{"version":"2.1.229","anchor":"subagent-prompt-for-analysing-one-artifact-comment-thread","canonical_anchor":"subagent-prompt-for-analysing-one-artifact-comment-thread","heading":"Subagent prompt for analysing one artifact comment thread","tier":"internal","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.229\/e\/subagent-prompt-for-analysing-one-artifact-comment-thread","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.229","markdown":"### Subagent prompt for analysing one artifact comment thread\n\nThere's now a prompt for a helper agent that analyses a single artifact comment thread.\n\n**What**\n\nA 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.\n\n**Details**\n\n- It may only read that thread plus page data, and any write-shaped tool call is denied.\n- Comment text is treated as reader feedback, never as instructions to follow.\n\n**Evidence**\n\n`You are an artifact comment-thread analyst for Claude Code.`\n\n- Area: Artifacts\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 4\/5"}