diff --git a/.claude/skills/start-sprint/SKILL.md b/.claude/skills/start-sprint/SKILL.md
index a2b59e72a..2aaf2df40 100644
--- a/.claude/skills/start-sprint/SKILL.md
+++ b/.claude/skills/start-sprint/SKILL.md
@@ -95,7 +95,27 @@ Output a summary:
 - Key decisions loaded
 - Suggested first task (lowest ID unblocked ticket)
 
-Then mark the first actionable ticket as `in_progress`:
-```bash
-"$REPO_ROOT/db/connectors/ticket" status <id> in_progress
-```
+Do NOT mark any ticket as `in_progress` yet.
+
+### 8. Enter plan mode
+
+After presenting the work plan summary, you MUST enter plan mode using the
+`EnterPlanMode` tool. In plan mode:
+
+1. **Create a concrete sprint plan** — for each actionable ticket, outline:
+   - What files need to be created or modified
+   - What the implementation approach is
+   - What order tickets should be tackled in (respecting dependencies)
+   - Any open questions or risks per ticket
+
+2. **Include blocked tickets** — note what unblocks them and when they might
+   become actionable during the sprint.
+
+3. **Write the plan to the plan file** — the plan should be self-contained so
+   you can follow it step-by-step once approved.
+
+4. **Exit plan mode** — use `ExitPlanMode` to present the plan for user
+   approval before starting any implementation work.
+
+Only after the user approves the plan should you mark the first ticket as
+`in_progress` and begin implementation.