{"version":"2.1.307","anchor":"the-agent-tool-description-in-the-agent-claude-prompt-was-re","canonical_anchor":"the-agent-tool-description-in-the-agent-claude-prompt-was-re","heading":"Claude's subagent instructions now stress what gets lost in a handoff","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-agent-claude-prompt-was-re","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.307","markdown":"### Claude's subagent instructions now stress what gets lost in a handoff\n\nIn the agent-claude prompt, the Agent tool's description now warns that detail is lost both when Claude briefs a subagent and when it reports back\n\n**What**\n\nThe Agent tool lets Claude hand a task to a subagent, a separate helper that works on its own and returns a summary. Its description in the agent-claude prompt has been rewritten.\n\nThe old text mostly told Claude when to delegate: matching agent types, parallel work, reading across many files. The new text adds a warning about the two handoffs. It says the subagent knows only what Claude puts in the prompt, Claude sees only the summary that comes back, and detail is dropped both ways without either side knowing what the other missed.\n\nThe standard Agent tool description is unchanged.\n\n**Why**\n\nThese are instructions Claude follows, so they can change how often it delegates and how fully it briefs a subagent. That effect has not been measured.\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}