diff --git a/get-shit-done/templates/subagent-task-prompt.md b/get-shit-done/templates/subagent-task-prompt.md
index 9b0c2aafc..c09baf796 100644
--- a/get-shit-done/templates/subagent-task-prompt.md
+++ b/get-shit-done/templates/subagent-task-prompt.md
@@ -1,6 +1,6 @@
 # Subagent Task Prompt Template
 
-Template for spawning plan execution subagents from execute-phase orchestrator.
+Template for spawning plan execution agents from execute-phase orchestrator.
 
 ---
 
@@ -11,6 +11,8 @@ Template for spawning plan execution subagents from execute-phase orchestrator.
 Execute plan {plan_number} of phase {phase_number}-{phase_name}.
 
 Commit each task atomically. Create SUMMARY.md. Update STATE.md.
+
+**Checkpoint handling:** If you hit a checkpoint task, STOP and return a checkpoint message (see checkpoint_behavior below). The orchestrator will present it to the user and resume you with their response.
 </objective>
 
 <execution_context>
@@ -26,8 +28,40 @@ Project state: @.planning/STATE.md
 Config: @.planning/config.json (if exists)
 </context>
 
+<checkpoint_behavior>
+When you encounter a checkpoint task (type="checkpoint:*"), STOP execution and return this format:
+
+## CHECKPOINT REACHED
+
+**Type:** [human-verify | decision | human-action]
+**Plan:** {phase}-{plan}
+**Progress:** {completed}/{total} tasks complete
+
+[Checkpoint content from checkpoint_protocol in execute-plan.md]
+
+**Awaiting:** [Resume signal from the task]
+
+The orchestrator will present this to the user and resume you with their response.
+When resumed, you'll receive: "User response: {their_input}"
+Parse and continue appropriately.
+</checkpoint_behavior>
+
+<completion_format>
+When plan completes successfully, return:
+
+## PLAN COMPLETE
+
+**Plan:** {phase}-{plan}
+**Tasks:** {completed}/{total}
+**SUMMARY:** {path to SUMMARY.md}
+
+**Commits:**
+- {hash}: {message}
+...
+</completion_format>
+
 <success_criteria>
-- [ ] All tasks executed
+- [ ] All tasks executed (or paused at checkpoint)
 - [ ] Each task committed individually
 - [ ] SUMMARY.md created in plan directory
 - [ ] STATE.md updated with position and decisions
@@ -58,4 +92,8 @@ Task(
 )
 ```
 
-Subagent reads @-references, loads full workflow context, executes plan.
+Agent reads @-references, loads full workflow context, executes plan.
+
+When agent returns:
+- If contains "## CHECKPOINT REACHED": Parse and present to user, then resume
+- If contains "## PLAN COMPLETE": Finalize execution
diff --git a/get-shit-done/workflows/execute-plan.md b/get-shit-done/workflows/execute-plan.md
index 5bb35305a..5af23cfd7 100644
--- a/get-shit-done/workflows/execute-plan.md
+++ b/get-shit-done/workflows/execute-plan.md
@@ -1152,6 +1152,49 @@ I'll verify after: [verification]
 See ~/.claude/get-shit-done/references/checkpoints.md for complete checkpoint guidance.
 </step>
 
+<step name="checkpoint_return_for_orchestrator">
+**When spawned by an orchestrator (execute-phase or execute-plan command):**
+
+If you were spawned via Task tool and hit a checkpoint, you cannot directly interact with the user. Instead, RETURN to the orchestrator with checkpoint details so it can present to the user and resume you.
+
+**Return format for checkpoints:**
+
+```
+## CHECKPOINT REACHED
+
+**Type:** [human-verify | decision | human-action]
+**Plan:** {phase}-{plan}
+**Progress:** {completed}/{total} tasks complete
+
+[Checkpoint content - same as checkpoint_protocol display above]
+
+**Awaiting:** [Resume signal from the task]
+```
+
+The orchestrator will:
+1. Parse your return
+2. Present the checkpoint to the user
+3. Collect user's response
+4. Resume you with: `Task(resume=your_agent_id, prompt="User response: {their_input}")`
+
+**When resumed after checkpoint:**
+
+You will receive a prompt like: `"User response: approved"` or `"User response: option-a"`
+
+- Parse the user's response
+- If approved/done: continue to next task
+- If issues described: address them, then continue or re-present checkpoint
+- If option selected: proceed with that choice
+
+**How to know if you were spawned:**
+
+If you're reading this workflow because an orchestrator spawned you (vs running directly from /gsd:execute-plan), the orchestrator's prompt will include checkpoint return instructions. Follow those instructions when you hit a checkpoint.
+
+**If running in main context (not spawned):**
+
+Use the standard checkpoint_protocol - display checkpoint and wait for direct user response.
+</step>
+
 <step name="verification_failure_gate">
 If any task verification fails: