{"version":"2.1.307","anchor":"the-agent-tool-description-in-the-command-init-prompt-was-re","canonical_anchor":"the-agent-tool-description-in-the-command-init-prompt-was-re","heading":"Command-init instructions warn that subagents sound sure when they are wrong","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-command-init-prompt-was-re","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.307","markdown":"### Command-init instructions warn that subagents sound sure when they are wrong\n\nIn the command-init prompt, the Agent tool's description now warns that subagent mistakes sound as confident as their findings\n\n**What**\n\nThe Agent tool lets Claude hand a task to a subagent, a separate helper that returns a summary. Its description in the command-init prompt, used by the command-line tool and the SDK, has been rewritten.\n\nThe old text mainly listed when to delegate. The new text warns that a subagent's mistakes come back sounding just as confident as its findings. It also warns that a subagent given Claude's own guess tends to report that guess as confirmed.\n\nThe standard Agent tool description is unchanged.\n\n**Why**\n\nThese are instructions Claude follows, so they may make Claude more careful about trusting a subagent's answer. That effect has not been measured.\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}