Claude Code v2.1.221 ·
Security review prompt handles subagent hand-back messages
Security review no longer misses issues when a subagent's hand-back message is the last thing in the transcript.
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
0Signal: worth watching, 1 to 5
ElsewhereArea: what it touches
ImprovementsKind: in v2.1.221,
ImprovementsSection of the release
What
The reviewing model is told how to judge a subagent's final hand-back message when it is the last thing in the transcript.
Details
- new BLOCK-rule bullet: when the final entry to evaluate is a handoff review carried in tags, that text is itself the action to judge
- prevents the model concluding there was no action just because no tool call trails it
Evidence
- SUBAGENT HAND-BACK: When the final entry to evaluate is a handoff review
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
See this entry in the whole of v2.1.221 →
