diff --git a/.beads/formulas/mol-deacon-patrol.formula.yaml b/.beads/formulas/mol-deacon-patrol.formula.yaml
index a708ac55..7db00d04 100644
--- a/.beads/formulas/mol-deacon-patrol.formula.yaml
+++ b/.beads/formulas/mol-deacon-patrol.formula.yaml
@@ -13,6 +13,7 @@ version: 1
 
 steps:
   - id: inbox-check
+    title: Handle callbacks from agents
     description: |
       Handle callbacks from agents.
 
@@ -32,6 +33,7 @@ steps:
       Callbacks may spawn new polecats, update issue state, or trigger other actions.
 
   - id: trigger-pending-spawns
+    title: Nudge newly spawned polecats
     needs: [inbox-check]
     description: |
       Nudge newly spawned polecats that are ready for input.
@@ -58,6 +60,7 @@ steps:
       Timeout: 60 seconds per polecat. If not ready, try again next cycle.
 
   - id: health-scan
+    title: Check Witness and Refinery health
     needs: [trigger-pending-spawns]
     description: |
       Check Witness and Refinery health for each rig.
@@ -118,6 +121,7 @@ steps:
       Reset unresponsive_cycles to 0 when component responds normally.
 
   - id: plugin-run
+    title: Execute registered plugins
     needs: [health-scan]
     description: |
       Execute registered plugins.
@@ -144,6 +148,7 @@ steps:
       Skip this step if ~/gt/plugins/ does not exist or is empty.
 
   - id: orphan-check
+    title: Find abandoned work
     needs: [health-scan]
     description: |
       Find abandoned work.
@@ -165,6 +170,7 @@ steps:
       - File incident beads if data loss occurred
 
   - id: session-gc
+    title: Clean dead sessions
     needs: [orphan-check]
     description: |
       Clean dead sessions.
@@ -183,6 +189,7 @@ steps:
       Preserve audit trail. Only clean sessions confirmed dead.
 
   - id: context-check
+    title: Check own context limit
     needs: [session-gc]
     description: |
       Check own context limit.
@@ -202,6 +209,7 @@ steps:
       This enables the Deacon to burn and respawn cleanly.
 
   - id: loop-or-exit
+    title: Burn and respawn or loop
     needs: [context-check]
     description: |
       Burn and let daemon respawn, or exit if context high.
diff --git a/.beads/formulas/mol-polecat-arm.formula.yaml b/.beads/formulas/mol-polecat-arm.formula.yaml
index a821f5fa..823bbcbc 100644
--- a/.beads/formulas/mol-polecat-arm.formula.yaml
+++ b/.beads/formulas/mol-polecat-arm.formula.yaml
@@ -26,6 +26,7 @@ variables:
 
 steps:
   - id: capture
+    title: Capture polecat state
     description: |
       Capture recent tmux output for {{polecat_name}}.
 
@@ -39,6 +40,7 @@ steps:
       - Completion indicators ("Done", "Finished", etc.)
 
   - id: assess
+    title: Assess work status
     needs: [capture]
     description: |
       Categorize polecat state based on captured output.
@@ -53,6 +55,7 @@ steps:
       Calculate: minutes since last activity.
 
   - id: load-history
+    title: Load intervention history
     needs: [assess]
     description: |
       Read nudge history for {{polecat_name}} from patrol state.
@@ -66,6 +69,7 @@ steps:
       to the arm via the bonding context.
 
   - id: decide
+    title: Decide intervention action
     needs: [load-history]
     description: |
       Apply the nudge matrix to determine action for {{polecat_name}}.
@@ -90,6 +94,7 @@ steps:
       Record decision and rationale.
 
   - id: execute
+    title: Execute intervention
     needs: [decide]
     description: |
       Take the decided action for {{polecat_name}}.
diff --git a/.beads/formulas/mol-refinery-patrol.formula.yaml b/.beads/formulas/mol-refinery-patrol.formula.yaml
index d5922f0c..b55a32e9 100644
--- a/.beads/formulas/mol-refinery-patrol.formula.yaml
+++ b/.beads/formulas/mol-refinery-patrol.formula.yaml
@@ -15,6 +15,7 @@ version: 1
 
 steps:
   - id: inbox-check
+    title: Check refinery mail
     description: |
       Check mail for MR submissions, escalations, messages.
 
@@ -26,6 +27,7 @@ steps:
       Handle shutdown requests, escalations, and status queries.
 
   - id: queue-scan
+    title: Scan merge queue
     needs: [inbox-check]
     description: |
       Fetch remote and identify polecat branches waiting.
@@ -40,6 +42,7 @@ steps:
       Track branch list for this cycle.
 
   - id: process-branch
+    title: Process next branch
     needs: [queue-scan]
     description: |
       Pick next branch. Rebase on current main.
@@ -55,6 +58,7 @@ steps:
       - Skip to loop-check for next branch
 
   - id: run-tests
+    title: Run test suite
     needs: [process-branch]
     description: |
       Run the test suite.
@@ -66,6 +70,7 @@ steps:
       Track results: pass count, fail count, specific failures.
 
   - id: handle-failures
+    title: Handle test failures
     needs: [run-tests]
     description: |
       **VERIFICATION GATE**: This step enforces the Beads Promise.
@@ -90,6 +95,7 @@ steps:
       This is non-negotiable. Never disavow. Never "note and proceed."
 
   - id: merge-push
+    title: Merge and push to main
     needs: [handle-failures]
     description: |
       Merge to main and push immediately.
@@ -105,6 +111,7 @@ steps:
       Main has moved. Any remaining branches need rebasing on new baseline.
 
   - id: loop-check
+    title: Check for more work
     needs: [merge-push]
     description: |
       More branches to process?
@@ -115,6 +122,7 @@ steps:
       Track: branches processed, branches skipped (with reasons).
 
   - id: generate-summary
+    title: Generate handoff summary
     needs: [loop-check]
     description: |
       Summarize this patrol cycle.
@@ -129,6 +137,7 @@ steps:
       This becomes the digest when the patrol is squashed.
 
   - id: context-check
+    title: Check own context limit
     needs: [generate-summary]
     description: |
       Check own context usage.
@@ -141,6 +150,7 @@ steps:
       - Can continue processing
 
   - id: burn-or-loop
+    title: Burn and respawn or loop
     needs: [context-check]
     description: |
       End of patrol cycle decision.
diff --git a/.beads/formulas/mol-witness-patrol.formula.yaml b/.beads/formulas/mol-witness-patrol.formula.yaml
index 33432078..3eeba556 100644
--- a/.beads/formulas/mol-witness-patrol.formula.yaml
+++ b/.beads/formulas/mol-witness-patrol.formula.yaml
@@ -36,6 +36,7 @@ steps:
   # --- PREFLIGHT PHASE ---
 
   - id: inbox-check
+    title: Process witness mail
     description: |
       Process witness mail: lifecycle requests, help requests.
 
@@ -53,6 +54,7 @@ steps:
       Mark messages as processed when complete.
 
   - id: check-refinery
+    title: Ensure refinery is alive
     needs: [inbox-check]
     description: |
       Ensure the refinery is alive and processing merge requests.
@@ -78,6 +80,7 @@ steps:
       This ensures polecats don't wait forever for their branches to merge.
 
   - id: load-state
+    title: Load persisted patrol state
     needs: [check-refinery]
     description: |
       Read handoff bead and get nudge counts.
@@ -98,6 +101,7 @@ steps:
   # --- DISCOVERY PHASE (Dynamic Bonding) ---
 
   - id: survey-workers
+    title: Survey all polecats (fanout)
     needs: [load-state]
     description: |
       List polecats and bond mol-polecat-arm for each one.
@@ -131,6 +135,7 @@ steps:
   # --- CLEANUP PHASE (Gate + Fixed Steps) ---
 
   - id: aggregate
+    title: Aggregate arm results
     needs: [survey-workers]
     waits_for: all-children
     description: |
@@ -147,6 +152,7 @@ steps:
       Build the consolidated state for save-state.
 
   - id: save-state
+    title: Persist patrol state
     needs: [aggregate]
     description: |
       Update handoff bead with new states.
@@ -165,6 +171,7 @@ steps:
       This state survives wisp burns and session cycles.
 
   - id: generate-summary
+    title: Generate handoff summary
     needs: [save-state]
     description: |
       Summarize this patrol cycle for digest.
@@ -180,6 +187,7 @@ steps:
       This becomes the digest when the patrol wisp is squashed.
 
   - id: context-check
+    title: Check own context limit
     needs: [generate-summary]
     description: |
       Check own context usage.
@@ -192,6 +200,7 @@ steps:
       - Can continue patrolling
 
   - id: burn-or-loop
+    title: Burn and respawn or loop
     needs: [context-check]
     description: |
       End of patrol cycle decision.