Answer: By default subagents run in the background, but Claude waits when its next action needs the report, blocking and returning `status: "completed"`. You can make that choice yourself by asking Claude in your prompt to wait (e.g., "run the test-runner agent and wait for it"), or by setting `background` to `true` in the definition to keep that agent in the background. Status: Confirmed Entry: tool/claude-code/agents-and-automation/wait-for-subagents Revision: 3 Digest: sha256:75b5f11902d0b218 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:03:03Z Last changed: 2026-11-19T12:13:12Z (definition option: — → true) Last verified: 2026-11-20T12:17:28Z Next check: 2026-11-21T12:17:28Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of default behavior | runs in the background | [1] | 2026-11-20 waiting status | status: "completed" | [1] | 2026-11-20 prompt option | run the test-runner agent and wait for it | [1] | 2026-11-20 definition option | true | [1] | 2026-11-20 Sources: [1] Anthropic. "Subagents in the SDK". https://code.claude.com/docs/en/agent-sdk/subagents.md Role: primary. Accessed: 2026-11-20T12:17:28Z Quote: "By default, a subagent your main agent spawns [runs in the background]" (Supports: default behavior) Quote: "the call blocks and returns `status: "completed"`" (Supports: waiting status) Quote: "ask Claude to wait, such as "run the test-runner agent and wait for it"" (Supports: prompt option) Quote: "set `background` to `true` to keep that agent in the background" (Supports: definition option) Published: 2026-11-20T10:36:10Z Snapshot SHA-256: 39e8862dc192aa0a70a5153f84efe78010ae959a3f6f12a1f7b2c5982f0aaaed (captured 2026-11-20T12:17:27Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. Cross-check: not-available at 2026-11-20T12:17:28Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:17:28Z Last attempt: 2026-11-20T12:17:28Z Notes and limitations: Extracted automatically from a single official source (section "Choose whether Claude waits for subagents"). Related: https://latestn.com/tool/claude-code/agents-and-automation/what-is-a-hook What is a hook in Claude Code? https://latestn.com/tool/claude-code/agents-and-automation/what-is-a-subagent What is a subagent in Claude Code? https://latestn.com/tool/claude-code/agents-and-automation/when-to-use-single-message-input When should I use single message input instead of streaming input in the Claude Agent SDK? https://latestn.com/tool/claude-code/agents-and-automation/test-timer-drawing How do I test a timer or a drawing in a Claude Code mod? https://latestn.com/tool/claude-code/agents-and-automation/tool-return-images-structured-data How do I return images or structured data from a Claude Code custom tool? https://latestn.com/tool/claude-code/agents-and-automation/user-input-limitations What are the limitations of handling user input with the Claude Code Agent SDK? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-19T12:13:12Z | changed | definition option: — → true | [1] 2026-11-19T12:13:12Z | changed | prompt option: — → run the test-runner agent and wait for it | [1] 2026-11-19T12:13:12Z | changed | definition setting: true → — | [1] 2026-11-19T12:13:12Z | changed | prompt example: run the test-runner agent and wait for it → — | [1] 2026-11-19T12:13:12Z | changed | waiting status: completed → status: "completed" | [1] 2026-11-19T12:13:12Z | changed | default status: async_launched → — | [1] 2026-11-18T12:13:15Z | changed | definition setting: — → true | [1] 2026-11-18T12:13:15Z | changed | prompt example: — → run the test-runner agent and wait for it | [1] 2026-11-18T12:13:15Z | changed | default status: — → async_launched | [1] 2026-11-18T12:13:15Z | changed | background setting: true → — | [1] 2026-11-18T12:13:15Z | changed | prompt instruction: run the test-runner agent and wait for it → — | [1] 2026-11-18T12:13:15Z | changed | waiting status: status: "completed" → completed | [1] 2026-11-13T03:03:03Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-code/agents-and-automation/wait-for-subagents/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/claude-code/agents-and-automation/wait-for-subagents POST: https://latestn.com/dispute/tool/claude-code/agents-and-automation/wait-for-subagents with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-code/agents-and-automation/wait-for-subagents?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I make Claude wait for subagents to finish before continuing? Revision 3, last verified 2026-11-20T12:17:28Z. https://latestn.com/tool/claude-code/agents-and-automation/wait-for-subagents (accessed 2026-11-21T09:58:55Z). @misc{LatestN_tool_claude_code_agents_and_automation_wait_for_subagents_r3, title = {How do I make Claude wait for subagents to finish before continuing?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-code/agents-and-automation/wait-for-subagents}}, note = {Revision 3; digest sha256:75b5f11902d0b218; last verified 2026-11-20T12:17:28Z; accessed 2026-11-21T09:58:55Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/claude-code/agents-and-automation/wait-for-subagents