Security Classifier Scope Refined / Claude Code v2.1.186

The automode security classifier's scope description was sharpened to clarify exactly what it does and does not block.

Details

Scope now explicitly reads: "prevents destructive, hard-to-undo, or security-relevant actions only."
Explicitly out of scope: "fabricating or misreporting results; posting updates the user didn't ask for; poor code, wrong answers, looping, wasted tokens." These are for the user to correct, not the classifier.
A new EDIT REMOVALS annotation is now included in classifier context: removals in Edit calls are noted with removes / adds fields. Deletions are now weighted as seriously as additions. If removesTruncated: true, the full removal should be treated as significant.
NotebookEdit calls are annotated with mode and cell_id, and deleted cell content is treated as unverifiable per the high-severity rules.

Evidence

Revised classifier prompt (search for "EDIT REMOVALS: Edit calls show both \removes\" and "destructive, hard-to-undo, or security-relevant actions")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.