@sellable/mcp 0.1.151 → 0.1.152

package/skills/create-campaign-v2/core/auto-execute.yaml

@@ -14,10 +14,11 @@
 version: 1
 
 import:
-  # Initial review batch imported in Step 13 before the sample validation
-  # loop. Import + enrichment must never exceed this cap before the user
-  # reviews the sample and explicitly asks to expand.
-  importLimit: 25
+  # Initial review/process sample used after the confirmed source list is copied
+  # into the campaign. Enrichment must never exceed this cap before the message
+  # template is approved and the sample proves at least one passing generated
+  # message.
+  importLimit: 15
   # Provider is inherited from the campaign-attached source association created
   # during find-leads. Step 13 may re-run provider preflight in memory, but it
   # does not choose a new source.
@@ -27,11 +28,11 @@ sample:
   # Rows pulled from the imported cohort for the validation loop. In v2 this
   # equals the review-batch cap so the user sees a focused first test batch
   # without spending credits on hundreds of rows.
-  sampleSize: 25
+  sampleSize: 15
   # Projected first-batch passing count required to proceed to sample
   # messaging. This is not approval to scale the full source list.
   # projectedPass = round(passInSample / sampleSize * importLimit).
-  minProjectedPass: 5
+  minProjectedPass: 1
   # Hard cap on revision loops before escalating to the user. On a stale
   # resume the counter does NOT reset — the 3-round cap holds across
   # sessions.
@@ -106,7 +107,7 @@ handoff:
   # Orientation surfaced in Step 16 ("awaiting-user-greenlight") along with
   # the watch link. Keep this short and user-facing.
   orientation: >-
-    Review the first 25 enriched leads and messages. If they look good,
+    Review the first generated passing message. If it looks good,
     attach a sender in Settings, accept the recommended sequence, and start
     the campaign without spending credits on more leads first.
 

package/skills/create-campaign-v2/core/flow.v2.json

@@ -1,8 +1,8 @@
 {
   "version": "v2.1-compact",
   "workflow": "create-campaign-v2",
-  "principle": "CampaignOffer state and the watch link are canonical from the first brief onward. The active customer path is shell-first and state-first: create the watchable campaign shell with the brief, attach source/search state to that CampaignOffer, import one bounded review batch, persist rubrics, wait on Filter Leads for approved message-template review, save the approved template, validate the bounded review batch, generate and review bounded messages, then hand off to Settings, sequence, and explicit start.",
-  "normalCustomerPath": "Use campaign state, MCP tool responses, and concise watchNarration. Do not create, read, link, or surface local draft files in normal customer runs.",
+  "principle": "CampaignOffer state and watch link are canonical. Create the watched shell, approve source, materialize and confirm the source list, process the first 15 review rows, save rubrics for approval, approve the message template, then run the bounded filter/message cascade before Settings, sequence, and explicit start.",
+  "normalCustomerPath": "Use campaign state, MCP responses, and concise watchNarration. Do not create, read, link, or surface local draft files.",
   "legacyCompatibility": {
     "validationSubskill": "create-campaign-v2-validation",
     "tailSubskill": "create-campaign-v2-tail",
@@ -63,9 +63,7 @@
       "references/lead-validation-preview.md",
       "references/step-13-import-leads.md"
     ],
-    "filter": [
-      "references/filter-leads.md"
-    ],
+    "filter": ["references/filter-leads.md"],
     "message": [],
     "tail": [
       "references/sample-validation-loop.md",
@@ -76,7 +74,7 @@
   "safetyBoundaries": [
     "Do not call list_senders before Settings after message approval.",
     "Do not import leads until the source decision is approved.",
-    "Do not queue cells until the bounded review batch exists and the message/filter gates are satisfied.",
+    "Do not queue cells until confirmed source rows exist in the campaign and the message/filter gates are satisfied.",
     "Do not call start_campaign until the user explicitly confirms launch.",
     "Do not use local files as durable state in normal customer runs."
   ],
@@ -174,10 +172,7 @@
             "currentStep": "create-offer",
             "watchNarration.stage": "brief"
           },
-          "capture": [
-            "campaignId",
-            "watchUrl"
-          ],
+          "capture": ["campaignId", "watchUrl"],
           "canonicalStateWrites": [
             "campaignId",
             "watchUrl",
@@ -218,11 +213,7 @@
         "queue_cells",
         "start_campaign"
       ],
-      "waitFor": [
-        "campaign_shell_created",
-        "brief_ready",
-        "confirm_with_user"
-      ],
+      "waitFor": ["campaign_shell_created", "brief_ready", "confirm_with_user"],
       "transitions": {
         "campaign_shell_created": "brief-review",
         "brief_ready": "brief-review",
@@ -240,11 +231,7 @@
         {
           "action": "ask_brief_choice",
           "uses": "request_user_input",
-          "choices": [
-            "Approve brief",
-            "Revise brief",
-            "Pause here"
-          ]
+          "choices": ["Approve brief", "Revise brief", "Pause here"]
         }
       ],
       "requiredCampaignState": [
@@ -266,11 +253,7 @@
         "queue_cells",
         "start_campaign"
       ],
-      "waitFor": [
-        "user_brief_confirmed",
-        "revise_brief",
-        "auto_continue"
-      ],
+      "waitFor": ["user_brief_confirmed", "revise_brief", "auto_continue"],
       "transitions": {
         "user_brief_confirmed": "find-leads",
         "revise_brief": "brief-interview",
@@ -300,7 +283,7 @@
             "fallback lane if the first lane is weak",
             "what approval authorizes"
           ],
-          "approvalAuthorizes": "source scouting/search only; no lead import, review-batch creation, filtering, messaging, sequence, or launch"
+          "approvalAuthorizes": "source scouting/search only; no import/send"
         },
         "defaultWhenSourceUnspecified": [
           "signal-discovery",
@@ -341,6 +324,8 @@
         {
           "action": "show_pre_scout_source_recommendation",
           "uses": "request_user_input",
+          "oneShot": true,
+          "skipIf": "approved or leadSourceProvider",
           "requiredBeforeTools": [
             "get_provider_prompt",
             "search_signals",
@@ -406,11 +391,7 @@
           "stopOnFirstViableUnlessComparisonRequested": true
         }
       ],
-      "requiredCampaignState": [
-        "campaignId",
-        "campaignBrief",
-        "currentStep"
-      ],
+      "requiredCampaignState": ["campaignId", "campaignBrief", "currentStep"],
       "allowedTools": [
         "get_source_scout_registry",
         "get_provider_prompt",
@@ -438,11 +419,7 @@
         "queue_cells",
         "start_campaign"
       ],
-      "waitFor": [
-        "lead_review_ready",
-        "revise_brief",
-        "confirm_with_user"
-      ],
+      "waitFor": ["lead_review_ready", "revise_brief", "confirm_with_user"],
       "transitions": {
         "lead_review_ready": "lead-review",
         "revise_brief": "brief-interview",
@@ -458,9 +435,9 @@
           "requiredInlineFields": [
             "primary source and exact filters/recipe",
             "specific source action awaiting approval",
-            "for Signal Discovery: Source Recommendation markdown with ~150 good-fit prospects as the target, source-candidate plan ~1,000 raw engagers at a conservative ~15% fit assumption, review checkpoint size, selected-post table, total visible pool, estimated good-fit pool, first pass, and fallback",
+            "for Signal Discovery: compact Source Recommendation with target, raw-engager math, selected-post table, review checkpoint, estimated fit, and fallback",
             "for Signal Discovery: selected post count and target engager/source-candidate volume",
-            "bounded review batch size",
+            "15-row review/process sample size",
             "runner-up and why it lost",
             "raw volume",
             "sampled people",
@@ -475,14 +452,14 @@
           "uses": "request_user_input",
           "choices": [
             "Approve scraping N Signal Discovery posts",
-            "Run the approved source import for the bounded review batch",
+            "Run the approved source import",
             "Revise source",
             "Pause here"
           ],
           "approvalChoiceLabelsByProvider": {
             "signal-discovery": "Approve scraping {selectedPostCount} Signal Discovery posts?",
-            "sales-nav": "Import the approved Sales Nav review batch",
-            "prospeo": "Import the approved Prospeo review batch"
+            "sales-nav": "Import the approved Sales Nav source list",
+            "prospeo": "Import the approved Prospeo source list"
           },
           "postApprovalContract": {
             "singleUseApproval": true,
@@ -491,8 +468,8 @@
               "show_source_decision_card",
               "ask_source_review_choice"
             ],
-            "requiredNextActionAfterApproval": "acknowledge in one sentence, then call import_leads immediately",
-            "signalDiscoveryNextTool": "import_leads({ campaignOfferId, provider: \"signal-discovery\", targetEngagerCount, maxPostsToScrape, confirmed: true })"
+            "requiredNextActionAfterApproval": "ack once; call import_leads immediately",
+            "signalDiscoveryNextTool": "import_leads({ provider: \"signal-discovery\", targetEngagerCount, maxPostsToScrape, confirmed: true })"
           }
         }
       ],
@@ -530,7 +507,7 @@
     },
     {
       "id": "auto-execute-leads",
-      "label": "Import bounded review batch",
+      "label": "Materialize confirmed source list",
       "currentStepValue": "auto-execute-leads",
       "reference": "references/step-13-import-leads.md",
       "onEnter": [
@@ -546,10 +523,11 @@
           "requiredFields": [
             "campaignOfferId",
             "selected source/list",
-            "importLimit"
+            "sourceListTarget or targetEngagerCount"
           ],
           "requiredValues": {
-            "importLimit": 25
+            "salesNavProspeoDefaultSourceListTarget": 1000,
+            "signalDiscoveryDefaultEngagerTarget": 1500
           },
           "modeAddHandshake": {
             "firstCallReturns": "needsModeSelection when adding to an existing campaign-attached list",
@@ -567,10 +545,10 @@
             "selectedLeadListId",
             "reviewBatchLimit"
           ],
-          "capture": [
-            "workflowTableId",
-            "reviewBatchRowIds"
-          ]
+          "requiredValues": {
+            "reviewBatchLimit": 15
+          },
+          "capture": ["workflowTableId", "reviewBatchRowIds"]
         },
         {
           "tool": "wait_for_campaign_table_ready"
@@ -581,9 +559,7 @@
             "tableId": "{workflowTableId}",
             "limit": 15
           },
-          "capture": [
-            "reviewBatchRowHash"
-          ]
+          "capture": ["reviewBatchRowHash"]
         },
         {
           "action": "summarize_review_batch_and_advance_to_filter_choice",
@@ -618,9 +594,9 @@
         "bulk_enrich_with_prospeo",
         "save_rubrics"
       ],
-      "waitFor": "review_batch_imported",
+      "waitFor": "source_list_confirmed_and_review_sample_ready",
       "transitions": {
-        "review_batch_imported": "filter-choice",
+        "source_list_confirmed_and_review_sample_ready": "filter-choice",
         "escalation_triggered": "escalation"
       }
     },
@@ -639,11 +615,7 @@
         {
           "action": "ask_filter_choice",
           "uses": "request_user_input",
-          "choices": [
-            "Use filters",
-            "Skip filters",
-            "Revise source"
-          ]
+          "choices": ["Use filters", "Skip filters", "Revise source"]
         }
       ],
       "hardRules": [
@@ -679,11 +651,7 @@
         "start_campaign",
         "generate_messages"
       ],
-      "waitFor": [
-        "filters_enabled",
-        "filters_skipped",
-        "revise_leads"
-      ],
+      "waitFor": ["filters_enabled", "filters_skipped", "revise_leads"],
       "transitions": {
         "filters_enabled": "post-lead-workstreams",
         "filters_skipped": "message-generation",
@@ -749,16 +717,19 @@
           "action": "save_filter_rubrics_to_campaign",
           "tool": "save_rubrics",
           "when": "filters_enabled and rubrics are production-shaped",
-          "requiredFields": [
-            "campaignOfferId",
-            "leadScoringRubrics"
-          ],
+          "requiredFields": ["campaignOfferId", "leadScoringRubrics"],
           "writesCampaignState": "leadScoringRubrics",
           "requiredSideEffects": {
             "enableICPFilters": true,
-            "currentStep": "apply-icp-rubric",
-            "watchNarration.headline": "Filter rules saved"
+            "currentStep": "create-icp-rubric",
+            "watchNarration.headline": "Filter rules saved for review"
           }
+        },
+        {
+          "action": "ask_filter_rubric_review_choice",
+          "uses": "request_user_input",
+          "choices": ["Approve filters", "Revise filters", "Pause"],
+          "purpose": "let the user read saved rubrics before Filter Leads or enrichment"
         }
       ],
       "requiredCampaignState": [
@@ -792,13 +763,14 @@
         "generate_messages"
       ],
       "waitFor": [
-        "post_lead_workstreams_ready",
+        "filter_rubrics_approved",
         "revise_leads",
         "revise_rubric",
         "revise_messaging"
       ],
       "hardRules": [
-        "after_save_rubrics_currentStep_must_be_apply-icp-rubric",
+        "after_save_rubrics_currentStep_must_stay_create-icp-rubric_until_filter_approval",
+        "filter_approval_required_before_apply-icp-rubric_or_queue_cells",
         "do_not_move_browser_to_messages_until_filter_leads_step_is_current_or_filters_are_explicitly_skipped",
         "no_post_lead_worker_or_deep_prompt_before_filter_choice",
         "lead_fit_builder_starts_only_after_filters_enabled",
@@ -806,7 +778,7 @@
         "msg_draft_no_cells"
       ],
       "transitions": {
-        "post_lead_workstreams_ready": "message-generation",
+        "filter_rubrics_approved": "message-generation",
         "revise_leads": "find-leads",
         "revise_rubric": "filter-rubric",
         "revise_messaging": "message-generation",
@@ -826,22 +798,21 @@
         },
         {
           "tool": "save_rubrics",
-          "requiredFields": [
-            "campaignOfferId",
-            "leadScoringRubrics"
-          ],
+          "requiredFields": ["campaignOfferId", "leadScoringRubrics"],
           "writesCampaignState": "leadScoringRubrics",
           "requiredSideEffects": {
             "enableICPFilters": true,
-            "currentStep": "apply-icp-rubric",
-            "watchNarration.headline": "Filter rules saved"
+            "currentStep": "create-icp-rubric",
+            "watchNarration.headline": "Filter rules saved for review"
           }
+        },
+        {
+          "action": "ask_filter_rubric_review_choice",
+          "uses": "request_user_input",
+          "choices": ["Approve filters", "Revise filters", "Pause"]
         }
       ],
-      "requiredCampaignState": [
-        "campaignId",
-        "workflowTableId"
-      ],
+      "requiredCampaignState": ["campaignId", "workflowTableId"],
       "allowedTools": [
         "get_subskill_asset",
         "save_rubrics",
@@ -859,13 +830,13 @@
         "check_rubric"
       ],
       "waitFor": [
-        "lead_filter_ready",
+        "filter_rubrics_approved",
         "revise_leads",
         "confirm_with_user",
         "auto_continue"
       ],
       "transitions": {
-        "lead_filter_ready": "message-generation",
+        "filter_rubrics_approved": "message-generation",
         "revise_leads": "find-leads",
         "confirm_with_user": "message-generation",
         "auto_continue": "message-generation"
@@ -879,7 +850,7 @@
           "action": "set_message_review_visible_step_by_filter_choice",
           "tool": "update_campaign",
           "branchRules": [
-            "yes: currentStep=apply-icp-rubric; wait on Filter Leads",
+            "yes after filter approval: currentStep=apply-icp-rubric; wait on Filter Leads",
             "no: currentStep=messages; message review"
           ],
           "watchNarration.stage": "fit-message"
@@ -910,9 +881,9 @@
         "request_user_input"
       ],
       "toolRules": [
-        "Message Draft Builder must run as the background post-find-leads-message-scout when the host exposes it. If the host cannot launch the agent, the parent-thread fallback must execute the same full get_subskill_prompt({ subskillName: \"generate-messages\" }) from live state before drafting.",
-        "Do not use brief.md, lead-review.md, or lead-sample.json as required live state; those files are optional debug context only.",
-        "The messageDraftRecommendation must return templateRecommendation, tokenFillRules, renderedSample, concerns, status, basisToken, outputAt, outputHash, and error or retry detail.",
+        "Run post-find-leads-message-scout when available; otherwise parent fallback must load get_subskill_prompt({ subskillName: \"generate-messages\" }) from live state.",
+        "brief.md, lead-review.md, and lead-sample.json are optional debug context only.",
+        "messageDraftRecommendation returns templateRecommendation, tokenFillRules, renderedSample, concerns, status, basisToken, outputAt, outputHash, and error/retry detail.",
         "If campaign/source/table/review-batch basis does not match, classify the output stale or blocked."
       ],
       "doNotAllow": [
@@ -976,10 +947,7 @@
         {
           "action": "ask_message_review_choice",
           "uses": "request_user_input",
-          "choices": [
-            "approve-message",
-            "revise-messaging"
-          ]
+          "choices": ["approve-message", "revise-messaging"]
         },
         {
           "action": "sync_approved_message_set_to_campaign_brief",
@@ -1004,9 +972,7 @@
         "request_user_input",
         "update_campaign_brief",
         "update_campaign",
-        "get_rows_minimal",
-        "queue_cells",
-        "wait_for_rubric_results"
+        "get_rows_minimal"
       ],
       "doNotAllow": [
         "create_campaign",
@@ -1016,10 +982,7 @@
         "confirm_lead_list",
         "start_campaign"
       ],
-      "waitFor": [
-        "message_approved",
-        "revise_messaging"
-      ],
+      "waitFor": ["message_approved", "revise_messaging"],
       "transitions": {
         "message_approved": "validate-sample",
         "revise_messaging": "message-generation"
@@ -1027,10 +990,10 @@
     },
     {
       "id": "validate-sample",
-      "label": "Validate bounded review batch",
+      "label": "Validate first review/process sample",
       "currentStepValue": "apply-icp-rubric",
       "reference": "references/sample-validation-loop.md",
-      "visibleStepRule": "This is the same Filter Leads screen reached by save_rubrics. Do not route away from or back to Filter Leads on approve-message; save the approved template, refresh watch narration on apply-icp-rubric, then queue the bounded Enrich Prospect cells.",
+      "visibleStepRule": "Filter Leads is reached only after saved-filter approval. On approve-message, save the template, refresh apply-icp-rubric narration, then queue bounded Enrich Prospect cells.",
       "onEnter": [
         {
           "tool": "update_campaign",
@@ -1043,13 +1006,13 @@
         },
         {
           "tool": "queue_cells",
-          "purpose": "queue ICP/enrichment cells for the bounded review batch only",
+          "purpose": "queue ICP/enrichment cells for the first 15 review/process rows only",
           "requiredFields": [
             "workflowTableId",
             "reviewBatchRowIds",
             "cellTypes"
           ],
-          "targetCountSource": "reviewBatchRowIds.length"
+          "targetCountSource": "reviewBatchRowIds.length (default 15)"
         },
         {
           "tool": "wait_for_campaign_table_ready",
@@ -1085,7 +1048,8 @@
       "requiredCampaignState": [
         "campaignId",
         "workflowTableId",
-        "approvedMessageTemplate"
+        "approvedMessageTemplate",
+        "filterRubricsApproved when enableICPFilters=true"
       ],
       "allowedTools": [
         "get_subskill_asset",
@@ -1111,10 +1075,7 @@
         "timeout_never_repeats_without_customer_handoff",
         "timeout_or_underfloor_sample_never_advances_to_settings"
       ],
-      "waitFor": [
-        "sample_validated",
-        "sample_revision_required"
-      ],
+      "waitFor": ["sample_validated", "sample_revision_required"],
       "transitions": {
         "sample_validated": "auto-execute-messaging",
         "sample_revision_required": "lead-review",
@@ -1229,10 +1190,7 @@
         "opus_reserved_for_highest_value_subset",
         "proposed_token_never_persisted_in_rewrite"
       ],
-      "waitFor": [
-        "generated_messages_approved",
-        "sample_revision_required"
-      ],
+      "waitFor": ["generated_messages_approved", "sample_revision_required"],
       "transitions": {
         "generated_messages_approved": "awaiting-user-greenlight",
         "revise_filters": "filter-rubric",
@@ -1287,9 +1245,7 @@
           "tool": "update_campaign",
           "when": "user selected an available connected sender",
           "requiredValues": {
-            "senderIds": [
-              "{selectedSenderId}"
-            ],
+            "senderIds": ["{selectedSenderId}"],
             "currentStep": "sequence",
             "watchNarration.stage": "review-ready"
           },
@@ -1309,11 +1265,7 @@
           "action": "ask_final_launch_greenlight",
           "uses": "request_user_input",
           "singleChoice": true,
-          "choices": [
-            "Start campaign",
-            "Review campaign first",
-            "Pause here"
-          ],
+          "choices": ["Start campaign", "Review campaign first", "Pause here"],
           "onUserStart": "claude-greenlight"
         }
       ],
@@ -1326,10 +1278,7 @@
         "AskUserQuestion",
         "request_user_input"
       ],
-      "doNotAllow": [
-        "start_campaign",
-        "import_leads"
-      ],
+      "doNotAllow": ["start_campaign", "import_leads"],
       "autoStart": false,
       "watchRequired": true,
       "waitFor": [
@@ -1369,9 +1318,7 @@
         },
         {
           "tool": "start_campaign",
-          "requiredFields": [
-            "campaignId"
-          ],
+          "requiredFields": ["campaignId"],
           "persistsCurrentStep": "running",
           "watchNarrationRule": "After start_campaign succeeds, the running state must say the final greenlight was accepted, the campaign is now live/running, and the user can watch progress from the campaign."
         }
@@ -1401,28 +1348,16 @@
           "action": "surface_campaign_live_confirmation"
         }
       ],
-      "allowedTools": [
-        "get_campaign",
-        "AskUserQuestion",
-        "request_user_input"
-      ],
-      "doNotAllow": [
-        "start_campaign"
-      ],
+      "allowedTools": ["get_campaign", "AskUserQuestion", "request_user_input"],
+      "doNotAllow": ["start_campaign"],
       "terminal": true
     },
     {
       "id": "escalation",
       "label": "Escalation",
       "reference": "references/escalation-ladder.md",
-      "allowedTools": [
-        "AskUserQuestion",
-        "request_user_input"
-      ],
-      "doNotAllow": [
-        "start_campaign",
-        "import_leads"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
+      "doNotAllow": ["start_campaign", "import_leads"],
       "transitions": {
         "revise_brief": "brief-interview",
         "revise_leads": "find-leads",
@@ -1434,10 +1369,7 @@
     {
       "id": "abort",
       "label": "Abort",
-      "allowedTools": [
-        "AskUserQuestion",
-        "request_user_input"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
       "terminal": true
     }
   ]

package/skills/create-campaign-v2/core/policy.md

@@ -36,10 +36,11 @@ mutation gates:
   plan or explicitly chooses a source.
 - Do not call `import_leads` or `confirm_lead_list` until the concrete source
   action is approved.
-- Import/confirm only the first bounded review batch before message approval.
-- Do not call `queue_cells` until filter choice is resolved, rubrics are saved
-  when filters are enabled, and the default Use Template path has an approved
-  message template/token rule set.
+- Copy the confirmed source list into the campaign, but process only the first
+  review/process sample before message approval.
+- Do not call `queue_cells` for enrichment/filtering until filters are approved
+  when enabled and the default Use Template path has an approved message
+  template/token rule set.
 - Do not attach a sequence or call `start_campaign` until the user explicitly
   chooses to launch.
 
@@ -50,13 +51,13 @@ Customer roleplay critique is advisory only. It cannot approve a campaign.
 Do not run a downstream stage until the matching live state exists:
 
 - campaign shell exists before a watch link is shown as active
-- selected source/list state exists before importing a review batch
-- `workflowTableId` and non-empty bounded review-batch rows exist before filter
+- selected source/list state exists before copying source rows into the campaign
+- `workflowTableId` and non-empty review/process sample rows exist before filter
   and message branches run
-- `leadScoringRubrics` are saved before queueing ICP filter cells when filters
+- `leadScoringRubrics` are saved and approved before Filter Leads when filters
   are enabled
-- approved message template/token rules are written to campaign brief before
-  queueing Generate Message cells on the default Use Template path
+- approved message template/token rules are written to the campaign brief before
+  queueing enrichment, ICP scoring, or Generate Message cells
 
 ## 5) Revision Routing
 
@@ -70,9 +71,9 @@ Revision choices route back to the exact upstream stage:
 
 ## 6) Post-Message Tail
 
-After message approval, queue only the bounded review-batch cells needed to move
-the watched app through enrichment, ICP filtering, and approved-template
-message generation. Keep the tail observable through watch narration.
+After message approval, queue only the first review/process sample cells needed to move
+the watched app through enrichment, ICP filtering, and approved-template message
+generation. Keep the tail observable through watch narration.
 
 The tail stops at `awaiting-user-greenlight`. Never call `start_campaign`
 inside the autonomous tail.

package/skills/create-campaign-v2/references/approval-gate-framing.md

@@ -14,9 +14,10 @@ packet.
 ## Purpose
 
 The approval gate used to be the place where the user authorized
-spend/send-adjacent mutation. It is now compatibility-only. New runs import the
-bounded review batch after source approval, save rubrics and the approved
-message template after post-import review, and only then queue the cascade.
+spend/send-adjacent mutation. It is now compatibility-only. New runs copy the
+confirmed source list into the campaign after source approval, use the first
+review/process sample for post-import review, save rubrics and the approved
+message template, and only then queue the cascade.
 
 If `campaign-shell.json` exists, a draft `CampaignOffer` row already exists but
 must remain non-sendable. If no shell exists, no campaign row exists until the