{"version":"2.1.265","anchor":"subagent-prompt-now-documents-automatic-claudemd-injection","canonical_anchor":"subagent-prompt-now-documents-automatic-claudemd-injection","heading":"Subagent prompt now documents automatic CLAUDE.md injection","tier":"notice","area":"Subagents","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265\/e\/subagent-prompt-now-documents-automatic-claudemd-injection","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265","markdown":"### Subagent prompt now documents automatic CLAUDE.md injection\n\nClaude Code now tells the orchestrating model that subagents already receive CLAUDE.md automatically\n\n**What**\n\nWhen the main Claude Code assistant spins up a subagent (a separate Claude instance handling a sub-task, launched via the Task\/agent tool), the instructions given to the orchestrating model now explain that the subagent already receives the same `CLAUDE.md` project instruction files that were loaded at the start of the session. This applies to all subagents except the built-in `Explore` and `Plan` agent types, which don't get these files injected.\n\n**Why**\n\nPreviously the orchestrating model might have re-read `CLAUDE.md` itself or pasted its rules into the subagent's prompt, wasting effort on something the subagent already had. Documenting this should make orchestration a bit more efficient and avoid redundant instructions being stuffed into subagent prompts.\n\n- Area: Subagents\n- Names: `CLAUDE.md`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5"}