{"version":"2.1.281","anchor":"agent-seating-can-re-apply-the-agent-system-prompt","canonical_anchor":"agent-seating-can-re-apply-the-agent-system-prompt","heading":"Agent seating can re-apply the agent system prompt","tier":"notice","area":"Agents","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281\/e\/agent-seating-can-re-apply-the-agent-system-prompt","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281","markdown":"### Agent seating can re-apply the agent system prompt\n\nStarting a session with --agent now goes through one helper, which can also re-apply the agent's system prompt when that agent is already active\n\n**Unclear.** The finding does not say what situation makes Claude Code use `reapplySystemPromptIfSeated`.\n\n**What**\n\n`--agent` is a command-line option that picks an agent for the current session, overriding the `agent` setting. An agent here is a preset that gives Claude its own instructions and defaults. Setting one up for the session is now done by a single step that applies three things:\n\n- the agent's system prompt, which is the standing instructions Claude follows for the whole session\n\n- the agent's model, unless you chose a model yourself\n\n- the agent's `initialPrompt`, a first message the agent starts with\n\nA new option, `reapplySystemPromptIfSeated`, lets this step apply the agent's system prompt again even when that agent is already active in the session.\n\n**Why**\n\nIn practice an agent's instructions can be put back in place without starting the agent over. A model you picked yourself still takes priority over the one the agent names.\n\n- Area: Agents\n- Names: `--agent`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}