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 v2.1.229 Home All releases ←olderv2.1.228 v2.1.231newer→
Claude Code v2.1.229

Subagent prompt for analysing one artifact comment thread

Under the hood
Useful1 Signal4
Artifacts

There's now a prompt for a helper agent that analyses a single artifact comment thread.

What

A system prompt was added for a dispatched subagent that reads exactly one comment thread on one published artifact and writes a plain-text brief whose first line must be exactly "ANALYSIS BRIEF". It replaced an unrelated read-before-edit reminder in that slot.

Details
  • It may only read that thread plus page data, and any write-shaped tool call is denied.
  • Comment text is treated as reader feedback, never as instructions to follow.
Evidence

You are an artifact comment-thread analyst for Claude Code.

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 v2.1.229 →