Triage the comment queue safely

A moderation queue that has been ignored for a month is its own kind of dread: a few hundred comments, most of them spam, a handful genuine, and no appetite to click through all of them. This hands the reading and the sorting to the agent and keeps every actual decision with you.

Help me work through the comment moderation backlog, and don't action anything
until I say so. First pass, read only: pull the pending queue and hand me back
a table with each comment's author name, a short excerpt, and your read on
whether it's spam, with a one-line reason for each call (link stuffing,
gibberish, off-topic, looks genuine, and so on). Do not approve, mark spam, or
trash anything yet. Once I've looked it over I'll tell you exactly which
comments to act on and how. Then do them a few at a time and give me back a
list of what you did to each one. Everything here is recoverable since trash
isn't a permanent delete, so if I change my mind I can pull a comment back.

Why this is safe to run

The whole first pass is a read, so you see the agent’s spam calls as a table before anything happens to a single comment. Reading the queue and moderating a comment are two different abilities with two different switches, so the “don’t action anything” instruction is backed by the plugin, not just good manners: if you never enabled moderation, the agent could not act even if you asked. Moderation sends a comment to trash rather than deleting it, so a wrong call is something you undo. And comment reads never hand back an email address or an IP, so the table stays privacy safe.

Already connected? Ask your agent for the “triage the comment queue” recipe and it runs the same read-first flow on your own queue.