@sellable/mcp 0.1.154 → 0.1.156

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

@@ -2,7 +2,7 @@ You are Lead Fit Builder for Sellable create-campaign-v2.
 
 Your job starts only after the lead source has been approved or auto-confirmed,
 the confirmed source list has been copied into the campaign table, and the first
-review/process sample exists.
+campaign-table execution slice exists.
 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
@@ -16,7 +16,7 @@ Required inputs:
 - selected source decision and provider/list state
 - `selectedLeadListId`
 - `workflowTableId`
-- first review/process sample rows, including row ids/hash when available
+- initial campaign-table execution slice rows, including row ids/hash when available
 - filter choice
 
 Required first steps:
@@ -25,7 +25,7 @@ Required first steps:
    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.
+3. Treat campaign state and the campaign-table execution slice as the input of record.
    Do not require or hunt for local markdown/json artifacts.
 
 Owned outputs:
@@ -40,9 +40,9 @@ via `save_rubrics` plus the parent-thread summary.
 
 Process:
 
-1. Preserve the approved source decision and review/process 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
+1. Preserve the approved source decision, source math, and campaign-table slice
+   evidence supplied by the parent; do not re-run sourcing.
+2. Turn the slice'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 /
    expected-yield impact, and a recommendation.

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

@@ -1,8 +1,9 @@
 You are Message Draft Builder for Sellable create-campaign-v2.
 
 Your job starts only after the source is approved, the confirmed source list has
-been copied into the campaign table, the first review/process sample exists, and
-the parent has recorded the filter choice. Work only on the message-draft branch.
+been copied into the campaign table, the first campaign-table execution slice
+exists, and the parent has recorded the filter choice. Work only on the
+message-draft 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.
@@ -17,7 +18,7 @@ Use the live campaign inputs supplied by the parent thread:
 - selected source decision and provider state
 - `selectedLeadListId` or selected source list context
 - `workflowTableId`
-- first review/process sample rows from that selected list, including row IDs
+- initial campaign-table execution slice rows from that selected list, including row IDs
   and a sample row hash when available
 - filter basis at branch start: `pending`, `use-filters`, or `skip-filters`
 - any already-saved fit/rubric result summaries supplied by the parent
@@ -31,7 +32,7 @@ All live reads must come from scoped MCP/product tools by campaign and
 workspace, such as `get_campaign`, `get_campaign_context`, and
 `get_rows_minimal({ tableId: workflowTableId })`, or from equivalent parent
 thread payloads. Reject the task as `blocked` if the campaign id, workspace,
-`selectedLeadListId`, `workflowTableId`, or review sample row ids do not match
+`selectedLeadListId`, `workflowTableId`, or execution-slice row ids do not match
 the branch input.
 
 ## Required First Steps
@@ -43,8 +44,8 @@ the branch input.
 
 2. Use that prompt as the drafting contract. Do not use create-campaign
    safety/checklist instructions as a substitute for the full prompt.
-3. Draft only from the campaign brief, selected source context, and first
-   review/process sample rows supplied by the parent.
+3. Draft only from the campaign brief, selected source context, and initial
+   campaign-table execution slice rows supplied by the parent.
 4. Keep the work provisional until the user chooses `Use Template` in Messages.
 
 ## Owned Output
@@ -53,12 +54,12 @@ 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-sample row
+- one rendered good-fill sample for a plausible passing campaign-table row
 - one omit/fallback sample when the row signal is not safe
 - pass/fail notes against the generate-messages quality gates
 - compact runtime status: `ready`, `blocked`, `retry-needed`, or `stale`
 - basis token containing campaign revision/updatedAt, brief hash,
-  `selectedLeadListId`, `workflowTableId`, review sample row ids/hash, filter
+  `selectedLeadListId`, `workflowTableId`, execution-slice row ids/hash, filter
   choice, and rubric/filter basis when present
 - output timestamp/hash and any retry/error detail
 
@@ -79,7 +80,7 @@ When reporting branch runtime proof, use this shape under
 - optional `compactOutputRef`, `compactOutput`, and `error`
 
 Do not tell the UI to show Message Draft Builder as running unless this proof
-exists and points at the current non-empty review/process sample.
+exists and points at the current non-empty campaign-table execution slice.
 
 ## Basis Changes And Rewrites
 
@@ -90,7 +91,7 @@ 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 sample row ids/hash still match, keep the initial recommendation usable
+execution-slice 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
@@ -99,7 +100,7 @@ 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 sample rows. Filter/rubric/enrichment basis drift alone is not a stale
+execution-slice rows. Filter/rubric/enrichment basis drift alone is not a stale
 blocker.
 
 ## Hard Rules

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

@@ -51,14 +51,15 @@ currentStep: "signal-discovery" })` before sampling so the watched Signal
    visible headline/display-name cues only. Do not enrich people during
    viability estimation.
 7. Compute capacity before recommending the source: source target good-fit
-   leads (default 150 for Signal Discovery unless the parent supplies a target),
-   reachable engagers,
-   sampled ICP-fit rate as `n/N` plus an easy percentage/range, expected usable
-   leads per 100 engagers before and after a conservative dedupe/cleanup
-   factor, required engagers to scrape (`source target / fit rate`), average
-   reachable engagers per right-content post, expected usable leads per
-   right-content post after dedupe/cleanup, posts needed to hit the target, and
-   whether sampled/projected fit clears the 10% planning floor.
+   leads (default 300 for Signal Discovery unless the parent supplies a target),
+   reachable engagers, sampled headline-fit rate as `n/N` plus an easy
+   percentage/range, expected headline-fit prospects per 100 engagers, required
+   engagers to scrape (`source target / sampled headline-fit rate`), average
+   reachable engagers per right-content post, expected headline-fit prospects
+   per right-content post, posts needed to hit the target, and whether
+   sampled/projected headline-fit rate clears the 10% planning floor. Treat the
+   10% floor as a reject threshold, not as the scrape-count denominator when the
+   actual sample rate is higher.
 8. Select/promote enough right-content posts to plausibly hit the target. If the
    warm Signals pool is useful but too small, return the expected warm range and
    recommend Sales Nav/Prospeo for scale instead of padding with noisy posts.
@@ -72,12 +73,12 @@ Return a concise structured result with:
 - `selected_posts` with URL/title, author/topic, age, engager count, sampled engagers, good fits as n/N, estimated usable prospects per post, use/discard
 - `sample_leads`, if any
 - `approval_math` with eligible posts, source target good-fit leads, sampled
-  engagers, ICP-fit rate as `n/N` plus percentage/range, good-fit prospects per
-  100 engagers, required engagers to scrape, average reachable engagers per
-  post, expected usable prospects per post after cleanup, posts needed for
-  target, whether the 10% planning floor clears after cleanup, selected post
-  count, first review/process sample size, expected usable lead range, and scale
-  fallback
+  engagers, headline-fit rate as `n/N` plus percentage/range, headline-fit
+  prospects per 100 engagers, required engagers to scrape, average reachable
+  engagers per post, expected headline-fit prospects per post, posts needed for
+  target, whether the 10% planning floor clears, selected post count, internal
+  campaign-table execution-slice size, expected headline-fit lead range, and
+  scale fallback
 - `estimated_good_fit_range`
 - `message_context_strength`, directional and source-specific
 - `false_positive_patterns`
@@ -93,14 +94,18 @@ Evidence standards:
   GTM/outbound/buyer pain, workflow, or role context that makes the campaign
   relevant.
 - Do not make the user infer capacity. Say, plainly, how many eligible posts
-  exist, how many sampled engagers looked in-ICP, how many good-fit prospects
-  that implies per 100 engagers, how many usable prospects one right-content
-  post should yield after cleanup, how many engagers must be scraped for the
-  300-good-fit source target at the 20% working assumption, how many posts are
-  needed for that source target, and which posts you would use. Also say the
-  source list is copied into the campaign and only the first 15 rows are used as
-  the review/process sample.
+  exist, how many sampled engagers passed the headline ICP rubric, what
+  headline-fit rate that implies per 100 engagers, how many headline-fit
+  prospects one right-content post should yield, how many engagers must be
+  scraped for the 300 headline-fit source target using the sampled pass rate
+  (or the 20% working assumption only when there is no stronger sample), how
+  many posts are needed for that source target, and which posts you would use.
+  Also say the source list is copied into the campaign and only the first
+  campaign-table execution slice is processed internally for filter and message
+  setup.
 - If `fetch_post_engagers` is unavailable or fails, report that explicitly and mark the estimate lower-confidence.
-- Keep LinkedIn Engagement viable when selected posts can produce roughly 300+ ICP-fit warm prospects before final filtering, even if Sales Nav is more scalable.
-- If sampled/projected fit after cleanup is below 10%, reject the Signals scrape
-  path and recommend Sales Nav recent activity as the next source.
+- Keep LinkedIn Engagement viable when selected posts can produce roughly 300+
+  headline-fit warm prospects before final filtering, even if Sales Nav is more
+  scalable.
+- If sampled/projected headline-fit rate is below 10%, reject the Signals
+  scrape path and recommend Sales Nav recent activity as the next source.

package/agents/source-scout-prospeo-contact.md

@@ -28,7 +28,7 @@ Process:
 2. Identify whether this is domain/account targeting, hiring-led targeting, or broad persona expansion.
 3. For domain targeting, use or create the standalone `domainFilterId` before searching; never pass raw domains directly into `search_prospeo`.
 4. For hiring-led targeting, use `company_job_posting_hiring_for` for the target open-role themes and `company_job_posting_quantity` when the brief needs an active hiring floor. Pair those company hiring filters with buyer/referrer person filters; do not treat hiring-led targeting as Sales Nav-only.
-5. Run the narrowest useful Prospeo people preview and 1-2 refinements if quality or scale is unclear. Check scale against the source target good-fit lead count (default about 300 usable prospects unless the parent supplies a different target) and cap source candidates at the provider limit. Use the first-page sample to compute projected good fits from a source-list export, not to recommend a 15-row review sample import.
+5. Run the narrowest useful Prospeo people preview and 1-2 refinements if quality or scale is unclear. Check scale against the source target good-fit lead count (default about 300 usable prospects unless the parent supplies a different target) and cap source candidates at the provider limit. Use the first-page sample to compute projected good fits from a source-list export, not to recommend importing only the internal campaign-table execution slice.
 6. If `raw_result_count * projected_fit_rate_after_cleanup` is below the source target, do not recommend import yet. Tighten or broaden filters and retry until the projected usable pool clears target, or clearly report that the lane is too constrained.
 7. Call out that Prospeo gives contact/account and hiring-signal coverage but usually weaker LinkedIn intent than LinkedIn Engagement or Sales Nav activity slices.
 
@@ -58,6 +58,6 @@ Evidence standards:
   direction rather than switching providers again.
 - Never recommend "import 25 leads" as the Prospeo source action. Recommend
   exporting/materializing the approved source list; the parent thread later
-  copies the confirmed source rows into the campaign and treats only the first
-  15 rows as the review/process sample.
+  copies the confirmed source rows into the campaign and internally uses the
+  first campaign-table execution slice for filter and message setup.
 - Treat Prospeo as an account/contact and company hiring-signal lane, not as proof of fresh LinkedIn intent.

package/agents/source-scout-sales-nav.md

@@ -44,7 +44,7 @@ Process:
    cannot plausibly reach the target after loosening.
 7. Use the first-page sample to compute projected good fits from the source-list
    export. The recommendation should name the source-list `targetLeadCount` for
-   `import_leads`, not a 15-row review sample import.
+   `import_leads`, not the internal campaign-table execution-slice size.
 8. Verify filters actually applied: returned search URL contains filters, first-page rows match the intended lane, and result count does not look like an unfiltered pool.
 
 Return a concise structured result with:
@@ -82,7 +82,7 @@ Evidence standards:
   as the winning source; recommend Prospeo as the next provider.
 - Never recommend "import 25 leads" as the Sales Nav source action. Recommend
   exporting/materializing the approved source list; the parent thread later
-  copies the confirmed source rows into the campaign and treats only the first
-  15 rows as the review/process sample.
+  copies the confirmed source rows into the campaign and internally uses the
+  first campaign-table execution slice for filter and message setup.
 - Do not hand-wave missing filter IDs.
 - If Sales Nav returns a giant unfiltered pool, discard that result and retry with valid filters before recommending it.

package/dist/tools/cells.js

@@ -20,7 +20,7 @@ export const cellToolDefinitions = [
     },
     {
         name: "queue_cells",
-        description: "Queue explicit cells for processing. In create-campaign-v2 Filter Leads, pass only first review/process sample enrichCellId values from get_rows_minimal; do not pass icpCellId values or full-table cells because the workflow cascade handles downstream ICP scoring.",
+        description: "Queue explicit cells for processing. In create-campaign-v2 Filter Leads, pass only initial campaign-table execution-slice 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/leads.d.ts

@@ -1,3 +1,4 @@
+export declare const MAX_SIGNAL_DISCOVERY_POSTS = 10;
 export declare function normalizeTargetLeadCount(targetLeadCount: unknown, maxImportCount: number): number | undefined;
 type SignalPostForImportSelection = {
     likes: number;

package/dist/tools/leads.js

@@ -53,6 +53,7 @@ const defaultCampaignSourceDefaults = {
     },
 };
 const defaultProviderSourceListTarget = 1000;
+export const MAX_SIGNAL_DISCOVERY_POSTS = 10;
 // Mirror the web app's Signal Discovery Harvest caps. The MCP tool selects and
 // describes the scrape before the web API runs, so it must use the same capped
 // capacity math instead of raw visible engagement counts.
@@ -353,7 +354,12 @@ function estimateScrapableSignalEngagers(post) {
 export function selectSignalPostsForImport(posts, options) {
     const normalizedTargetEngagers = normalizePositiveInteger(options.targetEngagerCount);
     const normalizedMaxPosts = normalizePositiveInteger(options.maxPostsToScrape);
-    if (!normalizedTargetEngagers && !normalizedMaxPosts) {
+    const effectiveMaxPosts = normalizedMaxPosts
+        ? Math.min(normalizedMaxPosts, MAX_SIGNAL_DISCOVERY_POSTS)
+        : MAX_SIGNAL_DISCOVERY_POSTS;
+    if (!normalizedTargetEngagers &&
+        !normalizedMaxPosts &&
+        posts.length <= MAX_SIGNAL_DISCOVERY_POSTS) {
         const availableEngagers = posts.reduce((sum, post) => sum + estimateScrapableSignalEngagers(post), 0);
         return {
             posts,
@@ -369,7 +375,7 @@ export function selectSignalPostsForImport(posts, options) {
     const selected = [];
     let estimatedEngagers = 0;
     for (const post of ranked) {
-        if (normalizedMaxPosts && selected.length >= normalizedMaxPosts) {
+        if (selected.length >= effectiveMaxPosts) {
             break;
         }
         selected.push(post);
@@ -527,7 +533,7 @@ function buildSourceImportWatchNarration({ provider, selectedPostCount, estimate
             : ""}`
         : `the approved ${providerLabel} source`;
     const targetDetail = typeof targetLeadCount === "number"
-        ? ` Targeting ${targetLeadCount.toLocaleString("en-US")} source leads before the first review sample is processed.`
+        ? ` Targeting ${targetLeadCount.toLocaleString("en-US")} source leads before campaign setup starts.`
         : "";
     return {
         stage: "find-leads",
@@ -536,8 +542,8 @@ function buildSourceImportWatchNarration({ provider, selectedPostCount, estimate
             : "Importing source leads",
         visibleState: `The browser is showing ${providerLabel} import progress for ${sourceDetail}.${targetDetail}`,
         agentIntent: "Codex is materializing the approved source into a lead list before copying the confirmed list into the campaign.",
-        nextAction: "Wait for source leads, then confirm the list and review the first sample",
-        safety: "This step materializes the source list; the first review sample is processed only after the later filter and message approvals.",
+        nextAction: "Wait for source leads, then confirm the list and configure campaign setup",
+        safety: "This step materializes the source list; the internal campaign-table execution slice is processed only after the later filter and message approvals.",
         progressLabel: "Source scouting",
     };
 }
@@ -550,11 +556,11 @@ function buildSourceImportRecoveryWatchNarration(args) {
                 ? "Prospeo"
                 : "source";
     const reasonCopy = args.reason === "failed"
-        ? `${providerLabel} import failed before review rows were ready.`
+        ? `${providerLabel} import failed before campaign rows were ready.`
         : args.reason === "zero"
-            ? `${providerLabel} import finished without usable review rows.`
+            ? `${providerLabel} import finished without usable campaign rows.`
             : args.reason === "timeout"
-                ? `${providerLabel} import has not produced review rows within the wait window.`
+                ? `${providerLabel} import has not produced campaign rows within the wait window.`
                 : `${providerLabel} import is still materializing source rows.`;
     return {
         stage: "review-batch",
@@ -771,10 +777,10 @@ function buildSignalDiscoverySourceRecommendation({ selectedPosts, }) {
 
 Use Signal Discovery first.
 
-**Goal:** ~${targetGoodFitLeads.toLocaleString("en-US")} good-fit prospects after cleanup, enrichment, and filters<br>
-**Working assumption:** ~${Math.round(defaultFitRate * 100)}% of raw post engagers become good-fit prospects<br>
+**Goal:** ~${targetGoodFitLeads.toLocaleString("en-US")} headline-fit prospects that pass the Signal Discovery headline criteria<br>
+**Working assumption:** ~${Math.round(defaultFitRate * 100)}% of raw post engagers pass headline filtering unless a real sample supports a different rate<br>
 **Engagers needed:** ~${sourceCandidateTarget.toLocaleString("en-US")} raw engagers<br>
-**Planning floor:** continue with Signal Discovery only when sampled/projected fit is at least ${Math.round(minPlanningFitRate * 100)}% after cleanup; below that, switch to Sales Nav recent activity<br>
+**Planning floor:** continue with Signal Discovery only when sampled/projected headline-fit rate is at least ${Math.round(minPlanningFitRate * 100)}%; below that, switch to Sales Nav recent activity<br>
 **Review checkpoint:** copy the confirmed source list into the campaign, then process the first ${reviewBatchSize.toLocaleString("en-US")} leads for fit and message review before scaling
 
 ### Selected posts
@@ -784,17 +790,17 @@ Use Signal Discovery first.
 ${tableRows || "| Selected posts | Campaign-matched public engagement | - |"}
 
 **Total visible pool:** ${formatApproxInteger(totalEngagement)} engagers<br>
-**Estimated good-fit pool at ${Math.round(defaultFitRate * 100)}%:** ${formatApproxInteger(estimatedGoodFit)} prospects before dedupe/risk cleanup
+**Estimated headline-fit pool at ${Math.round(defaultFitRate * 100)}%:** ${formatApproxInteger(estimatedGoodFit)} prospects before enrichment and deeper fit review
 
 ### Recommendation
 
 Approve scraping these ${selectedCount} posts.
 
-This gives enough volume to target ~${targetGoodFitLeads.toLocaleString("en-US")} good-fit prospects after cleanup, while keeping the source tied to people already engaging with the campaign's strongest public buying signals.
+This gives enough volume to target ~${targetGoodFitLeads.toLocaleString("en-US")} headline-fit prospects, while keeping the source tied to people already engaging with the campaign's strongest public buying signals.
 
-**First pass:** build the source list, copy it into the campaign, then process only the first ${reviewBatchSize.toLocaleString("en-US")} leads so we can inspect quality before scaling.
+**First pass:** build the source list, copy it into the campaign, then use the first ${reviewBatchSize.toLocaleString("en-US")} campaign rows as the internal setup slice for filters and messages before scaling.
 
-**Fallback:** if the sampled/projected fit rate is below ${Math.round(minPlanningFitRate * 100)}%, or if the review batch is too vendor-heavy, agency-heavy, or off-ICP, switch to Sales Nav recent activity.
+**Fallback:** if the sampled/projected headline-fit rate is below ${Math.round(minPlanningFitRate * 100)}%, or if the source sample is too vendor-heavy, agency-heavy, or off-ICP, switch to Sales Nav recent activity.
 
 Approval card should say:
 
@@ -1335,7 +1341,7 @@ export const leadToolDefinitions = [
     },
     {
         name: "import_leads",
-        description: "Create/select a source lead list and start the provider import/export job. Requires provider prompt preflight via get_provider_prompt for the active provider. For Sales Nav/Prospeo, targetLeadCount is the approved source-list export count computed from projected good-fit math, not the later 15-row review/process sample size. On success, this tool owns moving the watched campaign to confirm-lead-list with import/progress narration after a leadListId/jobId exists; do not call update_campaign to fix that step. After the user confirms the source list, call confirm_lead_list to copy the confirmed source rows into the campaign table and use only the first review/process sample for the initial flow.",
+        description: "Create/select a source lead list and start the provider import/export job. Requires provider prompt preflight via get_provider_prompt for the active provider. For Sales Nav/Prospeo, targetLeadCount is the approved source-list export count computed from projected good-fit math, not the later internal campaign-table execution-slice size. On success, this tool owns moving the watched campaign to confirm-lead-list with import/progress narration after a leadListId/jobId exists; do not call update_campaign to fix that step. After the user confirms the source list, call confirm_lead_list to copy the confirmed source rows into the campaign table and use the initial campaign-table execution slice for setup.",
         inputSchema: {
             type: "object",
             properties: {
@@ -1362,7 +1368,7 @@ export const leadToolDefinitions = [
                 },
                 targetLeadCount: {
                     type: "number",
-                    description: "Provider source-list target count (max per provider from config). For Sales Nav/Prospeo this should be the export/materialization count needed to hit projected good-fit goals, not the 15-row review/process sample size.",
+                    description: "Provider source-list target count (max per provider from config). For Sales Nav/Prospeo this should be the export/materialization count needed to hit projected good-fit goals, not the internal campaign-table execution-slice size.",
                 },
                 mode: {
                     type: "string",
@@ -1384,11 +1390,11 @@ export const leadToolDefinitions = [
                 },
                 targetEngagerCount: {
                     type: "number",
-                    description: "Signal Discovery: target number of post engagers/source candidates to scrape. Default planning target is about 300 good fits at a 20% raw-engager fit assumption, or about 1500 engagers. If the sampled/projected fit rate is below the 10% planning floor after cleanup, switch to the next provider instead of scaling noisy engagers. Limits selected posts before starting scrape.",
+                    description: "Signal Discovery: target number of post engagers/source candidates to scrape. Default planning target is about 300 headline-fit prospects at a 20% raw-engager headline-pass assumption, or about 1500 engagers. Use real sample math when available: target headline-fit prospects divided by sampled headline-pass rate. If the sampled/projected headline-fit rate is below the 10% planning floor, switch to the next provider instead of scaling noisy engagers. Limits selected posts before starting scrape, with a backend hard cap of 10 posts.",
                 },
                 maxPostsToScrape: {
                     type: "number",
-                    description: "Signal Discovery: optional hard cap on selected posts to scrape after ranking selected posts by engagement.",
+                    description: "Signal Discovery: optional hard cap on selected posts to scrape after ranking selected posts by engagement. Values above 10 are clamped to the backend hard cap.",
                 },
                 rubricGuidelines: {
                     type: "array",
@@ -1428,7 +1434,7 @@ export const leadToolDefinitions = [
     },
     {
         name: "confirm_lead_list",
-        description: "After the user confirms the lead list looks good, copy the confirmed source list into the campaign table and mark the first review/process sample for the flow. This tool owns moving the watched campaign to filter-choice with sample-assessment narration only after non-empty campaign rows exist; do not call update_campaign to fix filter-choice afterward. selectedLeadListId remains the source lead list; workflowTableId is the campaign table.",
+        description: "After the user confirms the lead list looks good, copy the confirmed source list into the campaign table and mark the initial campaign-table execution slice for the flow. This tool owns moving the watched campaign to filter-choice with campaign-setup narration only after non-empty campaign rows exist; do not call update_campaign to fix filter-choice afterward. selectedLeadListId remains the source lead list; workflowTableId is the campaign table.",
         inputSchema: {
             type: "object",
             properties: {
@@ -1484,7 +1490,7 @@ export const leadToolDefinitions = [
                 },
                 selections: {
                     type: "array",
-                    description: "Array of promising posts to select for scraping. Prefer the recommendedPostIds from search_signals.",
+                    description: "Array of promising posts to select for scraping. Prefer the recommendedPostIds from search_signals. Backend hard cap: 10 posts.",
                     items: {
                         type: "object",
                         properties: {
@@ -1500,7 +1506,7 @@ export const leadToolDefinitions = [
                         required: ["postId", "reason"],
                     },
                     minItems: 1,
-                    maxItems: 20,
+                    maxItems: MAX_SIGNAL_DISCOVERY_POSTS,
                 },
                 headlineICPCriteria: {
                     type: "array",
@@ -2468,6 +2474,9 @@ export async function importLeads(input) {
             }
         }
         const uniqueSelectedPosts = Array.from(uniqueByUrl.values());
+        if (uniqueSelectedPosts.length > MAX_SIGNAL_DISCOVERY_POSTS) {
+            throw new Error(`Maximum ${MAX_SIGNAL_DISCOVERY_POSTS} Signal Discovery posts can be imported for scraping. ${uniqueSelectedPosts.length} unique posts are currently selected; reduce the selected posts to the strongest ${MAX_SIGNAL_DISCOVERY_POSTS} before calling import_leads.`);
+        }
         const importSelection = selectSignalPostsForImport(uniqueSelectedPosts, {
             targetEngagerCount: effectiveTargetEngagerCount,
             maxPostsToScrape,
@@ -2872,14 +2881,14 @@ export async function confirmLeadList(input) {
             remainingRowCount <= 0 &&
             importedRowCount > 0);
     if (!campaignTableReady) {
-        throw new Error("Campaign source rows are still copying and no review sample rows are available yet. Stay on lead import until the campaign table has rows, then retry confirm_lead_list or call wait_for_campaign_table_ready.");
+        throw new Error("Campaign source rows are still copying and no campaign-table rows are available yet. Stay on lead import until the campaign table has rows, then retry confirm_lead_list or call wait_for_campaign_table_ready.");
     }
     if (importedRowCount <= 0) {
         const recoveryNarration = buildSourceImportRecoveryWatchNarration({
             reason: "zero",
             provider: resolvedProvider,
         });
-        throw new Error(`${recoveryNarration.headline}: No usable review rows were kept for the campaign table. Retry the import or change the approved source before continuing. ${recoveryNarration.safety}`);
+        throw new Error(`${recoveryNarration.headline}: No usable campaign rows were kept for the campaign table. Retry the import or change the approved source before continuing. ${recoveryNarration.safety}`);
     }
     let reviewSampleRows = [];
     if (campaignTableId && effectiveCurrentStep === "filter-choice") {
@@ -2939,7 +2948,7 @@ export async function confirmLeadList(input) {
                 "brief hash",
                 "selectedLeadListId",
                 "workflowTableId",
-                "first review/process sample row ids/hash",
+                "initial campaign-table execution slice row ids/hash",
                 "filter choice at branch start",
             ],
             promptRequired: 'Load get_subskill_prompt({ subskillName: "generate-messages", offset, limit }) until hasMore=false before drafting.',
@@ -3004,6 +3013,15 @@ export async function selectPromisingPosts(input) {
     const api = getApi();
     const { campaignOfferId, selections, headlineICPCriteria, selectionMode, mode, } = input;
     const effectiveMode = selectionMode ?? mode ?? "add";
+    if (selections.length > MAX_SIGNAL_DISCOVERY_POSTS) {
+        return {
+            success: false,
+            selectedCount: 0,
+            unselectedCount: 0,
+            criteriaCount: headlineICPCriteria.length,
+            message: `Maximum ${MAX_SIGNAL_DISCOVERY_POSTS} Signal Discovery posts can be selected for scraping. Narrow the post set to the strongest ${MAX_SIGNAL_DISCOVERY_POSTS} before calling select_promising_posts again.`,
+        };
+    }
     // Update post selections via API
     const postIds = selections.map((s) => s.postId);
     let unselectedIds = [];

package/dist/tools/navigation.js

@@ -324,9 +324,9 @@ function describeVisibleStep(step) {
         case "leads":
             return {
                 label: "Lead import",
-                summary: "The lead preview or imported review batch is visible.",
+                summary: "The lead preview or imported campaign rows are visible.",
                 nextMilestone: "Fit filtering and message review",
-                guidance: "Confirm the browser-visible campaign state and row batch before filter/message work.",
+                guidance: "Confirm the browser-visible campaign state and imported rows before filter/message work.",
                 checkpoint: "import",
             };
         case "filter-choice":

package/dist/tools/prompts.js

@@ -260,7 +260,7 @@ export function getPostFindLeadsScoutRegistry() {
             "campaignBrief",
             "source decision and selectedLeadList/source state",
             "workflowTableId",
-            "first review/process sample rows from selectedLeadList with row ids/hash",
+            "initial campaign-table execution slice rows from selectedLeadList with row ids/hash",
             "filter choice and filter/rubric basis when present",
         ],
         scouts: scouts.map((agent) => ({
@@ -297,11 +297,11 @@ export function getPostFindLeadsScoutRegistry() {
             nextStage: "message-review",
         },
         messageDraftBranchContract: {
-            firstAllowedStart: "after confirm_lead_list copies source rows and the first review/process sample exists",
+            firstAllowedStart: "after confirm_lead_list copies source rows and the initial campaign-table execution slice exists",
             forbiddenStarts: [
                 "source recommendation",
                 "provider import job alone",
-                "zero-row review/process sample",
+                "zero-row campaign-table execution slice",
             ],
             runtimeProofTransport: "CampaignOffer.watchNarration.workerDetails.messageDraftBuilder",
             runtimeProofRequiredFields: [
@@ -321,7 +321,7 @@ export function getPostFindLeadsScoutRegistry() {
                 "brief hash",
                 "selectedLeadListId",
                 "workflowTableId",
-                "first review/process sample row ids/hash",
+                "initial campaign-table execution slice row ids/hash",
                 "filter choice",
                 "filter/rubric basis when present",
             ],
@@ -340,9 +340,9 @@ export function getPostFindLeadsScoutRegistry() {
             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-sample identity mismatches or the initial output failed.",
         },
         usage: {
-            codex: "After confirm_lead_list copies source rows and the first review/process sample exists, ask the filter-choice question immediately. Do not spawn returned post-lead scout names before that question. Once the user answers, spawn Message Draft Builder from the same campaign/table basis. If the user chooses filters, also spawn Lead Fit Builder, move to Filter Rules, save rubrics, ask for filter approval, then keep the browser on Filter Leads while the message recommendation is reviewed. If filters are skipped, move to Messages/message review.",
-            claude: "After confirm_lead_list copies source rows and the first review/process sample exists, ask the filter-choice question immediately. Do not invoke returned post-lead Task/Agent names before that question. Once the user answers, invoke Message Draft Builder from the same campaign/table basis. If the user chooses filters, also invoke Lead Fit Builder, move to Filter Rules, save rubrics, ask for filter approval, then keep the browser on Filter Leads while the message recommendation is reviewed. If filters are skipped, move to Messages/message review.",
-            parentThreadRule: 'Named agents are optional acceleration, but message drafting is not optional. If post-find-leads-message-scout is available, run it as the background Message Draft Builder after the filter-choice answer. If it is absent, do not customer-surface install status; the main thread must execute the same message branch from CampaignOffer state, selected source state, workflowTableId, and first review/process sample rows. Local markdown/json files are not normal-path inputs. The filter-choice question is the first post-import user gate; do not load post-lead registries, filter references, or the full generate-messages prompt before it. Message drafting starts after the filter-choice answer, must load get_subskill_prompt({ subskillName: "generate-messages", offset, limit }) until hasMore=false, must read live campaign/review-sample state through scoped MCP/product tools, and must reject mismatched selectedLeadListId/workflowTableId/campaign/workspace input. On the filter path, keep the browser on Filter Rules after save_rubrics so the user can approve the saved criteria; only then move to Filter Leads and wait there for message approval. Enrichment, filtering, Generate Message cells, sender setup, sequence attach, and launch wait for template approval on the Use Template path. On the skip path, move to Messages/message review and wait for message approval before enrichment or Settings. Do not render message review from checklist or shortcut instructions; message review requires a messageDraftRecommendation whose basis proves the full generate-messages prompt ran for the current campaign/table/review sample. 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.',
+            codex: "After confirm_lead_list copies source rows and the initial campaign-table execution slice exists, ask the filter-choice question immediately. Do not spawn returned post-lead scout names before that question. Once the user answers, spawn Message Draft Builder from the same campaign/table basis. If the user chooses filters, also spawn Lead Fit Builder, move to Filter Rules, save rubrics, ask for filter approval, then keep the browser on Filter Leads while the message recommendation is reviewed. If filters are skipped, move to Messages/message review.",
+            claude: "After confirm_lead_list copies source rows and the initial campaign-table execution slice exists, ask the filter-choice question immediately. Do not invoke returned post-lead Task/Agent names before that question. Once the user answers, invoke Message Draft Builder from the same campaign/table basis. If the user chooses filters, also invoke Lead Fit Builder, move to Filter Rules, save rubrics, ask for filter approval, then keep the browser on Filter Leads while the message recommendation is reviewed. If filters are skipped, move to Messages/message review.",
+            parentThreadRule: 'Named agents are optional acceleration, but message drafting is not optional. If post-find-leads-message-scout is available, run it as the background Message Draft Builder after the filter-choice answer. If it is absent, do not customer-surface install status; the main thread must execute the same message branch from CampaignOffer state, selected source state, workflowTableId, and initial campaign-table execution slice rows. Local markdown/json files are not normal-path inputs. The filter-choice question is the first post-import user gate; do not load post-lead registries, filter references, or the full generate-messages prompt before it. Message drafting starts after the filter-choice answer, must load get_subskill_prompt({ subskillName: "generate-messages", offset, limit }) until hasMore=false, must read live campaign table state through scoped MCP/product tools, and must reject mismatched selectedLeadListId/workflowTableId/campaign/workspace input. On the filter path, keep the browser on Filter Rules after save_rubrics so the user can approve the saved criteria; only then move to Filter Leads and wait there for message approval. Enrichment, filtering, Generate Message cells, sender setup, sequence attach, and launch wait for template approval on the Use Template path. On the skip path, move to Messages/message review and wait for message approval before enrichment or Settings. Do not render message review from checklist or shortcut instructions; message review requires a messageDraftRecommendation whose basis proves the full generate-messages prompt ran for the current campaign/table execution slice. 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/dist/tools/readiness.js

@@ -101,7 +101,7 @@ export const readinessToolDefinitions = [
                 },
                 targetLeadCount: {
                     type: "number",
-                    description: "Target number of leads requested. Used as a fallback completion check when status is unavailable. For Signal Discovery, pass the approved source-candidate target; if the completed source list lands below it, the tool still returns ready with a source_shortfall warning so the confirmed list can be copied and the first review sample can proceed.",
+                    description: "Target number of leads requested. Used as a fallback completion check when status is unavailable. For Signal Discovery, pass the approved source-candidate target; if the completed source list lands below it, the tool still returns ready with a source_shortfall warning so the confirmed list can be copied and campaign setup can proceed.",
                 },
                 timeoutMs: {
                     type: "number",
@@ -489,7 +489,7 @@ export async function waitForLeadListReady(input) {
                     targetLeadCount: targetLeadCount ?? null,
                     sourceShortfall: signalSourceShortfall,
                     warning: signalSourceShortfall
-                        ? `Signal Discovery completed with ${rowCount.toLocaleString("en-US")} source candidates, below the approved ${signalSourceShortfallTarget.toLocaleString("en-US")} source-candidate target. Confirm/copy the completed list for the first review sample, then add more approved posts or switch provider if the sample quality/scale is not enough.`
+                        ? `Signal Discovery completed with ${rowCount.toLocaleString("en-US")} source candidates, below the approved ${signalSourceShortfallTarget.toLocaleString("en-US")} source-candidate target. Confirm/copy the completed list for campaign setup, then add more approved posts or switch provider if the source quality/scale is not enough.`
                         : undefined,
                 };
             }

package/dist/tools/rubrics.js

@@ -99,7 +99,7 @@ const filterRulesSavedForReviewWatchNarration = {
     stage: "fit-message",
     headline: "Filter rules saved for review",
     visibleState: "The browser is showing Filter Rules with the saved criteria.",
-    agentIntent: "Codex is waiting for filter approval before the review batch is enriched or scored.",
+    agentIntent: "Codex is waiting for filter approval before campaign rows are enriched or scored.",
     nextAction: "Approve or revise the filters",
     progressLabel: "Fit + message",
     safety: "Saved rules are ready to review; downstream row processing remains gated.",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.154",
+  "version": "0.1.156",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",