice Agent on a Skill Roster, Not Under Constant Review](https://hashnode.com/posts/put-your-real-time-voice-agent-on-a-skill-roster-not-under-constant-review/6aaf42a8900c482fa6e812f7)

[Mihai\_LeanZero](https://hashnode.com/@mihaileanzero)

[Sep 20](https://hashnode.com/posts/put-your-real-time-voice-agent-on-a-skill-roster-not-under-constant-review/6aaf42a8900c482fa6e812f7/comment/6aaf952d3ec55f01f5e01eee)

The one gap I'd want closed before promoting anything past speak: the code enforces authority going in — checking the proposed skill against the roster — but the confirm path doesn't show a pending confirmation id tied to that specific proposed effect. A user's "yes" needs to be validated against the exact action it's confirming, not just treated as a fresh transcript that happens to sound affirmative. With barge-in and stale-response suppression already in the design, it's easy for a real "yes" to land after the turn it was answering has already been interrupted or replaced, and without a pending-action id to check it against, the supervisor has no way to tell a stale confirmation from a current one. Same failure class as the interruption handling already in there, just one step later in the flow.
