@sellable/mcp 0.1.128 → 0.1.130

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": "0.1.128",
+  "version": "0.1.130",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/create-campaign/SKILL.md

@@ -13,7 +13,6 @@ allowed-tools:
   - mcp__sellable__get_provider_prompt
   - mcp__sellable__get_source_scout_registry
   - mcp__sellable__get_post_find_leads_scout_registry
-  - mcp__sellable__get_message_prompt
   - mcp__sellable__get_active_workspace
   - mcp__sellable__list_senders
   - mcp__sellable__get_sender
@@ -71,10 +70,11 @@ 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. 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.
+first review batch. After that, the user chooses whether to use filters or skip.
+When filters are chosen, save rubrics, then pause before queueing enrichment or
+filtering: tell the user the fit rules are saved, the message template needs
+approval next, and enrichment/filtering will start after that approval. Use
+Template is the default message path; AI Generated is only an explicit opt-out.
 
 ## Opening Turn Contract
 
@@ -148,12 +148,13 @@ 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 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.
+review batch exists, including while the user is on filter choice, but workflow
+cell execution must wait. After rubrics are saved, do not queue enrichment,
+filtering, or Generate Message cells until the user approves the message
+template. 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
@@ -561,24 +562,26 @@ 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 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 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.
+   resolved, rubrics are saved when filters are enabled, template/token rules
+   are approved on the default Use Template path, and the approved message set
+   is synced into the campaign brief. After rubrics save, pause and say the fit
+   rules are saved; approve the message template next; after approval, queue the
+   bounded review-batch `enrichCellId` cells to kick off enrichment/filtering.
+   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

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

@@ -571,29 +571,19 @@ until the filter choice is resolved and you choose Use Template.`
   provisional candidate work from probable good-fit rows in `lead-sample.json`,
   but the final `message-validation.md` winner must cite basis rows from
   `lead-sample.json` that still pass `lead-filter.md`.
-- Parallel means real parallel execution, not optimistic progress copy. For the
-  lead-source scout, first call `get_source_scout_registry` and use the
-  returned canonical `name` values. In Codex, explicitly spawn one named custom scout per
-  credible source lane when those subagents are visible in the current runtime:
-  `source-scout-linkedin-engagement`
-  (display: LinkedIn Engagement Scout, powered by the `signal-discovery`
-  provider prompt), `source-scout-sales-nav` (Sales Nav Scout), and
-  `source-scout-prospeo-contact` (Prospeo Contact Scout). For Claude Code,
-  invoke the generated `source-scout-*` Task/Agent subagents for all credible
-  lanes in one assistant message only when the session exposes those names.
-  They are installed from the same canonical Sellable agent registry and carry
-  explicit Sellable MCP tool allowlists when `@sellable/install` is active. The
-  parent thread should not preload every provider prompt before spawning scouts;
-  each scout loads only its own provider prompt. If host subagents are
-  unavailable or the names are not visible, use the same provider probes via
-  independent MCP/tool calls in the parent thread or dedicated Sellable MCP
-  tools that perform server-side `Promise.all` fan-out. Do not write "source
-  scout agents are not installed" or similar host status into customer-facing
-  output. If real parallel execution is not available or not allowed, run the
-  same DAG sequentially and use honest copy: `I’ll tighten the filter first,
-then draft the message from the same sample.` Never say `kicking off two
-workstreams`, `in parallel`, or `background` unless parallel branches were
-  actually launched.
+- Parallel means real parallel execution, not optimistic progress copy. Source
+  scouting is sequential by default: start with the first recommended lane from
+  `flow.v2.json`, usually Signal Discovery / LinkedIn engagement. Only launch
+  multiple named source scouts when the user explicitly requested comparison, a
+  prior lane failed, or the active flow marks the first lane borderline. The
+  fallback order is plain: use Sales Nav to find ICP people who are actively
+  posting on LinkedIn; if that is not enough, search Sales Nav by titles; if
+  that is still not enough, use Prospeo for a broader account/contact path.
+  Before any source scout dispatch, call `get_source_scout_registry` and use the
+  returned canonical `name` values. The parent thread should not preload every
+  provider prompt; each scout loads only its own provider prompt. Do not write
+  "source scout agents are not installed" or similar host status into
+  customer-facing output.
 - Source scout parallelism must not hide all provider work from the watch UI.
   The parent thread owns the first visible provider search: call the chosen
   provider prompt/search with the minted CampaignOffer id and provider
@@ -633,22 +623,25 @@ batch`, and a no-launch safety note. Do not leave the guide saying
   recovery and ask whether to retry import, import more from the approved
   source, or revise source. Active filtering starts only after rubrics are
   saved; do not say filtering the batch before rubrics are saved.
-- After Lead Fit Builder saves rubrics, move the watched browser to Filter
-  Leads before waiting for message work to finish. Persist
-  `enableICPFilters: true`, `currentStep: "apply-icp-rubric"`, and
-  `watchNarration.stage: "fit-message"` so the user can see fit filtering
-  happen while the Message Draft Builder finishes. The next user-facing Messages
-  screen must show mode choice first: Use Template and AI Generated. Use
-  Template is recommended. AI Generated is an explicit opt-out that cancels or
+- When the user chooses filters, immediately persist `enableICPFilters: true`
+  and `currentStep: "create-icp-rubric"` so the watched app leaves the filter
+  choice screen and shows that Codex is defining the rules in chat. After Lead
+  Fit Builder saves rubrics, move the watched browser to Filter Leads before
+  waiting for message work to finish. Persist `currentStep:
+"apply-icp-rubric"` and `watchNarration.stage: "fit-message"`, then read the
+  bounded review batch with `get_rows_minimal`, but do not queue workflow cells
+  yet. Tell the user the fit rules are saved, the message template needs
+  approval next, and enrichment/filtering will start after approval. Do not call
+  `check_rubric` in the normal create-campaign-v2 path. Use Template is the
+  default message path. AI Generated is an explicit opt-out that cancels or
   ignores the background template draft and must not let late template output
   overwrite campaign state. Product Generate Message cells should not run from
   the background template path until template/token rules are approved. After
   message approval, update the campaign brief with an Approved Message Template
-  containing `{{...}}` tokens and keep `enableICPFilters: true`; Generate
-  Message detects template mode from those tokens, not from
-  `useMessagingTemplate`. Sample validation then runs the review-batch cascade,
-  and the user should be walked through fit results, generated message results,
-  and Settings/sender/sequence handoff.
+  containing `{{...}}` tokens and keep `enableICPFilters: true`; then queue only
+  pending/error `enrichCellId` values with `queue_cells` to start enrichment and
+  filtering. Generate Message detects template mode from those tokens, not from
+  `useMessagingTemplate`.
 - During pre-import validation, do not call `check_rubric`; use the lead-filter
   artifacts and only use campaign-backed scoring after Step 13 imports the
   15-lead test batch.
@@ -1283,21 +1276,22 @@ Do not:
 
 Step 3 is the Message Draft Builder path. It is orchestrated by the main thread
 and executed either by the `post-find-leads-message-scout` worker or by the
-parent-thread fallback. The worker carries the campaign-launch message rules in
-its agent prompt. The parent-thread fallback must load the small safety-gate
-reference before writing message artifacts:
+parent-thread fallback. The worker and fallback must load the full
+`generate-messages` prompt with `get_subskill_prompt` and use it as the drafting
+contract. The small safety-gate reference is only a supplemental approval
+check, not a replacement for the long message workflow:
 
 ```
+mcp__sellable__get_subskill_prompt({ subskillName: "generate-messages", offset, limit }) until hasMore=false
 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
-`create-campaign-v2`. The safety-gate asset is a parent-thread compatibility
-path for hosts that cannot launch `post-find-leads-message-scout`, not a
-generate-message fast-mode prompt and not the preferred route. If the safety gate
-is missing a needed campaign-specific rule or the draft fails quality gates, stop
-at `revise-messaging` with the exact failure instead of pulling the long prompt
-into the main thread.
+Use campaign state, campaign brief content, selected source state, and the
+selected/imported review-batch rows as the source of truth. Do not read
+`brief.md`, `lead-review.md`, or `lead-sample.json` as required state in the
+normal live campaign path; those files are optional debug context only. If the
+long prompt plus safety gate cannot safely approve the draft, stop at
+`revise-messaging` with the exact failure.
 
 Do NOT proceed to Step 4 (message review gate) unless the user has answered
 filter choice, the Messages step has shown the mode choice, the user chose Use

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

@@ -230,31 +230,24 @@ setting: `~/.codex/config.toml` with
 
 ## Parallelism + Naming
 
-Source-angle comparison should be real, not implied. When the source is not
-supplied and multiple source angles are viable, scout Signals, Sales Nav, and
-relevant domain/contact paths as independent branches when the host can do so.
-Call `get_source_scout_registry` first and use the returned canonical `name`
-values; the names below are the current registry entries. In Codex, explicitly
-spawn named custom scouts in the same turn when the current runtime exposes
-them:
-`source-scout-linkedin-engagement` (LinkedIn Engagement Scout, backed by the
-`signal-discovery` provider prompt), `source-scout-sales-nav` (Sales Nav Scout), and
-`source-scout-prospeo-contact` (Prospeo Contact Scout) for the credible lanes. Codex
-does not infer subagent fan-out from generic "compare paths" wording. In Claude
-Code, invoke the generated `source-scout-linkedin-engagement`, `source-scout-sales-nav`,
-and/or `source-scout-prospeo-contact` Task/Agent subagents in one assistant
-message only when the session lists those names, so Claude can run the source
-lanes concurrently/background. These agents come from the same canonical
-Sellable registry and must load their matching provider prompt before
-searching. The parent thread should not fetch every provider prompt first; that
-burns time and often degenerates into parallel tool calls instead of true
-subagents. When asking the user to approve a brief with Sellable finding leads,
-use an explicit label like `Approve brief + use background source scouts` only
-when the current runtime exposes the named agents; otherwise use `Approve brief
-
-- compare source paths`. If the host runs them sequentially or the named agents
-  are absent, keep the output numeric but do not claim the source scout was
-  parallel or surface install status to the customer.
+Source selection is sequential by default. Start with the first recommended
+source lane from `flow.v2.json`; for the current campaign shape that is usually
+Signal Discovery / LinkedIn engagement. Only try the next fallback after the
+current lane is not viable, the user asks for a comparison, or the first lane is
+borderline and needs a second source to avoid a bad recommendation. The fallback
+order must stay plain: use Sales Nav to find ICP people who are actively posting
+on LinkedIn; if that is not enough, search Sales Nav by titles; if that is still
+not enough, use Prospeo for a broader account/contact path.
+
+Source-angle comparison should be real, not implied. Call
+`get_source_scout_registry` before dispatching source scouts and use the
+returned canonical `name` values. In Codex or Claude Code, launch multiple named
+source scouts in the same turn only when the user explicitly requested source
+comparison, a prior lane failed, or the active flow marks the first lane as
+borderline. The parent thread should not fetch every provider prompt first; each
+scout loads only its matching provider prompt. If source work is sequential,
+keep the output numeric but do not claim the source scout was parallel or
+surface install status to the customer.
 
 For post-lead work, call `get_post_find_leads_scout_registry` after source
 approval and use the returned canonical `name` values. Launch both returned

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

@@ -963,9 +963,10 @@
           "targetLeadCountFromConfig": "sourceTargetGoodFitLeadCount (default 300) for provider source-list materialization, not import.importLimit",
           "signalDiscoveryRequiredFields": [
             "targetEngagerCount from approved source math",
-            "maxPostsToScrape or selected post plan when available"
+            "approved promoted post ids selected with select_promising_posts",
+            "maxPostsToScrape from approved source math"
           ],
-          "signalDiscoveryRule": "For Signal Discovery, pass targetEngagerCount = ceil(sourceTargetGoodFitLeads / sampledFitRateAfterCleanup) and maxPostsToScrape = postsNeeded when known. This prevents import_leads from scraping every selected/promoted sample post by default. The first campaign review batch is still limited by confirm_lead_list targetLeadCount import.importLimit.",
+          "signalDiscoveryRule": "For Signal Discovery, promote/select the exact approved posts with select_promising_posts before import_leads. Then pass targetEngagerCount = ceil(sourceTargetGoodFitLeads / sampledFitRateAfterCleanup) and maxPostsToScrape = postsNeeded from the approved source math. If no approved promoted posts are attached to the campaign, stop and route back to find-leads; do not import from unpromoted sample/search results. The first campaign review batch is still limited by confirm_lead_list targetLeadCount import.importLimit.",
           "onZeroLeads": "escalate_hard_fail",
           "modeAddHandshake": {
             "firstCallReturns": "needsModeSelection=true + existingLeadListId",
@@ -976,7 +977,8 @@
           "defaultBranch": "normal-discovery",
           "skipWhen": "resolved source branch returns sourceLeadListId for confirm_lead_list",
           "requiredBeforeCall": [
-            "campaign_attached_source_state"
+            "campaign_attached_source_state",
+            "for Signal Discovery: approved_promoted_posts_attached_to_campaign"
           ]
         },
         {
@@ -1069,11 +1071,7 @@
         "review_batch_imported": "filter-choice",
         "escalation_triggered": "escalation"
       },
-      "requiredArtifacts": [
-        "brief.md",
-        "lead-review.md",
-        "lead-sample.json"
-      ],
+      "requiredArtifacts": [],
       "requiredCampaignState": [
         "campaignId",
         "providerSearchAssociation",
@@ -1102,7 +1100,18 @@
             "currentStep": "filter-choice",
             "watchNarration.stage": "fit-message"
           },
-          "watchNarrationRule": "Show Added to Campaign with a Choose filters or skip decision. Do not say filtering the batch before rubrics are saved."
+          "watchNarrationRule": "Ask whether the user wants to further filter the imported leads. Say whether the selected lead list looks mixed/good/noisy based on the imported 15-row review batch, then ask Choose filters or skip. Do not say filtering the batch before rubrics are saved."
+        },
+        {
+          "action": "persist_filters_enabled_choice",
+          "tool": "update_campaign",
+          "when": "immediately after the user chooses filters_enabled",
+          "requiredValues": {
+            "enableICPFilters": true,
+            "currentStep": "create-icp-rubric",
+            "watchNarration.stage": "fit-message"
+          },
+          "watchNarrationRule": "Move the watched app to Filter Rules and show passive copy that Codex is defining the filters in chat. Do not leave the user on filter-choice after they choose filters."
         }
       ],
       "allowedTools": [
@@ -1136,6 +1145,8 @@
       "interruptOnly": true,
       "requiredCampaignState": [
         "campaignId",
+        "campaignBrief",
+        "selectedLeadListId",
         "workflowTableId"
       ]
     },
@@ -1158,9 +1169,9 @@
               "name": "filter-leads",
               "target": "filter-leads",
               "inputs": [
-                "brief.md",
-                "lead-review.md",
-                "lead-sample.json",
+                "campaignBrief",
+                "selected source decision",
+                "selectedLeadListId",
                 "workflowTableId review-batch rows"
               ],
               "producesArtifacts": [
@@ -1176,30 +1187,33 @@
               "target": "generate-messages",
               "mode": "DRY MODE",
               "inputs": [
-                "brief.md",
-                "lead-review.md",
-                "lead-sample.json",
+                "campaignBrief",
+                "selected source decision",
+                "selectedLeadListId",
                 "workflowTableId 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"
               ],
               "ownership": "proof inventory, token strategy, angle drafting, skeptical-prospect review, and selected winner only"
             }
           ],
-          "earlyMessageStartRule": "After auto-execute-leads confirms the 15-row review batch, workflowTableId is ready, and the user has reached filter choice, the Message Draft Builder may start from brief.md, lead-review.md, lead-sample.json, and the imported campaign table sample, including while the user is on filter choice. This background template draft is provisional speed work only. The message worker carries the campaign-launch message rules in its agent prompt; parent-thread fallback loads references/message-review-safety-gate.md. Legacy/resume preview prep still requires at least 3 probable good-fit rows. It may run beside filter-leads, but the cascade cannot queue until save_rubrics and update_campaign_brief both succeed.",
-          "finalMessageReconcileRule": "message-validation.md may start before lead-filter.md exists, but before message-review it must cite only imported review-batch rows that still pass lead-filter.md. If the selected winner depends on a row later excluded by lead-filter.md, revise message-generation before message review.",
+          "earlyMessageStartRule": "After auto-execute-leads confirms the 15-row review batch, workflowTableId is ready, and the user has reached filter choice, the Message Draft Builder may start from campaignBrief, selected source state, selectedLeadListId, and imported campaign table rows, including while the user is on filter choice. This background template draft is provisional speed work only. The message worker must load the full generate-messages prompt; parent-thread fallback loads the same prompt and may use references/message-review-safety-gate.md only as a supplemental approval checklist. Legacy/resume preview prep still requires at least 3 probable good-fit rows. It may run beside filter-leads, but product Generate Message cells cannot queue until save_rubrics and update_campaign_brief both succeed.",
+          "finalMessageReconcileRule": "The message recommendation may start before lead-filter.md exists, but before message-review it must cite only imported review-batch rows that still pass the saved rubric/filter results. If the selected winner depends on a row later excluded by saved filters, revise message-generation before message review.",
           "finalTemplateReviewLockRule": "cannot start template review until filter choice is answered and the user chooses Use Template in Messages. If filters are enabled, lock template review until saved rubrics exist, a bounded filter run has completed, and there are usable passing/probably passing rows. prefer at least 2 usable passing rows for template review; if only 1 passes, show weak-sample copy and ask whether to continue, revise, import more, or skip filters. If filters are skipped, route to Messages mode choice once the review batch is ready. AI Generated is an explicit opt-out and must cancel or ignore the background template draft.",
           "claudeRule": "In Claude Code, launch both returned post-find-leads scouts with Task/Agent subagents in the same assistant message only when the current session lists those agent names. Do not run filter first and then message generation unless subagents/background work are unavailable.",
           "codexRule": "In Codex, launch both returned post-find-leads scout names as disjoint subagents in the same assistant turn only when the host exposes those custom agents for this run. If the host cannot spawn them, run the same branches sequentially and say so.",
           "fallback": "If real parallel branches are unavailable or the named agents are absent, run filter-leads and then message-generation in the parent thread with product MCP tools/assets. Do not customer-surface agent install status, and do not claim background or parallel work in that fallback."
         },
         {
-          "action": "wait_for_lead_filter_artifact",
+          "action": "wait_for_lead_filter_rules",
           "requiredArtifacts": [
             "lead-filter.md"
           ],
@@ -1209,7 +1223,7 @@
             "message-prep.md",
             "message-candidate-drafts.md"
           ],
-          "rule": "Do not wait for message-validation.md before saving rubrics and moving the watched browser to Filter Leads. Message work may still be running while the user watches fit filtering."
+          "rule": "Do not wait for message-validation.md before saving rubrics and moving the watched browser to Filter Leads. lead-filter.md is a debug artifact name; the durable requirement is production-safe rubric rules derived from the live campaign table review batch. Message work may still be running while the user watches fit filtering."
         },
         {
           "action": "save_filter_rubrics_to_campaign",
@@ -1247,11 +1261,35 @@
           "when": "after_save_rubrics_succeeds_before_waiting_for_message_validation",
           "writesCampaignState": "currentStep:apply-icp-rubric"
         },
+        {
+          "tool": "get_rows_minimal",
+          "requiredValues": {
+            "tableId": "workflowTableId",
+            "limit": "import.importLimit"
+          },
+          "purpose": "read_bounded_review_batch_cell_ids_before_filter_wait",
+          "requiredBeforeCascade": true
+        },
+        {
+          "tool": "queue_cells",
+          "requiredValues": {
+            "tableId": "workflowTableId",
+            "cellSource": "bounded_review_batch_enrichCellIds",
+            "statusFilter": [
+              "pending",
+              "error",
+              "dependency_blocked"
+            ]
+          },
+          "purpose": "queue_bounded_review_batch_enrichment_before_waiting_for_rubric_results",
+          "rule": "Queue only enrichCellId values from get_rows_minimal for the bounded review batch. Do not queue icpCellId values or whole-table cells; the workflow cascade runs ICP scoring after enrichment."
+        },
         {
           "tool": "wait_for_rubric_results",
           "requiredValues": {
             "includeRows": false,
-            "minPassedCount": 1
+            "minPassedCount": 1,
+            "targetCount": "bounded review batch count"
           },
           "purpose": "wait_for_bounded_filter_run_before_messages_mode",
           "readVia": "stats_only_tool_result",
@@ -1269,22 +1307,21 @@
           "optional": true
         },
         {
-          "action": "wait_for_message_validation_artifact",
-          "requiredArtifacts": [
-            "message-validation.md"
+          "action": "wait_for_message_draft_recommendation",
+          "requiredOutputs": [
+            "template recommendation",
+            "token fill rules",
+            "rendered sample"
           ],
           "optionalArtifacts": [
+            "message-validation.md",
             "message-prep.md",
             "message-candidate-drafts.md"
           ],
-          "reconciliationRule": "Before entering message-review, verify message-validation.md came from the same brief.md, lead-review.md, lead-sample.json, and saved lead-filter.md. lead-filter.md gates the sample rows; lead-sample.json remains the message sample source."
+          "reconciliationRule": "Before entering message-review, verify the recommendation came from the same campaignBrief, selected source state, selectedLeadListId, imported review-batch rows, and saved filters. Saved filters gate the sample rows; debug markdown files are optional only."
         }
       ],
-      "requiredArtifacts": [
-        "brief.md",
-        "lead-review.md",
-        "lead-sample.json"
-      ],
+      "requiredArtifacts": [],
       "producesArtifacts": [
         "lead-filter.md",
         "message-validation.md"
@@ -1299,6 +1336,8 @@
         "get_subskill_asset",
         "get_post_find_leads_scout_registry",
         "save_rubrics",
+        "get_rows_minimal",
+        "queue_cells",
         "wait_for_rubric_results",
         "update_campaign",
         "get_campaign_navigation_state",
@@ -1309,16 +1348,16 @@
       ],
       "toolRules": [
         "The post-lead workstreams are disjoint: filter-leads owns lead-filter.md/rubric.json; message-generation owns message-validation.md/message-prep.md/message-candidate-drafts.md.",
-        "message-generation can start before lead-filter.md, but message-review cannot start until both lead-filter.md and message-validation.md exist and reconcile against the same lead-sample.json.",
+        "message-generation can start before saved filters, but message-review cannot start until saved filters and the message recommendation reconcile against the same imported review-batch rows.",
         "Do not let filter-leads create a new message sample. Do not let message-generation fetch new prospects.",
-        "Before writing message-validation.md, message-generation must either run in the post-find-leads-message-scout agent that carries the campaign-launch message rules in its prompt or load get_subskill_asset({ subskillName: \"create-campaign-v2\", assetPath: \"references/message-review-safety-gate.md\" }) in the parent-thread fallback. Do not load the full long generate-messages prompt in create-campaign-v2; if the safety gate cannot safely approve the draft, route to revise-messaging with the concrete failure.",
-        "Do not queue, enrich, attach sequence, or start until save_rubrics succeeds and the approved message set is synced into campaignBrief."
+        "Before writing message-validation.md or returning a template recommendation, message-generation must load the full get_subskill_prompt({ subskillName: \"generate-messages\" }) prompt and use campaignBrief, selected source state, selectedLeadListId, and imported review-batch rows as the source of truth. Optional debug markdown files are not durable state.",
+        "Do not queue before saved rubrics. After save_rubrics succeeds, queue only bounded review-batch enrichCellId values from get_rows_minimal before wait_for_rubric_results.",
+        "Do not attach sequence, start, or queue product Generate Message cells until the approved message set is synced into campaignBrief."
       ],
       "doNotAllow": [
         "create_campaign",
         "import_leads",
         "confirm_lead_list",
-        "queue_cells",
         "start_campaign",
         "check_rubric",
         "generate_messages",
@@ -1343,6 +1382,8 @@
       "interruptOnly": true,
       "requiredCampaignState": [
         "campaignId",
+        "campaignBrief",
+        "selectedLeadListId",
         "workflowTableId"
       ],
       "debugProducesArtifacts": [
@@ -1363,9 +1404,9 @@
           "tool": "update_campaign",
           "requiredValues": {
             "currentStep": "messages",
-            "watchNarration.stage": "review-ready"
+            "watchNarration.stage": "fit-message"
           },
-          "watchNarrationRule": "Messages first shows a mode choice: Use Template and AI Generated. Use Template is recommended because it uses the approved campaign brief and review-batch evidence. AI Generated is an explicit opt-out from the background template draft."
+          "watchNarrationRule": "Messages first shows a mode choice, not final review: Use Template and AI Generated. Use Template is recommended because it uses the approved campaign brief and review-batch evidence. AI Generated is an explicit opt-out from the background template draft. Do not show Review fit and message until the user chooses a mode and a reviewable message/template exists."
         },
         {
           "action": "show_messages_mode_choice",
@@ -1430,6 +1471,8 @@
       "interruptOnly": true,
       "requiredCampaignState": [
         "campaignId",
+        "campaignBrief",
+        "selectedLeadListId",
         "workflowTableId"
       ]
     },
@@ -1557,40 +1600,37 @@
       "onEnter": [
         {
           "action": "run_or_reconcile_subskill",
-          "target": "message-review-safety-gate",
+          "target": "generate-messages",
           "mode": "DRY MODE",
-          "sampleSource": "lead-sample.json from find-leads",
+          "sampleSource": "imported review-batch rows from selectedLeadListId",
           "toolCallRequiredBeforeArtifacts": [
-            "get_subskill_asset({ subskillName: \"create-campaign-v2\", assetPath: \"references/message-review-safety-gate.md\" }) unless the post-find-leads-message-scout agent prompt already supplied these rules"
+            "get_subskill_prompt({ subskillName: \"generate-messages\", offset, limit }) until hasMore=false",
+            "optional supplemental check: get_subskill_asset({ subskillName: \"create-campaign-v2\", assetPath: \"references/message-review-safety-gate.md\" })"
           ],
-          "skipIfFreshArtifactExists": "message-validation.md",
-          "reconcileWith": "lead-filter.md; lead-sample.json remains the sample source"
+          "skipIfFreshStateExists": "fresh messageDraftRecommendation from the same campaign/source/review-batch basis",
+          "reconcileWith": "saved filters and imported review-batch rows; optional lead-filter.md only mirrors those filters"
         },
         {
-          "action": "write_artifact",
-          "artifact": "message-validation.md"
+          "action": "return_template_recommendation",
+          "optionalArtifact": "message-validation.md"
         }
       ],
-      "requiredArtifacts": [
-        "brief.md",
-        "lead-review.md",
-        "lead-sample.json"
-      ],
+      "requiredArtifacts": [],
       "producesArtifacts": [
         "message-validation.md"
       ],
       "allowedTools": [
+        "get_subskill_prompt",
         "get_subskill_asset",
         "AskUserQuestion",
         "request_user_input"
       ],
       "toolRules": [
-        "Before writing message-validation.md, message-review.md, or a message-review AskUserQuestion, the current run must either execute inside the post-find-leads-message-scout agent that carries the campaign-launch message rules in its prompt or load get_subskill_asset({ subskillName: \"create-campaign-v2\", assetPath: \"references/message-review-safety-gate.md\" }) in the parent-thread fallback.",
-        "Lead Sample Basis must cite rows from lead-sample.json produced by find-leads. lead-filter.md only gates those rows; it is not a source for a new sample.",
-        "Do not hand-write message-validation.md from message-prep.md, message-candidate-drafts.md, or general campaign knowledge.",
-        "message-validation.md must prove the message-review safety-gate workflow ran: Gold Standard Strategy Map, Campaign Element Pool, 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, and a raw sendable Selected Winner are required before message-review can recommend approve-message.",
-        "If the hosted output is plausible but weaker than the safety-gate gold-standard rules, stop at message-review with revise-messaging. Do not continue to approval or mint just because the mechanical flow worked.",
-        "Do not load the full generate-messages subskill in create-campaign-v2. If the safety gate is missing a needed campaign-specific rule or the first safety-gate draft fails quality gates, route to revise-messaging with the concrete failure instead of loading the long prompt.",
+        "Before writing message-validation.md, message-review.md, or a message-review AskUserQuestion, load the full get_subskill_prompt({ subskillName: \"generate-messages\" }) prompt and draft from campaignBrief, selected source state, selectedLeadListId, and imported review-batch rows.",
+        "Do not use brief.md, lead-review.md, or lead-sample.json as required live state; those files are optional debug context only.",
+        "Do not hand-write message-validation.md from message-prep.md, message-candidate-drafts.md, stale markdown files, database reads, or general campaign knowledge.",
+        "message-validation.md or the returned recommendation must prove the generate-messages workflow ran and include Token Fill Rules, good-fill and omit/fallback examples, a raw sendable selected winner, and quality gate notes before message-review can recommend approve-message.",
+        "If the generate-messages output is plausible but weaker than the gold-standard rules, stop at message-review with revise-messaging. Do not continue to approval or mint just because the mechanical flow worked.",
         "The approved message set must be written back into campaignBrief before auto-execute-messaging observes or queues product Generate Message cells. AI Generated mode uses the product's AI-generated path instead of template review."
       ],
       "doNotAllow": [
@@ -1628,6 +1668,8 @@
       "interruptOnly": true,
       "requiredCampaignState": [
         "campaignId",
+        "campaignBrief",
+        "selectedLeadListId",
         "workflowTableId"
       ]
     },
@@ -1638,15 +1680,18 @@
       "resumeOnly": false,
       "onEnter": [
         {
-          "action": "read_draft_artifacts",
-          "requiredFiles": [
-            "brief.md",
-            "lead-review.md",
-            "lead-sample.json",
-            "lead-filter.md",
-            "message-validation.md"
+          "action": "read_live_message_recommendation",
+          "requiredState": [
+            "campaignBrief",
+            "selected source state",
+            "selectedLeadListId",
+            "workflowTableId",
+            "saved filters when filters are enabled",
+            "template recommendation with token fill rules and rendered sample"
           ],
-          "optionalFiles": [
+          "optionalDebugFiles": [
+            "lead-filter.md",
+            "message-validation.md",
             "message-prep.md",
             "message-candidate-drafts.md"
           ]
@@ -1765,8 +1810,8 @@
           "requires": [
             "campaignId",
             "message-review-decision.md",
-            "message-validation.md",
-            "lead-filter.md when filters are enabled"
+            "approved template recommendation",
+            "saved filters when filters are enabled"
           ],
           "when": "after_message_approved_before_product_messaging",
           "fields": [

package/skills/create-campaign-v2/references/watch-guide-narration.md

@@ -192,9 +192,9 @@ After review batch import:
 ```json
 {
   "stage": "fit-message",
-  "headline": "Added to Campaign",
-  "visibleState": "The first review batch is in the campaign.",
-  "agentIntent": "Codex is asking you to Choose filters or skip. The Message Draft Builder may prepare a template in the background, but review waits until the filter path is settled.",
+  "headline": "Do you want filters?",
+  "visibleState": "The first review batch is in the campaign. The list is ready to decide whether extra filtering is worth it.",
+  "agentIntent": "Codex is asking whether you want to further filter these leads before message review. The Message Draft Builder may prepare a template in the background, but review waits until the filter path is settled.",
   "nextAction": "Choose filters or skip",
   "safety": "Nothing enriches, validates, or sends until the message is ready and approved.",
   "workerStatuses": {
@@ -207,8 +207,9 @@ After review batch import:
 Use this after the selected review rows are present and before filters are
 saved. This is add-filters intent, not active filtering. Tell the user to
 Choose filters or skip, and do not say filtering the batch before rubrics are
-saved. `enableICPFilters` only becomes true after active filter criteria are
-saved.
+saved. When the user chooses filters, immediately persist
+`enableICPFilters: true` and move to `create-icp-rubric` so the watched app
+shows Filter Rules while Codex defines the rules in chat.
 
 Fit + message:
 

package/skills/create-rubric/SKILL.md

@@ -51,9 +51,13 @@ Create and save a comprehensive lead scoring rubric that:
 
 ## Rubric Validation + Results
 
-- `mcp__sellable__check_rubric` - Queue enrichment + scoring sample (default 7)
+- `mcp__sellable__get_rows_minimal` - Read bounded review-batch cell IDs
+- `mcp__sellable__queue_cells` - Queue only bounded `enrichCellId` values
 - `mcp__sellable__wait_for_rubric_results` - Poll pass-rate results
 
+`check_rubric` is legacy/recovery only. Do not use it in normal
+create-campaign-v2 runs.
+
 </tools>
 
 <rubric_structure>
@@ -117,7 +121,7 @@ Required fields:
 
 - If **Keep & apply**:
   - Call `update_campaign({ campaignId, enableICPFilters: true, currentStep: "apply-icp-rubric" })`
-  - Then proceed to Phase 5 (enrich + score a sample).
+  - Then proceed to Phase 5 (queue bounded enrichment cells + wait for score results).
 
 **If no campaignOfferId:**
 Ask: "Which campaign should I create the rubric for? You can share the campaign ID or describe the target audience."
@@ -203,7 +207,9 @@ update_campaign({
 
 This triggers the campaign sync and moves the user to the filter-leads step where they can see the campaign table with scoring columns.
 
-Then ask the user if we should kick off enrichment for a sample:
+For normal create-campaign-v2 runs, the caller should immediately queue only the
+bounded review-batch enrichment cells and wait for scores. For standalone
+rubric editing, ask the user if we should kick off enrichment for a sample:
 
 "ICP filtering enabled — you should see the leads table with scoring columns now. Want me to run enrichment on the first 5 leads to check pass rates?"
 
@@ -212,9 +218,14 @@ Then ask the user if we should kick off enrichment for a sample:
 
 ## Phase 5: Enrich + Score a Sample
 
-1. Call `check_rubric` with `maxProspects: 5` — finds the first 5 rows' enrich column cells and kicks off enrichment + ICP scoring via the batch queue API.
-2. Call `wait_for_rubric_results` with `targetCount: 5` — polls until ICP scores land.
-3. Summarize pass rate (`passed/completed`, percent) and recommend:
+1. Call `get_rows_minimal({ tableId, limit: 5 })` or use the caller-provided
+   bounded review-batch rows.
+2. Call `queue_cells({ tableId, cellIds })` with only pending/error
+   `enrichCellId` values. Do not pass `icpCellId` values or full-table cells;
+   the workflow cascade handles downstream ICP scoring after enrichment.
+3. Call `wait_for_rubric_results` with `targetCount: 5` and `minPassedCount: 1`
+   — polls until ICP scores land.
+4. Summarize pass rate (`passed/completed`, percent) and recommend:
    - Tighten filters if pass rate is too high (>80% — too loose).
    - Loosen filters if pass rate is too low (<20% — too strict).
    - Continue when results look healthy (30-70% is typical).