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.
When Claude proposes a plan and the user rejects it, they'll now see a more informative display instead of a generic message. This helps users understand what was rejected and provides better context for continuing in plan mode.