Source Intelligence
Follow Discord

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 v2.1.238 Home All releases ←olderv2.1.237 v2.1.239newer→
Claude Code v2.1.238

Second, shorter review prompt when a subagent hands work back

Under the hood
Useful2 Signal3
Subagents

The safety review of returning subagent work gained a shorter prompt that flags dangerous files with a reason.

What

The safety check that reviews a subagent's work when it returns control to the main agent gained a second, trimmed prompt variant alongside the existing one, which asks the reviewer to flag dangerous files and give the main agent a reason.

Details
  • Both sit next to the existing two-stage grading prompts.
  • Which variant is used is decided at the call site, and the code does not make the condition explicit.
Evidence

Subagent has finished and is handing back control to the main agent. Review the subagent's work for anything dangerous under the block rules.

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

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.238 →