@sellable/mcp 0.1.100 → 0.1.102

package/dist/tools/sequencer.d.ts

@@ -30,6 +30,7 @@ export type AttachSequenceResponse = {
 export type AttachRecommendedSequenceInput = {
     campaignId: string;
     confirmed?: boolean;
+    currentStep?: string;
 };
 export type AttachRecommendedSequenceResponse = {
     success: boolean;
@@ -74,6 +75,7 @@ export declare const sequencerToolDefinitions: ({
             template?: undefined;
             confirmed?: undefined;
             campaignId?: undefined;
+            currentStep?: undefined;
         };
         required: string[];
     };
@@ -101,6 +103,7 @@ export declare const sequencerToolDefinitions: ({
             senderLinkedinUrl?: undefined;
             sequenceActions?: undefined;
             campaignId?: undefined;
+            currentStep?: undefined;
         };
         required: string[];
     };
@@ -118,6 +121,10 @@ export declare const sequencerToolDefinitions: ({
                 type: string;
                 description: string;
             };
+            currentStep: {
+                type: string;
+                description: string;
+            };
             name?: undefined;
             senderId?: undefined;
             clientProspectId?: undefined;

package/dist/tools/sequencer.js

@@ -81,6 +81,10 @@ export const sequencerToolDefinitions = [
                     type: "boolean",
                     description: "Set true to overwrite existing sequence columns if the campaign already has a sequence attached",
                 },
+                currentStep: {
+                    type: "string",
+                    description: "Optional CampaignOffer currentStep to persist with the sequence attach, usually 'send' after the recommended sequence is bound.",
+                },
             },
             required: ["campaignId"],
         },
@@ -178,6 +182,9 @@ export async function attachRecommendedSequence(input) {
         return await api.put(`/api/v3/campaigns/${input.campaignId}/sequence`, {
             autoSelectFromSenders: true,
             confirmed: input.confirmed,
+            ...(input.currentStep !== undefined
+                ? { currentStep: input.currentStep }
+                : {}),
         });
     }
     catch (error) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.100",
+  "version": "0.1.102",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/create-campaign/SKILL.md

@@ -155,7 +155,8 @@ for them. The link is for deeper inspection; never use it as a substitute for
 showing the content in chat.
 
 Never mention MCP namespaces, prompt chunking, plugin cache paths, missing
-linked skill versions, runbooks, or local skill files in normal customer-facing
+linked skill versions, runbooks, npm/package details, repo-local files, VPS or
+browser automation limitations, or local skill files in normal customer-facing
 copy.
 
 ## Codex Watch Browser Handoff
@@ -173,16 +174,17 @@ In Codex Desktop, when in-app browser control is available, open the returned wa
 I’ll open the campaign view and keep it in sync as I build.
 ```
 
-If browser control is unavailable, say so briefly and provide the watch link.
-In VPS or other off-desktop Codex runs, this fallback is the expected handoff for
-the local headed watch observer: make the signed link easy to copy/open, then
-continue with explicit chat progress and `get_campaign_navigation_state`
-orientation checks.
+If browser control is unavailable, provide the watch link without discussing the
+runtime limitation. In off-desktop Codex runs, make the signed link easy to
+copy/open, then continue with explicit customer-facing campaign progress and
+`get_campaign_navigation_state` orientation checks.
 Use this fallback shape:
 
 ```text
-I can’t inspect the campaign browser from this Codex session, so I’ll keep the
-chat steps explicit here. Watch link: {watchUrl}
+Watch link: {watchUrl}
+
+I’ll keep the campaign brief, lead source, and message-review steps explicit
+here as I build.
 ```
 
 If opening the watch link lands on an auth, 404, permission, blank, or visible
@@ -195,7 +197,7 @@ it was opened and observed.
 After every `update_campaign({ campaignId, currentStep })`, use
 `get_campaign_navigation_state` when available as a compact orientation check:
 match the browser-visible step to the saved campaign state, explain the current
-state in one sentence, and only then continue. Sender selection belongs at Settings after message approval and 10-row validation. Do not attach a sequence, start the campaign, or trigger a live send unless the user explicitly confirms that launch action outside UAT.
+state in one sentence, and only then continue. Sender selection belongs at Settings after message approval and 10-row validation. After message validation, use Settings to help the user connect or select a LinkedIn sender. Explain Slack reply review before launch. After sender selection, attach the recommended sequence and move the watched UI to Send. Do not start the campaign or trigger a live send unless the user explicitly confirms that launch action outside UAT.
 
 ## Names To Use
 
@@ -566,7 +568,9 @@ updates.
    the brief, `pick-provider` or the selected provider step while sourcing,
    `filter-choice` after the 10-row review batch, `messages` or
    `auto-execute-messaging` for message work, `validate-sample` for validation,
-   and `awaiting-user-greenlight` for Settings. Do not advance the step backward.
+   `awaiting-user-greenlight` for the final handoff, `settings` for sender
+   selection, `sequence` after sender attach, and `send` once the recommended
+   sequence is attached. Do not advance the step backward.
 7. Keep `selectedLeadListId` as the source list and `workflowTableId` as the
    campaign table. Do not use disk files as the post-mint source of truth.
 8. Do not ask the user to run another command.

package/skills/create-campaign-v2/SKILL.md

@@ -107,9 +107,15 @@ Optional debug/UAT draft directory, disabled in normal customer runs:
   import, saved rubrics, and the approved message template. It must never queue
   workflow cells, attach a sequence, or start sending until rubrics are saved
   and the approved message set has been synced into the campaign brief.
-- Sender ownership stays out of this plan. senderIds persistence is Plan 04;
-  update_campaign({ senderIds }) delegates to the v3 senders route and never
-  uses the v2 campaign-offers PUT for sender persistence.
+- Sender ownership belongs only to the final Settings handoff after message
+  validation. At that point the main thread may ask the user to connect or
+  select a LinkedIn sender, explain Slack reply review before launch, attach the
+  selected sender with `update_campaign({ senderIds, currentStep: "sequence" })`,
+  attach the recommended sequence, then move the watched UI to Send. It still
+  must not start sending until the user explicitly greenlights launch.
+- senderIds persistence uses `update_campaign({ senderIds })`, which delegates
+  to the v3 senders route and never uses the v2 campaign-offers PUT for sender
+  persistence.
 - Load `core/flow.v2.json` through
   `get_subskill_asset({ subskillName: "create-campaign-v2", assetPath: "core/flow.v2.json" })`
   at the start of the run and treat the returned JSON as the active state
@@ -161,7 +167,9 @@ Optional debug/UAT draft directory, disabled in normal customer runs:
 - Customer-facing progress updates must use product language. Say "quick
   setup choices", "campaign brief", "lead sourcing", and "approval" instead of
   `request_user_input`, Default mode, MCP namespaces, plugin caches, prompt
-  loading, runbooks, local skill files, skill versions, or "Sellable token".
+  loading, runbooks, local skill files, skill versions, npm/package details,
+  repo-local files, VPS/off-desktop/browser automation limitations, or
+  "Sellable token".
   "Quick question panel" is only acceptable when explaining a Codex/Claude setup
   blocker.
 - Before the 10-lead import/test batch, do not call `check_rubric`; Phase 84
@@ -613,9 +621,11 @@ There are four customer-visible gates in the net-new hosted flow:
   one more messaging revision (`revise-messaging`). `approve-message` authorizes
   syncing the approved message set into the campaign brief, saving rubrics,
   importing the bounded 10-lead test batch, and queueing/observing that sample.
-- The sender/settings/sequence handoff is the launch gate. Starting the campaign
-  still waits until a sender is attached, the sequence is accepted, and the user
-  greenlights start.
+- The sender/settings/sequence handoff is the launch gate. After message
+  validation, use Settings to help the user connect or select a LinkedIn sender.
+  Explain Slack reply review before launch. After sender selection, attach the
+  recommended sequence and move the watched UI to Send. Starting the campaign
+  still waits until the user explicitly greenlights start.
 
 Auto-continue without a structured question gate when the artifact says
 `Status: confirmed` (or equivalent), confidence is high/medium, volume is
@@ -728,8 +738,10 @@ Required behavior:
 - provider prompt preflight and interaction-mode approval are in-memory. On
   resume or MCP restart, call `get_provider_prompt({ provider, campaignOfferId })`
   again before any provider search/import; do not assume CampaignOffer state
-  proves preflight happened in this process.
-  on resume or MCP restart, call `get_provider_prompt({ provider, campaignOfferId })` again.
+  proves preflight happened in this process. Immediately before `import_leads`,
+  reload the provider prompt in the same turn with
+  `get_provider_prompt({ provider, campaignOfferId })`, even when source preview
+  loaded it in a previous turn.
 - if CampaignOffer campaignId is missing, stop and recover shell creation before
   sourcing; do not run a campaignless source path in the active flow.
 - do not import leads

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

@@ -58,6 +58,9 @@
     "message_set_synced_to_brief",
     "review_batch_imported",
     "settings_link_surfaced",
+    "sender_connection_required",
+    "sender_attached",
+    "ready_to_launch",
     "sequence_attached"
   ],
   "steps": [
@@ -840,6 +843,7 @@
         },
         {
           "tool": "import_leads",
+          "sameTurnPreflight": "Immediately before import_leads, call get_provider_prompt({ provider, campaignOfferId }) in the same resumed turn, even if source discovery loaded the provider prompt earlier.",
           "requiredFields": [
             "campaignOfferId",
             "targetLeadCount"
@@ -2138,16 +2142,76 @@
           "purpose": "surface available connected senders if the campaign has none attached"
         },
         {
-          "action": "verify_sender_attached_or_route_to_settings",
+          "tool": "update_campaign",
+          "requiredValues": {
+            "currentStep": "settings"
+          },
+          "purpose": "park the watched UI on Settings before sender selection"
+        },
+        {
+          "tool": "get_campaign_navigation_state",
+          "purpose": "confirm the watched UI is oriented to Settings before sender selection",
+          "optional": true
+        },
+        {
+          "action": "surface_sender_and_slack_handoff",
           "settingsUrlPattern": "/campaign-builder/{campaignId}/settings?mode=claude",
-          "onMissingSender": "surface settings link and STOP before sequence attach/start",
-          "onSenderAttached": "continue_to_sequence_selection"
+          "requiredVisibleContent": [
+            "connect or select a LinkedIn sender",
+            "Slack reply review",
+            "nothing starts until the user confirms launch"
+          ],
+          "onNoAvailableSender": "surface settings link and wait for sender_connection_required",
+          "onAvailableSender": "ask the user which connected sender to attach"
         },
         {
-          "action": "verify_sequence_attached_or_route_to_sequence",
-          "sequenceUrlPattern": "/campaign-builder/{campaignId}/sequence?mode=claude",
-          "onMissingSequence": "surface sequence link and STOP before start",
-          "onSequenceAttached": "continue_to_greenlight_handoff"
+          "action": "ask_sender_selection",
+          "uses": "request_user_input",
+          "singleChoice": true,
+          "choices": [
+            "Use this connected sender",
+            "Connect a different sender in Settings",
+            "Pause here"
+          ],
+          "uatSafety": "Only auto-select a mock/safe sender when an explicit UAT safe-mode sender is active; never select a real sender in UAT."
+        },
+        {
+          "action": "attach_selected_sender",
+          "tool": "update_campaign",
+          "when": "user selected an available connected sender",
+          "requiredValues": {
+            "senderIds": [
+              "{selectedSenderId}"
+            ],
+            "currentStep": "sequence"
+          }
+        },
+        {
+          "tool": "get_campaign_navigation_state",
+          "purpose": "confirm the watched UI moved to Sequence after sender attach",
+          "optional": true
+        },
+        {
+          "tool": "attach_recommended_sequence",
+          "when": "after senderIds are attached",
+          "requiredValues": {
+            "campaignId": "{campaignId}",
+            "currentStep": "send"
+          },
+          "purpose": "bind the tier-aware recommended sequence before the launch decision"
+        },
+        {
+          "tool": "update_campaign",
+          "when": "sequence attach response does not persist currentStep",
+          "requiredValues": {
+            "currentStep": "send"
+          },
+          "purpose": "show the Send tab once sender and sequence are ready"
+        },
+        {
+          "tool": "get_campaign_navigation_state",
+          "purpose": "confirm the watched UI is on Send before final launch greenlight",
+          "optional": true
         },
         {
           "action": "surface_watch_link",
@@ -2172,13 +2236,26 @@
           "fromConfig": "handoff.orientation"
         },
         {
-          "action": "stop_and_wait_for_greenlight"
+          "action": "ask_final_launch_greenlight",
+          "uses": "request_user_input",
+          "singleChoice": true,
+          "choices": [
+            "Start campaign",
+            "Review campaign first",
+            "Pause here"
+          ],
+          "onUserStart": "claude-greenlight",
+          "onReviewFirst": "awaiting-user-greenlight",
+          "onPause": "awaiting-user-greenlight"
         }
       ],
       "allowedTools": [
         "get_subskill_asset",
         "get_campaign",
+        "get_campaign_navigation_state",
         "list_senders",
+        "update_campaign",
+        "attach_recommended_sequence",
         "AskUserQuestion",
         "request_user_input"
       ],
@@ -2189,14 +2266,18 @@
       "autoStart": false,
       "watchRequired": true,
       "waitFor": [
+        "sender_connection_required",
         "sender_attached",
         "sequence_attached",
+        "ready_to_launch",
         "user_greenlight",
         "ui_start_detected"
       ],
       "transitions": {
+        "sender_connection_required": "awaiting-user-greenlight",
         "sender_attached": "awaiting-user-greenlight",
         "sequence_attached": "awaiting-user-greenlight",
+        "ready_to_launch": "awaiting-user-greenlight",
         "user_greenlight": "claude-greenlight",
         "ui_start_detected": "running"
       },

package/skills/create-campaign-v2/references/final-handoff-contract.md

@@ -29,29 +29,42 @@ order (all before waiting for the user):
    least one attached sender and whether a sequence is already attached.
 2. Call `list_senders()` so the handoff can name available connected senders if
    the campaign has none selected.
-3. If no sender is attached, surface the campaign Settings link
-   `/campaign-builder/{campaignId}/settings?mode=claude`, tell the user to attach
-   a sender there, and STOP. Do not attach sequence and do not start.
-4. If a sender is attached but no sequence is attached, surface the campaign
-   Sequence link `/campaign-builder/{campaignId}/sequence?mode=claude`, tell the
-   user to accept or adjust the recommended sequence there, and STOP. Do not
-   start. The Claude greenlight path may use
-   `attach_recommended_sequence({ campaignId })` as an explicit repair after the
-   user asks to start.
-5. Re-surface the `watchUrl` using the exact block in
+3. Call `update_campaign({ campaignId, currentStep: "settings" })` and use
+   `get_campaign_navigation_state` when available so the watch link visibly
+   lands on Settings before sender setup.
+4. Explain sender setup and Slack in normal customer language: Sellable needs a
+   connected LinkedIn sender before anything can send, and Slack reply review
+   matters because replies and approvals need a channel the team will monitor.
+5. If no connected sender exists, surface the campaign Settings link
+   `/campaign-builder/{campaignId}/settings?mode=claude`, tell the user to
+   connect a sender there, and STOP. Do not attach sequence and do not start.
+6. If connected senders exist and no sender is attached, ask the user which
+   connected sender to attach. Attach only the chosen sender. In explicit UAT
+   safe mode, auto-select only the safe mock sender; never select a real sender.
+7. Call `update_campaign({ campaignId, senderIds: [selectedSenderId],
+   currentStep: "sequence" })` to attach the sender via the v3 senders route and
+   move the watch link to Sequence.
+8. Call `attach_recommended_sequence({ campaignId, currentStep: "send" })` to
+   bind the tier-aware recommended sequence. If that response does not persist
+   `currentStep: "send"`, call `update_campaign({ campaignId, currentStep:
+   "send" })`.
+9. Re-surface the `watchUrl` using the exact block in
    `references/watch-link-handoff.md`.
-6. Surface the `handoff.orientation` string from `auto-execute.yaml`
+10. Surface the `handoff.orientation` string from `auto-execute.yaml`
    alongside the watch link so the user sees both the link and the
    "what to do next" sentence.
-7. STOP. Do not call `start_campaign`. Do not advance `currentStep`.
+11. Ask the final launch greenlight with the structured question function:
+    Start campaign, Review campaign first, or Pause here.
+12. STOP unless the user explicitly chooses Start campaign. Do not call
+    `start_campaign` from Step 16 itself.
 
 The final handoff must answer five customer questions in plain language:
 
 - where to inspect the campaign (`watchUrl`)
 - what is ready now (brief, filters/rubrics, review-batch leads, messages, and
-  sequence when a sender is attached)
-- whether the next UI step is Settings because a sender still needs to be
-  attached
+  sequence after a sender is attached)
+- whether the next UI step is Settings, Sequence, or Send
+- why the selected LinkedIn sender and Slack reply review matter before launch
 - what clicking Start does (approves/starts the campaign send path)
 - how to revise (reply with what to change, or use the campaign UI)
 - whether anything has started yet (nothing sends until the user starts)
@@ -67,8 +80,11 @@ When `lead-source-intake.json` exists, also answer:
 - for `existing-lead-list`, that the source list was reused, not recreated
 
 Use the exact state name `awaiting-user-greenlight` so logs and UX artifacts
-can verify the stop point, but explain it in normal words: the campaign is
-built and waiting for the user's final start decision.
+can verify the state-machine stop point, but explain it in normal words: the
+campaign is built, sender/sequence setup is being completed, and nothing sends
+until the user's final start decision. The watched UI may advance through
+Settings, Sequence, and Send while this state-machine step remains the final
+handoff.
 
 The skill waits. It does not poll. A fresh continuation turn arrives
 either because the user said something in chat (Claude greenlight path)
@@ -79,9 +95,9 @@ the UI.
 
 ### UI path
 
-The user reviews messages in the watch link, attaches a sender in Settings when
-needed, chooses/accepts the sequence, bulk-approves messages in the workflow
-table UI (the existing "Approve all" button that wraps
+The user reviews messages in the watch link, connects or selects a sender in
+Settings when needed, reviews the recommended sequence, bulk-approves messages
+in the workflow table UI (the existing "Approve all" button that wraps
 `POST /api/v3/workflow-tables/cells/approve-batch`), and clicks "Start Campaign"
 in the campaign-builder UI.
 
@@ -100,8 +116,8 @@ order, atomically:
    if already running.
 2. **Validate sender + sequence state.** If no sender is attached, refuse start
    and return the Settings link. If no sequence is attached but a sender is
-   attached, call `attach_recommended_sequence({ campaignId })` before approving
-   messages.
+   attached, call `attach_recommended_sequence({ campaignId, currentStep:
+   "send" })` before approving messages.
 3. **Bulk-approve queued messages** via the existing endpoint
    `POST /api/v3/workflow-tables/cells/approve-batch` with
    `{ tableId }`.
@@ -191,10 +207,11 @@ does NOT silently proceed.
 ## Hard Rules
 
 - The autonomous tail NEVER calls `start_campaign` on its own.
-- Step 16 NEVER auto-advances past `awaiting-user-greenlight` without a
-  user signal.
-- Step 16 routes to Settings before sequence/start when no sender is attached.
-- Step 16 routes to Sequence before start when no sequenceTemplate is attached.
+- Step 16 may move the watched UI through Settings, Sequence, and Send, but it
+  NEVER transitions to `running` or calls `start_campaign` without a user signal.
+- Step 16 routes to Settings before sender attach.
+- Step 16 routes to Sequence after sender attach and before sequence attach.
+- Step 16 routes to Send after the recommended sequence is attached.
 - Prefer `attach_recommended_sequence`; use `attach_sequence` only for an
   explicitly custom cadence.
 - Bulk-approve in the Claude greenlight path uses the EXISTING

package/skills/create-campaign-v2-tail/SKILL.md

@@ -61,10 +61,14 @@ Step 15 — observe messaging
 
 Step 16 — awaiting-user-greenlight
   get_campaign + list_senders
-  if no sender attached: surface campaign settings link and STOP
-  if sender attached: attach_recommended_sequence({ campaignId })  # tier-aware: premium/SN -> If Open Profile->INMAIL_OPEN, else INVITE->accepted->DM
-  re-surface watchUrl + review-batch orientation
-  STOP. DO NOT call start_campaign. DO NOT auto-advance currentStep.
+  update_campaign(currentStep=settings) + orient the watch link to Settings
+  if no connected sender exists: explain sender setup + Slack reply review, surface campaign settings link, and STOP
+  ask the user which connected sender to attach; in explicit UAT safe mode only, use the safe mock sender
+  update_campaign(senderIds=[selectedSenderId], currentStep=sequence)
+  attach_recommended_sequence({ campaignId, currentStep: "send" })  # tier-aware: premium/SN -> If Open Profile->INMAIL_OPEN, else INVITE->accepted->DM
+  if the attach response did not move the UI: update_campaign(currentStep=send)
+  re-surface watchUrl + review-batch orientation + final launch choices
+  STOP. DO NOT call start_campaign. DO NOT move to running without explicit launch greenlight.
 ```
 
 **Prefer `attach_recommended_sequence` over `attach_sequence` in the
@@ -136,7 +140,8 @@ reuse the v1 `create-campaign` watch-mode pattern verbatim.
 
 Resume currentStep names covered by this tail: `"auto-execute-leads"`,
 `"validate-sample"`, `"auto-execute-messaging"`,
-`"awaiting-user-greenlight"`, and `"running"`. New mint-early runs normally
+`"awaiting-user-greenlight"`, `"settings"`, `"sequence"`, `"send"`, and
+`"running"`. New mint-early runs normally
 enter Step 13 from `"confirm-lead-list"`; the `"auto-execute-leads"` string is
 kept for compatibility resumes.
 
@@ -407,7 +412,8 @@ row. Step 15 does not stall on critique.
 
 ## Step 16: awaiting-user-greenlight
 
-Entered on `CampaignOffer.currentStep === "awaiting-user-greenlight"`.
+Entered on `CampaignOffer.currentStep === "awaiting-user-greenlight"` or a
+final-handoff UI step (`"settings"`, `"sequence"`, or `"send"`).
 Full contract lives in `references/final-handoff-contract.md`.
 
 Shape:
@@ -415,17 +421,35 @@ Shape:
 1. Call `get_campaign({ campaignId })` and inspect sender/sequence state.
 2. Call `list_senders()` so you can surface connected sender options if the
    campaign has no attached sender.
-3. If the campaign has no attached sender, surface a direct settings link:
-   `/campaign-builder/{campaignId}/settings?mode=claude`. Tell the user to attach
-   a sender in Settings, then return here. STOP before sequence attach/start.
-4. If a sender is attached, call `attach_recommended_sequence({ campaignId })`
-   (bind the tier-recommended sequence to the campaign).
-5. Re-surface the `watchUrl` using `references/watch-link-handoff.md`.
-6. Surface the `handoff.orientation` string from `auto-execute.yaml`
+3. Call `update_campaign({ campaignId, currentStep: "settings" })`, then use
+   `get_campaign_navigation_state` when available to confirm the watch link is
+   visibly on Settings.
+4. Explain why the sender matters: Sellable needs a connected LinkedIn sender
+   before anything can send. Explain Slack reply review before launch: replies
+   and approvals need a place the team will actually monitor, so Slack should be
+   connected or intentionally skipped before launch.
+5. If no connected sender exists, surface a direct Settings link:
+   `/campaign-builder/{campaignId}/settings?mode=claude`. Tell the user to
+   connect a sender there, then return here. STOP before sequence attach/start.
+6. If connected senders exist but none is attached, ask the user which connected
+   sender to attach. Attach only after the user chooses. In explicit UAT safe
+   mode, use only the safe mock sender; never pick a real sender.
+7. Call `update_campaign({ campaignId, senderIds: [selectedSenderId],
+   currentStep: "sequence" })` to attach the sender through the v3 senders
+   route and orient the watch link to Sequence.
+8. Call `attach_recommended_sequence({ campaignId, currentStep: "send" })`
+   (bind the tier-recommended sequence to the campaign). If the tool response
+   does not persist `currentStep: "send"`, call
+   `update_campaign({ campaignId, currentStep: "send" })`.
+9. Re-surface the `watchUrl` using `references/watch-link-handoff.md`.
+10. Surface the `handoff.orientation` string from `auto-execute.yaml`
    alongside the link.
-7. STOP. Do NOT call `start_campaign`. Do NOT auto-advance
-   `currentStep`. The autonomous tail ends here.
-8. Make the credit boundary explicit in the handoff: only the first review
+11. Ask the final launch greenlight with the structured question function:
+   Start campaign, Review campaign first, or Pause here.
+12. STOP unless the user explicitly chooses Start campaign. Do NOT call
+   `start_campaign` from Step 16 itself; that belongs only to the Claude
+   greenlight path. The autonomous tail ends here.
+13. Make the credit boundary explicit in the handoff: only the first review
    batch has been enriched/messaged; expanding to more leads requires a
    separate user instruction.
 
@@ -441,9 +465,9 @@ campaign:
   sequence is attached, `attach_recommended_sequence({ campaignId })`, (c)
   bulk-approve queued messages via the EXISTING endpoint
   `POST /api/v3/workflow-tables/cells/approve-batch` (do NOT invent a
-  new tool/endpoint), (d) `start_campaign({ campaignId })`, (e)
-  `update_campaign({ campaignId, currentStep: "running" })`, (f)
-  re-surface `watchUrl` plus a "campaign is live" confirmation.
+  new tool/endpoint), (d) `start_campaign({ campaignId })`, which persists
+  `currentStep: "running"`, (e) re-surface `watchUrl` plus a "campaign is live"
+  confirmation.
 
 A Claude greenlight on an already-running campaign is a no-op
 confirmation, NOT a duplicate start. Detect via `get_campaign` before