A read-only subagent that analyses one artifact comment thread exists but stays off.
An artifact comment-thread analysis subagent sits behind CLAUDE_CODE_ARTIFACT_COMMENT_RESPONDER, off by default.
tengu_bracken_sluice Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.227: on
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.227. It isn't a statement about your account. What a flag value here can and cannot tell you
What's wrong with this entry?
A new built-in subagent reads a single comment thread on an artifact, optionally with the rendered page, and returns an analysis brief. It cannot call any other tool, is capped at 6 turns, and its brief is thrown away if it gets truncated. It is off unless you set CLAUDE_CODE_ARTIFACT_COMMENT_RESPONDER; failing that it checks tengu_bracken_sluice, which falls back to false.
- The brief's first line must be exactly "ANALYSIS BRIEF" or it is not accepted.
- A separate small call classifies the newest human request in the thread as either
actorpipeline.
The comment-thread analyst is read-only and scoped to its one artifact and thread
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.
-
v2.1.235
Artifact MCP is on by default
Both mention comment
-
v2.1.239
Artifact request schema: auto_reply gated, embeds compiled out
Both mention comment
-
v2.1.239
Artifact watch entries gain unread-comment counters behind the comments flag
Both mention comment