{"version":"2.1.232","anchor":"subagents-start-with-their-memory-already-loaded","canonical_anchor":"subagents-start-with-their-memory-already-loaded","heading":"Subagents start with their memory already loaded","tier":"notice","area":"Subagents","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232\/e\/subagents-start-with-their-memory-already-loaded","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232","markdown":"### Subagents start with their memory already loaded\n\nSubagents now start with their saved memory already loaded, unless you set the disable-auto-memory variable.\n\n**What**\n\nSubagent system prompts are now built with the agent's saved memory read in advance and handed to the prompt builder, so an agent sees what it recorded previously without a separate lookup. This only happens when auto-memory is on and a stored memory file exists; setting `CLAUDE_CODE_DISABLE_AUTO_MEMORY` turns it off and prompts are built exactly as before.\n\n**Details**\n\n- The memory text is read asynchronously before prompt construction and passed as `primedAgentMemory` into every agent definition's prompt builder.\n- With auto-memory off or no stored memory present, the helper returns undefined and the prompt is unchanged.\n\n**Evidence**\n\n`primedAgentMemory`\n\n- Area: Subagents\n- Names: `CLAUDE_CODE_DISABLE_AUTO_MEMORY`\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5"}