diff --git a/WORK-RECORDS.md b/WORK-RECORDS.md
index 87ffb48..c832170 100644
--- a/WORK-RECORDS.md
+++ b/WORK-RECORDS.md
@@ -10,6 +10,7 @@
 | --- | --- | --- | --- | --- |
 | workplan | CB-WP-0001 | done | — | workplans/CB-WP-0001-inner-loop.md |
 | workplan | CB-WP-0002 | proposed | — | workplans/CB-WP-0002-cost-accounting.md |
+| workplan | CB-WP-0003 | proposed | — | workplans/CB-WP-0003-loop-hardening.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 |
@@ -26,3 +27,13 @@
 | task | CB-WP-0002-T05 | todo | — | workplans/CB-WP-0002-cost-accounting.md |
 | task | CB-WP-0002-T06 | todo | — | workplans/CB-WP-0002-cost-accounting.md |
 | task | CB-WP-0002-T07 | todo | — | workplans/CB-WP-0002-cost-accounting.md |
+| task | CB-WP-0003-T01 | todo | — | workplans/CB-WP-0003-loop-hardening.md |
+| task | CB-WP-0003-T02 | todo | — | workplans/CB-WP-0003-loop-hardening.md |
+| task | CB-WP-0003-T03 | todo | — | workplans/CB-WP-0003-loop-hardening.md |
+| task | CB-WP-0003-T04 | todo | — | workplans/CB-WP-0003-loop-hardening.md |
+| task | CB-WP-0003-T05 | todo | — | workplans/CB-WP-0003-loop-hardening.md |
+| task | CB-WP-0003-T06 | todo | — | workplans/CB-WP-0003-loop-hardening.md |
+| task | CB-WP-0003-T07 | todo | — | workplans/CB-WP-0003-loop-hardening.md |
+| task | CB-WP-0003-T08 | todo | — | workplans/CB-WP-0003-loop-hardening.md |
+| task | CB-WP-0003-T09 | todo | — | workplans/CB-WP-0003-loop-hardening.md |
+| task | CB-WP-0003-T10 | todo | — | workplans/CB-WP-0003-loop-hardening.md |
diff --git a/workplans/CB-WP-0003-loop-hardening.md b/workplans/CB-WP-0003-loop-hardening.md
index 65b8c1e..a7ee57c 100644
--- a/workplans/CB-WP-0003-loop-hardening.md
+++ b/workplans/CB-WP-0003-loop-hardening.md
@@ -2,6 +2,7 @@
 id: CB-WP-0003
 title: "Harden the inner loop: executable rules, session economics, dead policy"
 status: proposed
+state_hub_workstream_id: "39d61dc0-870d-45c1-a595-bcf91f289dce"
 ---
 
 # Purpose
@@ -36,6 +37,7 @@ deleted.
 id: CB-WP-0003-T01
 status: todo
 priority: high
+state_hub_task_id: "3d5d45fb-f931-407a-be71-d2d727279d5e"
 ```
 
 Go through `specs/InnerLoop.md` v1.0 rule by rule and classify each:
@@ -60,6 +62,7 @@ added in v1.0 are currently prose.
 id: CB-WP-0003-T02
 status: todo
 priority: high
+state_hub_task_id: "f861e67f-ed09-489d-963d-06697da9c08e"
 ```
 
 `cargo bench -- --test` now covers benchmarks. The same error class
@@ -80,6 +83,7 @@ convention nobody can verify.
 id: CB-WP-0003-T03
 status: todo
 priority: medium
+state_hub_task_id: "1365b35d-4539-489a-beff-c072221e4702"
 ```
 
 The review step is specified for tier-L *research*. All four real errors
@@ -102,6 +106,7 @@ identify what the harness would report if the work silently stopped).
 id: CB-WP-0003-T04
 status: todo
 priority: high
+state_hub_task_id: "382724e6-efd5-4ef8-a438-9d31a65dacdb"
 ```
 
 Measured from the CB-WP-0001 session: **592 assistant turns, mean
@@ -131,6 +136,7 @@ policy.
 id: CB-WP-0003-T05
 status: todo
 priority: medium
+state_hub_task_id: "26c920ee-2c09-4b45-a908-4d343532db09"
 ```
 
 The global 8k soft / 10k hard per-task token budget was never
@@ -152,6 +158,7 @@ restating it.
 id: CB-WP-0003-T06
 status: todo
 priority: low
+state_hub_task_id: "8f3a6147-54e8-48f9-8543-c13b0e0b0278"
 ```
 
 The d10 tier roll never fired across the whole pass — roughly 0.2
@@ -170,6 +177,7 @@ to reject.
 id: CB-WP-0003-T07
 status: todo
 priority: medium
+state_hub_task_id: "2f702821-7e64-4981-9885-82fa07f638aa"
 ```
 
 AM-4's new targets were measured at 246,250 and set at 250,000 **in the
@@ -189,6 +197,7 @@ and AM-4b — either ratify them by ADR or change them.
 id: CB-WP-0003-T08
 status: todo
 priority: low
+state_hub_task_id: "c2ee91ee-e551-48a7-b1a9-477c34c0690c"
 ```
 
 Ten U-items plus GR-E02's "successes" are marked `provisional: true`
@@ -206,6 +215,7 @@ file must list them, not that the build breaks.
 id: CB-WP-0003-T09
 status: todo
 priority: low
+state_hub_task_id: "69ccc9ec-dc35-481c-8065-cef040f07f50"
 ```
 
 `make coverage` compares rule IDs in the spec against `covers:` lists.
@@ -225,6 +235,7 @@ scenario that claims it?) and cost it before adopting.
 id: CB-WP-0003-T10
 status: todo
 priority: low
+state_hub_task_id: "f43de208-92b1-4f0e-9236-a9d27f3ec451"
 ```
 
 Revise `specs/InnerLoop.md` to v1.1 from this pass. The question to