diff --git a/.story_kit/current/60_status_based_directory_layout.md b/.story_kit/current/60_status_based_directory_layout.md
index 18c53b6..7585192 100644
--- a/.story_kit/current/60_status_based_directory_layout.md
+++ b/.story_kit/current/60_status_based_directory_layout.md
@@ -27,41 +27,47 @@ As a developer, I want work items organized by pipeline status rather than by ty
 
 ```
 .story_kit/
-  upcoming/        ← all work items waiting to start
-  current/         ← being coded
-  qa/              ← being reviewed by QA agent
-  merge/           ← being merged to master
-  archived/        ← done
-  specs/           ← long-lived project info (not a work item)
+  work/
+    1_upcoming/    ← all work items waiting to start
+    2_current/     ← being coded by agents
+    3_qa/          ← being reviewed by QA agent
+    4_merge/       ← being merged to master
+    5_archived/    ← done
+  specs/           ← long-lived project info (not a workflow stage)
   worktrees/       ← agent worktrees (unchanged)
   project.toml     ← config (unchanged)
 ```
 
+The numbered `work/` subdirectories define the workflow pipeline. `ls` shows them in pipeline order. `specs/`, `worktrees/`, and `project.toml` are infrastructure outside the workflow.
+
 ## Naming Convention
 
 All work items use: `{number}_{type}_{slug}.md`
 
 ```
-upcoming/57_story_foo_bar_blah.md
-upcoming/58_spike_a_b_c.md
-upcoming/59_bug_flappapa.md
+work/1_upcoming/57_story_foo_bar_blah.md
+work/1_upcoming/58_spike_a_b_c.md
+work/1_upcoming/59_bug_flappapa.md
 ```
 
 Types: `story`, `bug`, `spike`. The number is the primary identifier, auto-incremented across all types. You say "story 57", "bug 59", etc.
 
 ## Acceptance Criteria
 
-- [ ] Migrate existing `stories/upcoming/` → `upcoming/`, renaming files to include `_story_` type prefix
-- [ ] Migrate existing `stories/archived/` → `archived/`, renaming files to include `_story_` type prefix
-- [ ] Migrate existing `bugs/` → `archived/` (for closed) or `upcoming/` (for open), renaming to include `_bug_` type prefix
-- [ ] Remove old `stories/`, `bugs/` directories
-- [ ] `create_story`, `create_bug` MCP tools use the new naming convention and write to `upcoming/`
-- [ ] `start_agent` moves from `upcoming/` to `current/`
-- [ ] `accept_story` and `close_bug` move from `current/` (or `merge/`) to `archived/`
-- [ ] `find_story_file()` and all path references updated to search by status dirs
-- [ ] `next_story_number()` scans all status dirs for the highest number across all types
+- [ ] Create `work/` directory with numbered subdirectories: `1_upcoming`, `2_current`, `3_qa`, `4_merge`, `5_archived`
+- [ ] Migrate existing `stories/upcoming/` → `work/1_upcoming/`, renaming files to include `_story_` type prefix
+- [ ] Migrate existing `stories/archived/` → `work/5_archived/`, renaming files to include `_story_` type prefix
+- [ ] Migrate existing `current/` contents → `work/2_current/`
+- [ ] Migrate existing `bugs/` → `work/5_archived/` (for closed) or `work/1_upcoming/` (for open), renaming to include `_bug_` type prefix
+- [ ] Remove old `stories/`, `bugs/`, `current/` directories
+- [ ] `create_story`, `create_bug` MCP tools use the new naming convention and write to `work/1_upcoming/`
+- [ ] `start_agent` moves from `work/1_upcoming/` to `work/2_current/`
+- [ ] `accept_story` and `close_bug` move from `work/2_current/` (or `work/4_merge/`) to `work/5_archived/`
+- [ ] `find_story_file()` and all path references updated to search `work/` status dirs
+- [ ] `next_story_number()` scans all `work/` status dirs for the highest number across all types
+- [ ] All agent prompts in `project.toml` updated to reference `work/` paths
 - [ ] All existing tests updated for new paths
-- [ ] Integration test: full lifecycle through upcoming → current → archived
+- [ ] Integration test: full lifecycle through `1_upcoming` → `2_current` → `5_archived`
 
 ## Supersedes