@sellable/mcp 0.1.136 → 0.1.137

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

@@ -1,7 +1,7 @@
 You are Lead Fit 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.
+Your job starts only after the lead source has been approved or auto-confirmed
+and the bounded review batch exists in the campaign table.
 Work only on the lead filter branch. Do not source new leads, draft messages,
 import leads, create campaigns, or ask the user questions. Your only live
 campaign mutation is calling `save_rubrics` after the production rubrics are
@@ -9,41 +9,38 @@ ready.
 
 Required inputs:
 
-- `brief.md`
-- `lead-review.md`
-- `lead-sample.json`
-- campaign state from the parent thread
-- campaign table sample from the parent thread
+- `campaignId`
+- campaign revision or `campaignUpdatedAt`
+- campaign brief content
+- selected source decision and provider/list state
+- `selectedLeadListId`
+- `workflowTableId`
+- imported review-batch rows, including row ids/hash when available
+- filter choice
 
 Required first steps:
 
-1. Read the three required inputs.
-2. Load the filter-leads reference before writing artifacts:
+1. Verify the campaign/source/table ids from the parent thread match the live
+   campaign context.
+2. Load the filter-leads reference before designing rubrics:
    `get_subskill_asset({ subskillName: "create-campaign-v2", assetPath: "references/filter-leads.md" })`.
 3. Treat campaign state and the campaign table sample as the input of record.
-   Disk files are context/debug aids, not durable state.
+   Do not require or hunt for local markdown/json artifacts.
 
 Owned outputs:
 
 - Durable campaign rubrics via `save_rubrics({ campaignOfferId, leadScoringRubrics })`
   when the filter is confirmed and production-shaped rubrics are safe to write.
   `save_rubrics` is the durable writer.
-- `lead-filter.md` debug artifact after the durable campaign write
-- `rubric.json` debug artifact after the durable campaign write
+- concise filter/rubric summary returned to the parent thread
 
-Do not write or modify:
-
-- `message-validation.md`
-- `message-review.md`
-- `approval-packet.md`
-- `brief.md`
-- `lead-review.md`
-- `lead-sample.json`
+Do not write or modify local markdown/json artifacts. Durable output is only
+via `save_rubrics` plus the parent-thread summary.
 
 Process:
 
-1. Preserve the approved source decision and the sample math from
-   `lead-review.md`; do not re-run sourcing.
+1. Preserve the approved source decision and review-batch sample math supplied
+   by the parent; do not re-run sourcing.
 2. Turn the sample's good-fit and false-positive patterns into a strict but
    campaign-native filter.
 3. Include keep rules, exclude rules, sample false positives, pass-rate /
@@ -56,14 +53,11 @@ Process:
 6. If status is `confirmed`, call `save_rubrics` with 2-5 production-shaped
    active `leadScoringRubrics` before reporting success. If `save_rubrics`
    fails, stop and report the blocker; do not claim the filter is persisted.
-7. Write `lead-filter.md` and `rubric.json` only as debug artifacts after
-   campaign persistence succeeds.
 
 Return a concise final status with:
 
 - filter status: `confirmed`, `confirm-with-user`, or `revise-find-leads`
 - whether `save_rubrics` succeeded and how many active rubrics were persisted
-- artifacts written
 - strongest keep rules
 - strongest exclusion rules
 - expected pass-rate / yield impact

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

@@ -80,6 +80,27 @@ When reporting branch runtime proof, use this shape under
 Do not tell the UI to show Message Draft Builder as running unless this proof
 exists and points at the current non-empty bounded review batch.
 
+## Basis Changes And Rewrites
+
+The first completed recommendation is the default message review candidate.
+Do not automatically retry or regenerate only because Lead Fit Builder finished,
+rubrics were saved, Filter Leads completed, enrichment cells populated, or more
+row data became available after this branch started.
+
+Treat later filter/enrichment data as optional rewrite context. If campaign id,
+brief hash, selected source, `selectedLeadListId`, `workflowTableId`, and
+review-batch row ids/hash still match, keep the initial recommendation usable
+and report `status: ready` with `basisStatus: "usable_initial"` or
+`"enriched_rewrite_available"`. The parent thread may offer the user a choice
+to keep the initial draft or rewrite with enriched/filter data, but the rewrite
+must be explicit user opt-in.
+
+Retry or regenerate without asking only when the initial recommendation is
+missing, failed, structurally invalid, unsafe, or mismatched on campaign id,
+brief hash, selected source, `selectedLeadListId`, `workflowTableId`, or
+review-batch rows. Filter/rubric/enrichment basis drift alone is not a stale
+blocker.
+
 ## Hard Rules
 
 - Do not call product Generate Message cells. This worker drafts the template

package/agents/registry.json

@@ -158,22 +158,20 @@
       "displayName": "Lead Fit Builder",
       "target": "filter-leads",
       "inputs": [
-        "brief.md",
-        "lead-review.md",
-        "lead-sample.json"
-      ],
-      "producesArtifacts": [
-        "lead-filter.md"
-      ],
-      "optionalProducesArtifacts": [
-        "rubric.json"
+        "campaignId",
+        "campaignBrief",
+        "source decision and selectedLeadList/source state",
+        "workflowTableId",
+        "imported review-batch rows"
       ],
+      "producesArtifacts": [],
+      "optionalProducesArtifacts": [],
       "ownership": "lead quality, false-positive patterns, keep/exclude rules, ability-to-pay checks, and production rubric translation only",
       "codex": {
         "description": "Lead Fit Builder for campaign-backed lead filtering and rubric persistence after source approval.",
         "model": "gpt-5.5",
         "modelReasoningEffort": "high",
-        "sandboxMode": "workspace-write",
+        "sandboxMode": "read-only",
         "nicknameCandidates": [
           "Lead Fit Builder",
           "Fit Builder",
@@ -181,17 +179,12 @@
         ]
       },
       "claude": {
-        "description": "Use proactively as Lead Fit Builder after lead source approval to persist campaign rubrics and write lead-filter debug artifacts from campaign state.",
+        "description": "Use proactively as Lead Fit Builder after lead source approval to persist campaign rubrics from campaign state.",
         "model": "inherit",
         "background": true,
         "maxTurns": 8,
         "color": "yellow",
         "tools": [
-          "Read",
-          "Write",
-          "Edit",
-          "Grep",
-          "Glob",
           "mcp__sellable__get_subskill_prompt",
           "mcp__sellable__get_subskill_asset",
           "mcp__sellable__save_rubrics"

package/agents/source-scout-linkedin-engagement.md

@@ -9,8 +9,8 @@ Required first step:
 "signal-discovery", campaignOfferId, confirmed: true })` and include that same
   `campaignOfferId` plus `currentStep: "signal-discovery"` in `search_signals`
   so the owning search route can show the source lane with current find-leads
-  narration and user options. Treat that as a campaign-attached persisted
-  search; do not run a post-mint search without the campaign ID. If no campaign
+  narration and user options. Treat that as a campaign-attached persisted search;
+  do not run a post-mint search without the campaign ID. If no campaign
   ID is supplied, run campaignless preview mode.
 
 Use the inherited Sellable MCP tools when available:

package/dist/tools/bootstrap.js

@@ -270,7 +270,7 @@ export async function bootstrapCreateCampaign(input = {}) {
         ? resumeDetected
             ? `Bootstrap complete.${workspaceNotice} Resume from campaign state and navigation diagnostics first; treat local draft artifacts as debug-only evidence. Then load ${createCampaignSubskill?.name ?? "create-campaign"} instructions with get_subskill_prompt({ subskillName: "${createCampaignSubskill?.name ?? "create-campaign"}" }); if the response has hasMore=true, continue with nextOffset until hasMore=false.`
             : flowVersion === "v2"
-                ? `Bootstrap complete.${workspaceNotice} Load create-campaign-v2 instructions with get_subskill_prompt({ subskillName: "create-campaign-v2" }); if the response has hasMore=true, continue with nextOffset until hasMore=false. Preserve the pre-intake sequence: confirm auth/workspace status, identity setup, sender discovery/listing, and lightweight profile/company lookup. Then run the short setup/intake, write the campaign brief, call create_campaign once to mint the watchable shell, surface the returned watch link, and hand off to lead finding.`
+                ? `Bootstrap complete.${workspaceNotice} Load the compact create-campaign-v2 entry prompt once with get_subskill_prompt({ subskillName: "create-campaign-v2" }); load flow/reference assets lazily only when that stage needs them. Preserve the pre-intake sequence: confirm auth/workspace status, resolve campaign identity, and run lightweight profile/company lookup. Do not call list_senders or sender discovery during setup; sender availability belongs only to Settings after message approval. Then run the short setup/intake, write the campaign brief, call create_campaign once to mint the watchable shell, surface the returned watch link, and hand off to lead finding.`
                 : `Bootstrap complete.${workspaceNotice} Load ${createCampaignSubskill?.name ?? "create-campaign"} instructions with get_subskill_prompt({ subskillName: "${createCampaignSubskill?.name ?? "create-campaign"}" }); if the response has hasMore=true, continue with nextOffset until hasMore=false. Follow that flow before calling create_campaign.`
         : "Bootstrap incomplete. Resolve blockingErrors and rerun bootstrap_create_campaign before provider/search/import tools.";
     // Strip prompt body from createCampaignSubskill — it's loaded via the host

package/dist/tools/navigation.js

@@ -243,6 +243,9 @@ function checkMessages(campaign) {
     if (!hasApprovedMessageTemplate(campaign)) {
         missing.push("approvedMessageTemplate");
     }
+    if (campaign.currentStep === "auto-execute-messaging") {
+        missing.push("generatedMessageReview");
+    }
     return { stepId: "messages", missing };
 }
 function checkSettings(campaign) {

package/dist/tools/prompts.d.ts

@@ -99,9 +99,7 @@ export interface SourceScoutRegistryResponse {
 export interface PostFindLeadsScoutRegistryResponse {
     version: number;
     trigger: "find_leads_source_approved";
-    requiredArtifacts?: string[];
     requiredInputs?: string[];
-    optionalDebugArtifacts?: string[];
     scouts: Array<{
         id: string;
         name: string;
@@ -125,11 +123,9 @@ export interface PostFindLeadsScoutRegistryResponse {
     }>;
     joinGate: {
         afterAllComplete: boolean;
-        requiredArtifacts?: string[];
         requiredState?: string[];
         noFilterRequiredState?: string[];
         skipFilterRule?: string;
-        optionalDebugArtifacts?: string[];
         show: string[];
         nextStage: string;
     };
@@ -140,6 +136,7 @@ export interface PostFindLeadsScoutRegistryResponse {
         runtimeProofRequiredFields: string[];
         basisFields: string[];
         compactOutputFields: string[];
+        reusePolicy?: string;
     };
     usage: {
         codex: string;

package/dist/tools/prompts.js

@@ -263,7 +263,6 @@ export function getPostFindLeadsScoutRegistry() {
             "imported review-batch rows from selectedLeadList with row ids/hash",
             "filter choice and filter/rubric basis when present",
         ],
-        optionalDebugArtifacts: ["brief.md", "lead-review.md", "lead-sample.json"],
         scouts: scouts.map((agent) => ({
             id: String(agent.id || ""),
             name: String(agent.name || ""),
@@ -294,7 +293,6 @@ export function getPostFindLeadsScoutRegistry() {
             requiredState: ["leadScoringRubrics", "messageDraftRecommendation"],
             noFilterRequiredState: ["messageDraftRecommendation"],
             skipFilterRule: "leadScoringRubrics may be absent only when the user explicitly skips filters with enableICPFilters=false; messageDraftRecommendation is still required before template review.",
-            optionalDebugArtifacts: ["lead-filter.md", "message-validation.md"],
             show: ["readable_filters_with_reasons", "sample_message_for_approval"],
             nextStage: "message-review",
         },
@@ -332,16 +330,18 @@ export function getPostFindLeadsScoutRegistry() {
                 "renderedSample",
                 "concerns",
                 "status",
+                "basisStatus",
                 "basisToken",
                 "outputAt",
                 "outputHash",
                 "error or retry detail",
             ],
+            reusePolicy: "The first completed Message Draft Builder recommendation remains the default review candidate. Later Lead Fit Builder, Filter Leads, enrichment, or rubric completion may make an enriched rewrite available, but does not automatically retry or replace the initial draft unless campaign/brief/source/list/table/review-batch identity mismatches or the initial output failed.",
         },
         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 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, must read live campaign/review-batch state through scoped MCP/product tools, must reject mismatched selectedLeadListId/workflowTableId/campaign/workspace input, and may use the create-campaign-v2 message-review safety gate as a supplemental approval check. 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. Local markdown/json files are not normal-path inputs. The message branch must load the full generate-messages prompt, must read live campaign/review-batch state through scoped MCP/product tools, must reject mismatched selectedLeadListId/workflowTableId/campaign/workspace input, and may use the create-campaign-v2 message-review safety gate as a supplemental approval check. Join before message review. Do not automatically rerun Message Draft Builder after filters/enrichment finish; show the initial draft by default and offer an enriched rewrite only with explicit user opt-in.",
         },
     };
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.136",
+  "version": "0.1.137",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",