Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.1.221 Home All releases olderv2.1.220 v2.1.222newer

Security review prompt handles subagent hand-back messages

You'll notice
Useful2 Signal0
Elsewhere

Security review no longer misses issues when a subagent's hand-back message is the last thing in the transcript.

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 →