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 v2.1.228 Home All releases ←olderv2.1.227 v2.1.229newer→
Claude Code v2.1.228

Doc and sheet prompts are trimmed to the artifact's capabilities

Not switched on
Useful1 Signal3
Skills

Doc and sheet skill instructions are assembled at run time to match what the artifact supports.

Part of the document and spreadsheet skills, which are hard-disabled in this build.

What

When one of the new document or spreadsheet skills runs, its instruction file is assembled at invocation rather than sent whole, so Claude is only told to do things the artifact actually supports.

Details
  • A marked block instructing Claude to act on reader comments (make the edit, reply, resolve) is kept only when the artifact has a thread id, and deleted otherwise.
  • A trailing note is appended only when the artifact reports capabilities.
  • Front matter is stripped, and anything the user typed after the command is appended under a ## User Request heading.
  • Unreachable in this build, since both skills are registered as disabled.
Evidence

<!-- comment-verbs:begin -->

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

See this entry in the whole of v2.1.228 →