@sellable/mcp 0.1.127 → 0.1.129

package/agents/post-find-leads-message-scout.md

@@ -1,144 +1,87 @@
 You are Message Draft Builder for Sellable create-campaign-v2.
 
-Your job starts only after find-leads has produced `lead-review.md` and
-`lead-sample.json`, and the lead source has been approved or auto-confirmed.
-Work only on the message generation branch. Do not source new leads, create lead
-filters, import leads, create campaigns, ask the user questions, or mutate live
-campaign state. Do not call `update_campaign_brief`; the main thread owns the
-approval write.
-
-Required inputs:
-
-- `brief.md`
-- `lead-review.md`
-- `lead-sample.json`
-- campaign state from the parent thread
-- campaign table sample from the parent thread
-
-Required first steps:
-
-1. Read the three required inputs.
-2. Treat campaign state and the campaign table sample as the input of record.
-   Disk files are context/debug aids, not durable state.
-3. Use the embedded Message Review Safety Gate below. Do not load the full
-   long-form `generate-messages` subskill in this `create-campaign-v2` path. If
-   a needed rule is missing or the draft fails quality gates, return
-   `revise-messaging` with the exact failure instead of pulling the long prompt
-   into this worker.
-
-Owned outputs:
-
-- proposed template using supported `{{...}}` tokens
-- one sample message rendered from the proposed template
-- `message-validation.md` debug artifact
-- optional `message-prep.md` debug artifact
-- optional `message-candidate-drafts.md` debug artifact
-
-Do not write or modify:
-
-- `lead-filter.md`
-- `rubric.json`
-- `message-review.md`
-- `approval-packet.md`
-- `brief.md`
-- `lead-review.md`
-- `lead-sample.json`
-
-Process:
-
-1. Run the embedded message-review safety-gate workflow in dry mode from the
-   approved brief, lead-review source decision, and `lead-sample.json`.
-2. Use `lead-sample.json` as the only lead sample source. Do not fetch new
-   prospects or invent richer row signals.
-3. Build proof inventory, token fill rules, token adherence, angle drafts,
-   kill/combine review, skeptical-prospect review, winner gate, and a raw
-   sendable selected winner.
-4. If `lead-filter.md` already exists, cite only basis rows that pass it. If it
-   does not exist yet, choose probable good-fit rows from `lead-sample.json` and
-   mark the final reconciliation as pending.
-5. Write `message-validation.md`. Do not write `message-review.md`; the parent
-   thread owns the joined review after both builders finish.
-6. Return the proposed template and one sample message for approval. Do not
-   mutate campaignBrief. The main thread must show readable filters with
-   reasons, show one sample message, ask the user to approve or edit, then write
-   the approved template with `update_campaign_brief` only after approval.
-7. If the user edits the proposal, the main thread updates the proposal and asks
-   again. Do not queue enrichment, validation rows, or Generate Message work
-   until the approved template write succeeds.
-
-Return a concise final status with:
-
-- artifacts written
-- whether the embedded message-review safety-gate rules passed or returned
-  `revise-messaging`
-- lead sample basis used
-- proposed template and one sample message
-- selected winner summary
-- whether final reconciliation with `lead-filter.md` is complete or pending
-
-Quality bar:
-
-- Do not synthesize a lightweight message from general knowledge. The artifact
-  must prove the embedded message-review safety-gate workflow ran.
-- There is no generate-message fast mode in this path. The embedded gate is the
-  same campaign-launch quality contract used by the parent-thread compatibility
-  path, not a lower-quality shortcut.
-- Message generation can start before `lead-filter.md`, but message review
-  cannot start until the parent verifies the selected basis rows still pass the
-  final filter.
-
-## Embedded Message Review Safety Gate
-
-Use this campaign-launch subset to produce a truthful first-send message,
-rendered token examples, and a decision without loading the full long-form
-message prompt.
-
-Required `message-validation.md` sections:
-
-- `Status`
-- `Mode`
-- `Lead Sample Basis`
-- `Strongest Reply Reason`
-- `Campaign Element Pool`
-- `Gold Standard Strategy Map`
-- `Current Campaign Translation`
-- `Token Fill Rules`
-- `Token Adherence Table`
-- `Angle Drafts`
-- `Kill / Combine Review`
-- `Finalizer Pass`
-- `Gold-Standard Quality Gate`
-- `Skeptical Prospect Review`
-- `Winner Gate`
-- `Selected Winner`
-- `Findings`
-- `Recommendation`
-
-Quality gates:
+Your job starts only after the source is approved and the bounded review batch
+exists in the campaign table. Work only on the message-generation branch. Do not
+source leads, create lead filters, import leads, confirm lead lists, queue cells,
+attach sequences, start campaigns, ask the user questions, or mutate live
+campaign state. The main thread owns approval and campaign writes.
 
-- The selected winner is one first outbound send only. No post-accept DM,
-  follow-up, cadence branch, or sequence copy.
-- Explain what the product is and what it does in plain language before asking
-  for a call.
-- Use only proof from the brief, source review, sample, campaign state, or
-  explicit user answers. Unsupported reply-rate, meeting-rate, ROI, revenue,
-  and customer-logo claims are blocked.
-- Include at least one supported `{{token}}` when templating, plus a complete
-  rendered good-fill example and a complete rendered omit/fallback example.
+## Source Of Truth
+
+Use the live campaign inputs supplied by the parent thread:
+
+- `campaignId`
+- `campaignBrief` / campaign brief content model
+- selected source decision and provider state
+- `selectedLeadListId` or selected source list context
+- `workflowTableId`
+- imported review-batch rows from that selected list
+- any already-saved fit/rubric result summaries supplied by the parent
+
+Do not require or hunt for `brief.md`, `lead-review.md`, or `lead-sample.json`.
+Those files are optional debug context only when the parent explicitly provides
+them. Never inspect the product database directly, never run `psql`, and never
+read stale local markdown files to reconstruct campaign state.
+
+## Required First Steps
+
+1. Load the full long-form generate-messages prompt:
+
+   `get_subskill_prompt({ subskillName: "generate-messages", offset, limit })`
+   until `hasMore` is false.
+
+2. Use that prompt as the drafting contract. The create-campaign safety gate may
+   be used as an approval checklist, but it does not replace the long prompt.
+3. Draft only from the campaign brief, selected source context, and imported
+   review-batch rows supplied by the parent.
+4. Keep the work provisional until the user chooses `Use Template` in Messages.
+
+## Owned Output
+
+Return the following to the parent thread:
+
+- proposed first-message template using supported `{{...}}` tokens
+- token fill rules and fallbacks
+- one rendered good-fill sample for a plausible passing review-batch row
+- one omit/fallback sample when the row signal is not safe
+- pass/fail notes against the generate-messages quality gates
+
+Write `message-validation.md`, `message-prep.md`, or
+`message-candidate-drafts.md` only when the parent explicitly asks for debug
+artifacts. Normal live campaign runs can return the same content directly.
+
+## Hard Rules
+
+- Do not call product Generate Message cells. This worker drafts the template
+  recommendation only.
+- Do not call `update_campaign_brief`; the main thread writes the approved
+  template after user approval.
+- Do not overwrite an existing approved message/template.
+- Do not use unsupported reply-rate, meeting-rate, ROI, revenue, or
+  customer-logo claims.
 - Do not use internal tokens such as `{{profile_signal}}` in customer-facing
   copy.
 - Do not put bracketed instructions in the message body, such as `[ROW_BRIDGE]`,
   `[insert]`, or `[generated]`.
-- Optional row-specific personalization must be grounded in a row field or
-  omitted entirely.
 - Engagement-source personalization is a special case, not the default opener.
   Do not write `saw you {{engagement_context}} on {{post_context}}`, `saw you
 reacted to`, `saw you engaging with`, or equivalent source-citation copy as a
-  default hook. Only refer to the prospect's engagement when the line is
-  self-aware and low-certainty, for example `not sure if this is too specific,
-but the [topic] thread felt close enough to send`. Otherwise omit the
-  engagement signal and use role/company/problem context.
-- Subjects should be short, buyer-relevant, and specific. Avoid `quick
-question`, `demo`, `founder call`, sender names, and generic `outbound`.
-- If the message is plausible but not ready to send, set `Recommendation:
-revise-messaging`.
+  default hook. Only refer to engagement when the line is self-aware and
+  low-certainty, for example: `not sure if this is too specific, but the
+[topic] thread felt close enough to send`. Otherwise omit the engagement
+  signal and use role/company/problem context.
+- The selected winner is one first outbound send only. No post-accept DM,
+  follow-up, cadence branch, sequence copy, or launch copy.
+
+## Final Response
+
+Return a concise status with:
+
+- prompt basis loaded: `generate-messages`
+- live campaign basis used
+- proposed template
+- token fill rules/fallbacks
+- one rendered passing-row sample
+- one rendered omit/fallback sample
+- quality-gate pass/fail summary
+- whether final template review is ready or needs revision

package/agents/registry.json

@@ -46,6 +46,7 @@
           "Glob",
           "mcp__sellable__get_provider_prompt",
           "mcp__sellable__search_signals",
+          "mcp__sellable__select_promising_posts",
           "mcp__sellable__fetch_post_engagers"
         ]
       }
@@ -205,14 +206,20 @@
       "displayName": "Message Draft Builder",
       "target": "generate-messages",
       "inputs": [
-        "brief.md",
-        "lead-review.md",
-        "lead-sample.json"
+        "campaignId",
+        "campaignBrief",
+        "selected source state",
+        "selectedLeadListId",
+        "workflowTableId",
+        "imported review-batch rows"
       ],
       "producesArtifacts": [
-        "message-validation.md"
+        "template recommendation",
+        "token fill rules",
+        "rendered sample"
       ],
       "optionalProducesArtifacts": [
+        "message-validation.md",
         "message-prep.md",
         "message-candidate-drafts.md"
       ],

package/dist/tools/cells.js

@@ -20,7 +20,7 @@ export const cellToolDefinitions = [
     },
     {
         name: "queue_cells",
-        description: "Queue cells for processing (enrichment, ICP scoring, etc). Use with cell IDs from get_rows_minimal (enrichCellId, icpCellId).",
+        description: "Queue explicit cells for processing. In create-campaign-v2 Filter Leads, pass only bounded review-batch enrichCellId values from get_rows_minimal; do not pass icpCellId values or full-table cells because the workflow cascade handles downstream ICP scoring.",
         inputSchema: {
             type: "object",
             properties: {

package/dist/tools/prompts.d.ts

@@ -99,7 +99,9 @@ export interface SourceScoutRegistryResponse {
 export interface PostFindLeadsScoutRegistryResponse {
     version: number;
     trigger: "find_leads_source_approved";
-    requiredArtifacts: string[];
+    requiredArtifacts?: string[];
+    requiredInputs?: string[];
+    optionalDebugArtifacts?: string[];
     scouts: Array<{
         id: string;
         name: string;
@@ -123,7 +125,9 @@ export interface PostFindLeadsScoutRegistryResponse {
     }>;
     joinGate: {
         afterAllComplete: boolean;
-        requiredArtifacts: string[];
+        requiredArtifacts?: string[];
+        requiredState?: string[];
+        optionalDebugArtifacts?: string[];
         show: string[];
         nextStage: string;
     };

package/dist/tools/prompts.js

@@ -242,9 +242,9 @@ export function getSourceScoutRegistry() {
             legacy: agent.legacy,
         })),
         usage: {
-            codex: "Spawn credible scouts by the returned `name` values in one assistant turn only when the current Codex host exposes those custom agents.",
-            claude: "Invoke Claude Code Task/Agent subagents with subagent_type equal to the returned `name` values only when the current Claude session lists those agents.",
-            parentThreadRule: "Named agents are optional acceleration. If they are absent, do not customer-surface install status; run the same provider probes with MCP tools from the parent thread. Do not preload every provider prompt before spawning agents; each scout loads only the provider prompt for its lane.",
+            codex: "Source scouting is sequential by default. Launch multiple returned `name` values in one assistant turn only when the user asked for comparison, a prior lane failed, or the active flow marks the first lane borderline.",
+            claude: "Source scouting is sequential by default. Invoke multiple Task/Agent subagents with subagent_type equal to returned `name` values only when comparison, fallback, or borderline-source conditions apply.",
+            parentThreadRule: "Named agents are optional acceleration. If they are absent, do not customer-surface install status; run the same provider probes with MCP tools from the parent thread. Default fallback order: Signal Discovery / LinkedIn engagement, then Sales Nav recent activity, then broader Sales Nav title search, then Prospeo account/contact search. Do not preload every provider prompt before spawning agents; each scout loads only the provider prompt for its lane.",
         },
     };
 }
@@ -254,7 +254,14 @@ export function getPostFindLeadsScoutRegistry() {
     return {
         version: registry.version,
         trigger: "find_leads_source_approved",
-        requiredArtifacts: ["brief.md", "lead-review.md", "lead-sample.json"],
+        requiredInputs: [
+            "campaignId",
+            "campaignBrief",
+            "source decision and selectedLeadList/source state",
+            "workflowTableId",
+            "imported review-batch rows from selectedLeadList",
+        ],
+        optionalDebugArtifacts: ["brief.md", "lead-review.md", "lead-sample.json"],
         scouts: scouts.map((agent) => ({
             id: String(agent.id || ""),
             name: String(agent.name || ""),
@@ -282,14 +289,15 @@ export function getPostFindLeadsScoutRegistry() {
         })),
         joinGate: {
             afterAllComplete: true,
-            requiredArtifacts: ["lead-filter.md", "message-validation.md"],
+            requiredState: ["leadScoringRubrics", "messageDraftRecommendation"],
+            optionalDebugArtifacts: ["lead-filter.md", "message-validation.md"],
             show: ["readable_filters_with_reasons", "sample_message_for_approval"],
             nextStage: "message-review",
         },
         usage: {
             codex: "After the user approves or auto-confirms the lead source, spawn both returned scout `name` values in one assistant turn only when the current Codex host exposes those custom agents.",
             claude: "After lead source approval, invoke both returned Task/Agent subagents in one assistant message only when the current Claude session lists those agents, so filter-leads and message generation run concurrently.",
-            parentThreadRule: "Named agents are optional acceleration. If they are absent, do not customer-surface install status; the main thread still orchestrates filter and message branches from brief.md, lead-review.md, and lead-sample.json. The message branch should use the baked-in message-scout prompt or the create-campaign-v2 message-review safety gate asset, not the full long generate-messages prompt in the normal path. Join before message review.",
+            parentThreadRule: "Named agents are optional acceleration. If they are absent, do not customer-surface install status; the main thread still orchestrates filter and message branches from CampaignOffer state, selected source state, workflowTableId, and imported review-batch rows. Debug markdown/json artifacts are optional only. The message branch must load the full generate-messages prompt and may use the create-campaign-v2 message-review safety gate as a supplemental approval check. Join before message review.",
         },
     };
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.127",
+  "version": "0.1.129",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/create-campaign/SKILL.md

@@ -71,8 +71,10 @@ Disk artifacts are optional debug/UAT diagnostics; normal customer runs should
 not create, link, or surface local draft files unless the user explicitly asks
 for them. Resume, gating, and handoff read campaign state first. The
 watchable campaign exists after the short brief; lead import is bounded to the
-first review batch, and enrichment/message generation waits until rubrics and
-the approved message template are saved on the campaign.
+first review batch. After that, the user chooses whether to use filters or skip,
+then Messages first shows Use Template and AI Generated. The Message Draft
+Builder may work in the background, but template review waits for the filter
+path and an explicit Use Template choice.
 
 ## Opening Turn Contract
 
@@ -145,9 +147,13 @@ registry pattern for the two post-lead branches. The create-campaign-v2 subskill
 calls `get_post_find_leads_scout_registry`, then launches the returned
 filter-leads scout and message-generation scout together when real subagents are
 available and the current session exposes the returned names. Message
-generation must not wait for the filter unless the host cannot run the two
-branches concurrently. If the post-lead agents are absent, the main thread still
-orchestrates the same branches from the compact context with MCP tools/assets.
+generation is the provisional Message Draft Builder: it may start after the
+review batch exists, including while the user is on filter choice, but template
+review cannot start until the user answers filter choice and chooses Use
+Template in Messages. AI Generated is an explicit opt-out that cancels or
+ignores the background template draft. If the post-lead agents are absent, the
+main thread still orchestrates the same branches from the compact context with
+MCP tools/assets.
 
 Use rendered Markdown for user review surfaces, not fenced code blocks. Keep
 lines short, use indexed section labels and bullets, and translate internal
@@ -200,7 +206,7 @@ After every `update_campaign({ campaignId, currentStep })`, use
 `get_campaign_navigation_state` when available as a compact orientation check:
 match the saved campaign state to the expected watch-link step, explain the
 current state in one sentence, and only then continue. Sender selection belongs
-at Settings after message approval and 10-row validation. After message
+at Settings after message approval and 15-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
@@ -555,33 +561,38 @@ updates.
    asset loader so they share the same config.
 3. Follow that prompt and workflow config exactly.
 4. For message generation, use the `post-find-leads-message-scout` agent when
-   available; its prompt carries the campaign-launch message rules. In the
-   parent-thread fallback, load
-   `mcp__sellable__get_subskill_asset({ subskillName: "create-campaign-v2", assetPath: "references/message-review-safety-gate.md" })`.
-   Do not load the full long-form `generate-messages` subskill in this
-   create-campaign path; if the safety gate cannot safely approve the draft,
-   route to revise messaging with the concrete failure.
-   This compatibility path is not a generate-message fast mode.
-   Do not synthesize `message-validation.md` from the brief, lead review, or
+   available. The worker and parent-thread fallback must load the full
+   long-form `generate-messages` prompt with
+   `mcp__sellable__get_subskill_prompt({ subskillName: "generate-messages", offset, limit })`
+   until `hasMore=false`. The create-campaign message-review safety gate is a
+   supplemental approval checklist, not a replacement for the long prompt. Use
+   campaign state, campaign brief content, selected source state, and imported
+   review-batch rows as the source of truth; do not read stale local markdown,
+   inspect the database directly, or synthesize `message-validation.md` from
    general knowledge.
 5. Create the campaign shell early with the v1 brief so the user can open the
    watch link and see useful setup state immediately. Import only the first
    bounded review batch after the source is attached to the campaign; do not
-   queue workflow cells, attach a sequence, or start until
-   `message-validation.md` proves the message-review safety-gate workflow ran,
-   `message-review.md` approves the template, rubrics are saved, and the
-   approved message set is synced into the campaign brief.
+   queue workflow cells, attach a sequence, or start until the filter choice is
+   resolved, Messages has shown Use Template / AI Generated, template/token
+   rules are approved when Use Template is chosen, rubrics are saved and the
+   bounded review-batch `enrichCellId` cells have been queued when filters are
+   enabled, and the approved message set is synced into the campaign brief.
+   Product Generate Message cells must not run from the background template
+   path before that template/token approval.
    Do not ask the user to approve the brief before shell creation unless they
    explicitly requested a no-write draft; the shell itself is the review surface.
 6. The main thread owns watch navigation. Call
    `mcp__sellable__update_campaign({ campaignId, currentStep })` before major
    visible work so the user can watch progress in the app: `create-offer` for
    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,
-   `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.
+   `filter-choice` after the 15-row review batch, `messages` for the Use
+   Template / AI Generated mode choice, `auto-execute-messaging` for approved
+   message work or the product's AI-generated path, `awaiting-user-greenlight`
+   for the final handoff, `settings` for sender selection, `sequence` after
+   sender attach, and `send` once the recommended sequence is attached.
+   `validate-sample` is recovery/legacy only if reached. 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.