diff --git a/WORK-RECORDS.md b/WORK-RECORDS.md
index 5b5a155..809dd5a 100644
--- a/WORK-RECORDS.md
+++ b/WORK-RECORDS.md
@@ -11,6 +11,7 @@
 | workplan | CB-WP-0001 | done | — | workplans/CB-WP-0001-inner-loop.md |
 | workplan | CB-WP-0002 | done | — | workplans/CB-WP-0002-cost-accounting.md |
 | workplan | CB-WP-0003 | done | — | workplans/CB-WP-0003-loop-hardening.md |
+| workplan | CB-WP-0004 | proposed | — | workplans/CB-WP-0004-mechanical-work.md |
 | task | CB-WP-0001-T01 | done | — | workplans/CB-WP-0001-inner-loop.md |
 | task | CB-WP-0001-T02 | done | — | workplans/CB-WP-0001-inner-loop.md |
 | task | CB-WP-0001-T03 | done | — | workplans/CB-WP-0001-inner-loop.md |
@@ -38,3 +39,9 @@
 | task | CB-WP-0003-T09 | done | — | workplans/CB-WP-0003-loop-hardening.md |
 | task | CB-WP-0003-T10 | done | — | workplans/CB-WP-0003-loop-hardening.md |
 | task | CB-WP-0003-T11 | done | — | workplans/CB-WP-0003-loop-hardening.md |
+| task | CB-WP-0004-T01 | todo | — | workplans/CB-WP-0004-mechanical-work.md |
+| task | CB-WP-0004-T02 | todo | — | workplans/CB-WP-0004-mechanical-work.md |
+| task | CB-WP-0004-T03 | todo | — | workplans/CB-WP-0004-mechanical-work.md |
+| task | CB-WP-0004-T04 | todo | — | workplans/CB-WP-0004-mechanical-work.md |
+| task | CB-WP-0004-T05 | todo | — | workplans/CB-WP-0004-mechanical-work.md |
+| task | CB-WP-0004-T06 | todo | — | workplans/CB-WP-0004-mechanical-work.md |
diff --git a/workplans/CB-WP-0004-mechanical-work.md b/workplans/CB-WP-0004-mechanical-work.md
index c0ad520..ea3fe1b 100644
--- a/workplans/CB-WP-0004-mechanical-work.md
+++ b/workplans/CB-WP-0004-mechanical-work.md
@@ -2,7 +2,7 @@
 id: CB-WP-0004
 title: "Move mechanical turns off the token budget, and prove it worked"
 status: proposed
-state_hub_workstream_id: ""
+state_hub_workstream_id: "6880ac78-d817-41b9-b267-f12ff9deea28"
 ---
 
 # Purpose
@@ -43,7 +43,7 @@ unless the instrument disproved it (§Step 4, correction vs retarget).
 id: CB-WP-0004-T01
 status: todo
 priority: high
-state_hub_task_id: ""
+state_hub_task_id: "3ddfd3e2-8596-4969-a069-09577933fcbc"
 ```
 
 84 turns / $15.33, the largest category and the least interesting work in
@@ -70,7 +70,7 @@ still cheaper than a regression.
 id: CB-WP-0004-T02
 status: todo
 priority: high
-state_hub_task_id: ""
+state_hub_task_id: "8a1b59c7-6318-47ba-8cbc-83bb44dd221f"
 ```
 
 Merges two categories: workplan status edits (21 turns, $4.06) and hub
@@ -99,7 +99,7 @@ stops holding estimates. Add `--self-test` per InnerLoop v1.1.
 id: CB-WP-0004-T03
 status: todo
 priority: medium
-state_hub_task_id: ""
+state_hub_task_id: "5466a510-37a5-4491-b93e-509cd400cc23"
 ```
 
 49 turns / $6.87 of `grep`/`ls`/`wc` answering "what is the state of this
@@ -123,7 +123,7 @@ disappear, and the review says so.
 id: CB-WP-0004-T04
 status: todo
 priority: high
-state_hub_task_id: ""
+state_hub_task_id: "b5dfbf1e-619b-4e64-8463-49ff2ce38b48"
 ```
 
 75 turns / $13.86 of heredocs opening a markdown file, string-replacing a
@@ -158,7 +158,7 @@ Confidence medium; this is the hardest task here and the most valuable.
 id: CB-WP-0004-T05
 status: todo
 priority: high
-state_hub_task_id: ""
+state_hub_task_id: "922346ac-1e99-4e94-9dc6-35c8fa0eddc5"
 ```
 
 The task this workplan exists for. Run `make cost-mix` over the sessions
@@ -197,7 +197,7 @@ absolute dollars.
 id: CB-WP-0004-T06
 status: todo
 priority: low
-state_hub_task_id: ""
+state_hub_task_id: "47892c23-ef09-4910-a9af-327494289e05"
 ```
 
 The question to answer honestly: **does converting agent work to