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 v2.1.26 Home All releases olderv2.1.25 v2.1.27newer
Claude Code v2.1.26

Plan Execution UI Improvements

The plan execution prompt has been improved with clearer messaging and numbered options. The confirmation prompt now reads "Claude has written up a plan and is ready to execute. Would you like to proceed?" instead of the previous generic "Would you like to proceed?". Plan selection options (like "Chat about this" and "Skip interview and plan immediately") are now displayed with numbered prefixes for easier keyboard selection.

Evidence

Plan confirmation text (search for "written up a plan and is ready to execute")

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

See this entry in the whole of v2.1.26 →