{"version":"2.1.242","anchor":"plugins-can-submit-prompts-and-the-model-is-told-where-they-","canonical_anchor":"plugins-can-submit-prompts-and-the-model-is-told-where-they-","heading":"Plugins can submit prompts, and the model is told where they came from","tier":"notice","area":"Plugins","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.242\/e\/plugins-can-submit-prompts-and-the-model-is-told-where-they-","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.242","markdown":"### Plugins can submit prompts, and the model is told where they came from\n\nA prompt submitted by a plugin is labelled to Claude as coming from that plugin.\n\n**What**\n\nWhen a plugin submits a prompt, Claude Code now wraps it in text naming the plugin and telling the model to address the message, whether the prompt starts a turn in your place or arrives partway through one alongside the next tool result.\n\n**Details**\n\n- Two cases are distinguished in the wrapper: a prompt submitted between turns, and one that lands inside a turn already running.\n- The wrapper is emitted whenever a plugin submits a prompt; no setting turns it on or off.\n\n**Evidence**\n\n`This is how Claude Code surfaces a prompt a plugin submits between `\n\n- Area: Plugins\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 3\/5"}