{"version":"2.1.227","anchor":"an-artifact-comment-thread-can-be-analysed-by-a-new-read-onl","canonical_anchor":"an-artifact-comment-thread-can-be-analysed-by-a-new-read-onl","heading":"An artifact comment thread can be analysed by a new read-only subagent","tier":"soon","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.227\/e\/an-artifact-comment-thread-can-be-analysed-by-a-new-read-onl","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.227","markdown":"### An artifact comment thread can be analysed by a new read-only subagent\n\nA read-only subagent that analyses one artifact comment thread exists but stays off.\n\n**What**\n\nA 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.\n\n**Details**\n\n- The brief's first line must be exactly \"ANALYSIS BRIEF\" or it is not accepted.\n- A separate small call classifies the newest human request in the thread as either `act` or `pipeline`.\n\n**Evidence**\n\n`The comment-thread analyst is read-only and scoped to its one artifact and thread`\n\n- Flag `tengu_bracken_sluice`: Not enough to say (read for one account on one subscription tier against v2.1.227; this account: no value returned, anonymous baseline: no value returned, compiled default: off) 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.\n- Area: Artifacts\n- Names: `CLAUDE_CODE_ARTIFACT_COMMENT_RESPONDER`\n- Tier: Nothing to try yet\n- Useful: 2\/5\n- Signal: 4\/5\n- Present in the build but not switched on"}