{"version":"2.1.307","anchor":"the-agent-tool-description-in-the-reminder-skill-run-prompt","canonical_anchor":"the-agent-tool-description-in-the-reminder-skill-run-prompt","heading":"Agent tool guidance rewritten in the skill-run reminder prompt","tier":"notice","area":"Subagents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.307\/e\/the-agent-tool-description-in-the-reminder-skill-run-prompt","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.307","markdown":"### Agent tool guidance rewritten in the skill-run reminder prompt\n\nIn the skill-run reminder prompt, Claude's helper-agent instructions now say to wait for delegated work instead of also doing it\n\n**What**\n\nThe description of the `Agent` tool was rewritten in the prompt Claude Code sends with its reminder when a skill runs. A skill is a packaged set of instructions Claude can use for a particular task. The `Agent` tool is how Claude passes work to a subagent, a separate helper copy of Claude.\n\nThe new text includes the rule: \"Once you've delegated something, don't also run it yourself; wait for the result.\"\n\n**Why**\n\nThis text is part of Claude's own instructions, so the rewrite changes how Claude behaves after handing work off. It is told not to repeat the same work in parallel with its helper.\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}