@sellable/install 0.1.151 → 0.1.153

package/README.md

@@ -59,11 +59,13 @@ Claude Code and Codex are configured to launch the same packaged MCP server. The
 installer also writes Sellable source-scout agents for both hosts from the
 packaged `agents/` registry: Claude Code gets `source-scout-*` subagents, and
 Codex gets `source-scout-linkedin-engagement`, `source-scout-sales-nav`, and
-`source-scout-prospeo-contact`. Runtime prompts use those named agents only
-when the current session exposes them; otherwise they fall back to the same MCP
-provider probes without customer-facing install-status copy. The MCP exposes
-the same list through `get_source_scout_registry`, so adding a future scout
-starts in one registry entry instead of scattered prompt edits.
+`source-scout-prospeo-contact`. After Find Buyers Plan approval, runtime prompts
+use the named scout for the approved source lane as the normal path when the
+current session exposes it. If a named scout is unavailable, they use a generic
+background agent when possible; parent-thread provider probes are the explicit
+fallback, not the default path. The MCP exposes the same list through
+`get_source_scout_registry`, so adding a future scout starts in one registry
+entry instead of scattered prompt edits.
 
 ## Names
 

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

@@ -1,6 +1,6 @@
-You are Lead Fit Builder for Sellable create-campaign-v2.
+You are Prospect Filters for Sellable create-campaign-v2.
 
-Your job starts only after the lead source has been approved or auto-confirmed,
+Your job starts only after the Start Import gate is approved or auto-confirmed,
 the confirmed source list has been copied into the campaign table, and the first
 campaign-table execution slice exists.
 Work only on the lead filter branch. Do not source new leads, draft messages,

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

@@ -1,9 +1,16 @@
-You are Message Draft Builder for Sellable create-campaign-v2.
+You are Message Drafting for Sellable create-campaign-v2.
+
+Your job starts only after the Start Import gate is approved, the confirmed
+source list has 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.
+
+This worker exists to keep the long `generate-messages` prompt, reference asset
+loading, token strategy, and skeptical copy review out of the parent campaign
+thread. The parent thread is only the orchestrator: it supplies campaign/table
+basis, receives the recommendation, persists the approved template after user
+approval, and handles Settings/launch.
 
-Your job starts only after the source is approved, the confirmed source list has
-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.
@@ -44,15 +51,9 @@ the branch input.
 2. Use that prompt as the drafting contract. Do not use any alternate prompt,
    examples-only shortcut, or create-campaign safety/checklist instructions as a
    substitute for the full message prompt.
-3. Follow the prompt's `Reference Asset Loading` section: load the required
-   pre-draft reference pack before drafting, load final-pass references before
-   approval, and report which assets were used and why. If those required
-   assets cannot be loaded, return `blocked` / `retry-needed`; do not draft from
-   the prompt alone. `ai-tells.md` is part of the required pack and is never
-   optional.
-4. Draft only from the campaign brief, selected source context, and initial
+3. Draft only from the campaign brief, selected source context, and initial
    campaign-table execution slice rows supplied by the parent.
-5. Keep the work provisional until the user chooses `Use Template` in Messages.
+4. Keep the work provisional until the user chooses `Use Template` in Messages.
 
 ## Owned Output
 
@@ -60,8 +61,6 @@ Return the following to the parent thread:
 
 - proposed first-message template using supported `{{...}}` tokens
 - token fill rules and fallbacks
-- `Reference Asset Loading` note naming the required and conditional assets used
-  and why each was used
 - 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
@@ -87,13 +86,13 @@ When reporting branch runtime proof, use this shape under
 - `basisToken` and `basis`
 - optional `messageDraftOutputRef`, `messageDraftOutput`, and `error`
 
-Do not tell the UI to show Message Draft Builder as running unless this proof
+Do not tell the UI to show Message Drafting as running unless this proof
 exists and points at the current non-empty campaign-table execution slice.
 
 ## Basis Changes And Rewrites
 
 The first completed recommendation is the default message review candidate.
-Do not automatically retry or regenerate only because Lead Fit Builder finished,
+Do not automatically retry or regenerate only because Prospect Filters finished,
 rubrics were saved, Filter Leads completed, enrichment cells populated, or more
 row data became available after this branch started.
 
@@ -111,6 +110,27 @@ brief hash, selected source, `selectedLeadListId`, `workflowTableId`, or
 execution-slice rows. Filter/rubric/enrichment basis drift alone is not a stale
 blocker.
 
+## User Revision Feedback
+
+If the parent sends user feedback about the template before `approve-message`,
+treat it as a Message Drafting revision, not a campaign write. Use the current
+`messageDraftRecommendation`, basis token/hash, campaign/table basis, and the
+latest user feedback as inputs. Load or reuse the full
+`generate-messages` contract, then return a revised recommendation with:
+
+- revised proposed template
+- what changed and why
+- token fill rule/fallback changes, if any
+- one rendered good-fill sample
+- pass/fail notes against the same quality gates
+- updated output timestamp/hash and basis token
+
+Keep the revision grounded in the same source/list/table rows unless the parent
+explicitly supplies a new selected list or review slice. Do not call
+`update_campaign_brief`, do not persist the template, and do not approve your
+own revision. The parent renders the revised template and waits for
+`approve-message`.
+
 ## Hard Rules
 
 - Do not call product Generate Message cells. This worker drafts the template
@@ -133,14 +153,10 @@ reacted to`, `saw you engaging with`, or equivalent source-citation copy as a
 hope this is relevant`, `saw you in a few conversations about [topic], so
 may be off, but this seemed relevant`, `saw you might be interested in [topic],
 so hope this is relevant`, `hope this is relevant if [topic] is on your plate`,
-or `found you in a thread about [topic], so may be off, but this seemed relevant`.
-Only use `saw you raise your hand for [topic], so figured this was (hopefully)
-worth sending` when the source was an explicit lead-magnet comment, reply, or
-opt-in.
+or `saw you raise your hand for [topic], so figured this was (hopefully) worth sending`.
 The cheekier `saw you raise your hand for [topic] (creepy to reach out based
 on that, i know) - but this felt too on the nose to ignore` version is also
-allowed only for explicit lead-magnet comments, replies, or opt-ins and when the
-sender's voice can carry it. Bad: `you commented on...`, `you reacted
+allowed when the sender's voice can carry it. Bad: `you commented on...`, `you reacted
 to...`, `saw you engaging with...`, `your LinkedIn activity...`, `you might
 not remember the thread...`, or `found you through [source] and your role
 looked close...`. Otherwise omit the engagement signal and use role/company/problem context.

package/agents/registry.json

@@ -6,7 +6,7 @@
       "name": "source-scout-linkedin-engagement",
       "kind": "source-scout",
       "promptFile": "source-scout-linkedin-engagement.md",
-      "displayName": "LinkedIn Engagement Scout",
+      "displayName": "LinkedIn Source Discovery",
       "provider": "signal-discovery",
       "lane": "linkedin-engagement",
       "legacy": {
@@ -56,7 +56,7 @@
       "name": "source-scout-sales-nav",
       "kind": "source-scout",
       "promptFile": "source-scout-sales-nav.md",
-      "displayName": "Sales Nav Scout",
+      "displayName": "Sales Nav Source Discovery",
       "provider": "sales-nav",
       "lane": "sales-nav",
       "legacy": {
@@ -105,7 +105,7 @@
       "name": "source-scout-prospeo-contact",
       "kind": "source-scout",
       "promptFile": "source-scout-prospeo-contact.md",
-      "displayName": "Prospeo Contact Scout",
+      "displayName": "Prospeo Source Discovery",
       "provider": "prospeo",
       "lane": "prospeo-contact",
       "legacy": {
@@ -155,7 +155,7 @@
       "name": "post-find-leads-filter-scout",
       "kind": "post-find-leads-scout",
       "promptFile": "post-find-leads-filter-scout.md",
-      "displayName": "Lead Fit Builder",
+      "displayName": "Prospect Filters",
       "target": "filter-leads",
       "inputs": [
         "campaignId",
@@ -166,20 +166,20 @@
       ],
       "producesArtifacts": [],
       "optionalProducesArtifacts": [],
-      "ownership": "lead quality, false-positive patterns, keep/exclude rules, ability-to-pay checks, and production rubric translation only",
+      "ownership": "prospect-fit criteria, false-positive patterns, keep/exclude rules, ability-to-pay checks, and production rubric translation only",
       "codex": {
-        "description": "Lead Fit Builder for campaign-backed lead filtering and rubric persistence after review-batch import and filter approval.",
+        "description": "Prospect Filters worker for campaign-backed fit criteria and rubric persistence after review-batch import and filter approval.",
         "model": "gpt-5.5",
         "modelReasoningEffort": "high",
         "sandboxMode": "read-only",
         "nicknameCandidates": [
-          "Lead Fit Builder",
-          "Fit Builder",
+          "Prospect Filters",
+          "Fit Criteria",
           "Rubric Builder"
         ]
       },
       "claude": {
-        "description": "Use proactively as Lead Fit Builder after review-batch import and filter approval to persist campaign rubrics from campaign state.",
+        "description": "Use proactively as Prospect Filters after review-batch import and filter approval to persist campaign rubrics from campaign state.",
         "model": "inherit",
         "background": true,
         "maxTurns": 8,
@@ -196,8 +196,8 @@
       "name": "post-find-leads-message-scout",
       "kind": "post-find-leads-scout",
       "promptFile": "post-find-leads-message-scout.md",
-      "displayName": "Message Draft Builder",
-      "target": "generate-messages-compact",
+      "displayName": "Message Drafting",
+      "target": "generate-messages",
       "inputs": [
         "campaignId",
         "campaignBrief",
@@ -212,20 +212,20 @@
         "rendered sample"
       ],
       "optionalProducesArtifacts": [],
-      "ownership": "proof inventory, token strategy, angle drafting, skeptical-prospect review, and selected winner only",
+      "ownership": "message strategy, proof inventory, token rules, skeptical-prospect review, and selected winner only",
       "codex": {
-        "description": "Message Draft Builder for campaign-backed template proposals after confirm_lead_list imports a non-empty bounded review batch.",
+        "description": "Message Drafting worker for campaign-backed template proposals after confirm_lead_list imports a non-empty bounded review batch.",
         "model": "gpt-5.5",
-        "modelReasoningEffort": "high",
+        "modelReasoningEffort": "xhigh",
         "sandboxMode": "read-only",
         "nicknameCandidates": [
-          "Message Draft Builder",
-          "Draft Builder",
+          "Message Drafting",
+          "Draft Writer",
           "Template Builder"
         ]
       },
       "claude": {
-        "description": "Use proactively as Message Draft Builder after confirm_lead_list imports a non-empty bounded review batch; load generate-messages-compact and draft only from scoped campaign/tool state.",
+        "description": "Use proactively as Message Drafting after confirm_lead_list imports a non-empty bounded review batch; load generate-messages and draft only from scoped campaign/tool state.",
         "model": "inherit",
         "background": true,
         "maxTurns": 10,

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

@@ -45,8 +45,8 @@ sales Claude`; do not treat broad anchor-only lanes like `Claude Code`, `MCP`,
 campaignOfferId, selectionMode: "replace", selections, headlineICPCriteria,
 scrapePlanMode: "all-selected", currentStep: "signal-discovery" })` before sampling so the watched Signal
    Discovery table shows the promoted posts and the exact posts being tested.
-   Do not move the campaign to `confirm-lead-list`; `import_leads` owns that
-   visible transition after source approval.
+	   Do not move the campaign to `confirm-lead-list`; `import_leads` owns that
+	   visible transition after Start Import approval.
 6. Fetch or sample engagers for promoted posts and score rough ICP fit from
    visible headline/display-name cues only. Do not enrich people during
    viability estimation.

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

@@ -12,8 +12,8 @@ campaignOfferId, confirmed: true })` and include that same `campaignOfferId`
   If no campaign ID is supplied, run campaignless preview mode. Treat post-mint
   searches with `campaignOfferId` as campaign-attached persisted search tabs;
   do not run a live campaign search without the campaign ID.
-  Do not move the campaign to `confirm-lead-list`; `import_leads` owns that
-  visible transition after source approval.
+	  Do not move the campaign to `confirm-lead-list`; `import_leads` owns that
+	  visible transition after Start Import approval.
 
 Use the inherited Sellable MCP tools when available:
 
@@ -57,7 +57,7 @@ Evidence standards:
   below 10% after reasonable refinement, recommend tightening the ICP/source
   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
+  Start Import for the approved source list; the parent thread later
   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

@@ -12,8 +12,8 @@ campaignOfferId, confirmed: true })` and include that same `campaignOfferId` in
   route. If no campaign ID is supplied, run campaignless preview mode. Treat post-mint
   searches with `campaignOfferId` as campaign-attached persisted search tabs;
   do not run a live campaign search without the campaign ID.
-  Do not move the campaign to `confirm-lead-list`; `import_leads` owns that
-  visible transition after source approval.
+	  Do not move the campaign to `confirm-lead-list`; `import_leads` owns that
+	  visible transition after Start Import approval.
 
 Use the inherited Sellable MCP tools when available:
 
@@ -81,7 +81,7 @@ Evidence standards:
 - If projected good-fit after cleanup is below 10%, do not recommend Sales Nav
   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
+  Start Import for the approved source list; the parent thread later
   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.

package/bin/sellable-install.mjs

@@ -772,7 +772,7 @@ are likely. Sales Nav is useful for recent LinkedIn activity, role/title
 precision, and referral paths, but it does not provide hiring-by-role filters;
 say that distinction plainly in the source-plan gate.
 
-After scouting, ask for a second approval on the concrete source action. For
+After scouting, ask for a second approval on Start Import. For
 LinkedIn engagement (\`signal-discovery\` internally), use plain language:
 selected posts, people we can check, likely prospects, what the first
 review will inspect, cleanup risk, and fallback. N must be the smallest
@@ -922,15 +922,15 @@ Treat host capabilities as concrete functions, not prose conventions:
   \`mcp__sellable__get_source_scout_registry({})\` before any scout dispatch.
 - \`load_post_find_leads_scout_registry\`: call
   \`mcp__sellable__get_post_find_leads_scout_registry({})\` after source
-  approval and before dispatching the post-lead filter/message scouts.
+  import and before dispatching Prospect Filters/Message Drafting.
 - \`launch_source_scout\`: Claude Code uses \`Task\` with \`subagent_type\` equal to
   the registry \`name\` only when the session lists those agents; Codex uses
   named custom agents such as
   \`source-scout-linkedin-engagement\`, \`source-scout-sales-nav\`, and
   \`source-scout-prospeo-contact\` when subagents are available.
 - \`launch_post_find_leads_scout\`: Claude Code uses \`Task\` with
-  \`subagent_type\` equal to the returned post-lead registry \`name\` only when
-  the session lists those agents; Codex uses the returned custom agents such as
+  \`subagent_type\` equal to the returned prospect-setup registry \`name\` only when
+  the session lists those agents; Codex uses the returned compatibility agents such as
   \`post-find-leads-filter-scout\` and \`post-find-leads-message-scout\` when
   subagents are available.
 
@@ -1108,10 +1108,22 @@ updates.
    copies of this file; packaged Claude Code and Codex runs must use the MCP
    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. The worker and parent-thread fallback must load
+4. For message generation, keep the parent thread as a lean orchestrator and
+   use the \`post-find-leads-message-scout\` agent whenever the host exposes it
+   and the current host policy allows agent launch. The worker must load
    \`mcp__sellable__get_subskill_prompt({ subskillName: "generate-messages" })\`.
-   Do not use any alternate or examples-only message prompt. Message review requires Message Draft Builder output:
+   In Codex, YOLO/autonomous mode counts as campaign-scoped permission to use
+   Sellable background agents for pre-launch work. If the user has not enabled
+   YOLO and has not explicitly asked for background agents, subagents, parallel
+   agents, delegation, or a message/bg agent in this campaign, ask once for
+   permission before loading the long message prompt in the parent. If
+   permission is granted but the named custom agent is not
+   available, spawn a generic background agent with \`model: "gpt-5.5"\` and
+   \`reasoning_effort: "xhigh"\` using the same campaign/table basis. Do not
+   silently fall back to parent-thread message drafting; parent fallback is
+   allowed only when the user explicitly says to continue without a background
+   agent.
+   Do not use any alternate or examples-only message prompt. Message review requires Message Drafting output:
    do not draft from a checklist, local markdown artifact, or parent-thread
 	   intuition. Use campaign state, campaign brief content, selected source state,
 	   and initial campaign-table execution slice rows as the source of truth; do not read stale
@@ -1120,10 +1132,10 @@ updates.
 5. Create the campaign shell early with the v1 brief so the user can open the
    watch link and see useful setup state immediately. Materialize the approved
    source list, copy confirmed rows into the campaign, and internally process the
-   first campaign-table execution slice after the source is attached to the campaign; do not
-   load post-lead registries/prompts before asking add filters vs skip filters.
-   Once the user answers, launch the message scout from the same campaign/table
-   basis. If filters are approved, also launch the filter scout. Do not queue
+	   first campaign-table execution slice after the source is attached to the campaign; do not
+   load prospect-setup registries/prompts before asking add filters vs skip filters.
+   Once the user answers, launch Message Drafting from the same campaign/table
+   basis. If filters are approved, also launch Prospect Filters. Do not queue
    workflow cells, attach a sequence, or start until saved filters and the
    message template/token rules are approved. When filters are chosen, immediately
    call \`mcp__sellable__update_campaign({ campaignId, enableICPFilters: true, currentStep: "create-icp-rubric", watchNarration })\`
@@ -1244,8 +1256,8 @@ Desktop, then start a new thread.
 2. When the canonical prompt asks for \`references/*.md\`, load those files
    with \`mcp__sellable__get_subskill_asset({ subskillName: "interview", assetPath: "references/<file>.md" })\`.
 3. Follow the canonical prompt exactly. Save local memory only where that prompt
-   directs, under \`~/.sellable/configs/core/**\` and
-   \`~/.sellable/interviews/**\`.
+   directs, under \`.sellable/configs/core/**\` and
+   \`.sellable/interviews/**\`.
 
 ## MCP Prompt Fallback
 
@@ -1291,7 +1303,7 @@ Desktop, then start a new thread.
    If the response has \`hasMore=true\`, continue with \`nextOffset\` until
    \`hasMore=false\`.
 2. Follow the canonical prompt exactly. Read the relevant
-   \`~/.sellable/configs/**\` memory files it names.
+   \`.sellable/configs/**\` memory files it names.
 3. Apply the loaded memory silently to the user's requested writing or answer.
    If the user only asked to load voice, summarize the active rules briefly and
    ask what they want drafted, answered, or reviewed.
@@ -2044,7 +2056,7 @@ function patchClaudeAlwaysLoad(opts) {
 }
 
 function installCodex(opts) {
-  if (!opts.dryRun && !commandExists("codex")) {
+  if (!commandExists("codex")) {
     const message =
       "Codex CLI not found. Install/login to Codex, then rerun: sellable --host codex";
     if (opts.host === "all") {
@@ -2053,9 +2065,6 @@ function installCodex(opts) {
     }
     throw new Error(message);
   }
-  if (!opts.dryRun) {
-    mkdirSync(codexHome(), { recursive: true, mode: 0o700 });
-  }
   if (opts.server === "hosted") {
     run("codex", codexMcpAddArgs(opts), opts);
     const info = installCodexDesktopPlugin(opts);
@@ -2622,13 +2631,6 @@ async function main() {
         process.exit(2);
       }
       const token = rawArgs[2];
-      const authSetFlags = rawArgs.slice(3);
-      const dryRun = authSetFlags.includes("--dry-run");
-      const unknownAuthSetFlag = authSetFlags.find((arg) => arg !== "--dry-run");
-      if (unknownAuthSetFlag) {
-        console.error(`Unknown auth set option: ${unknownAuthSetFlag}`);
-        process.exit(2);
-      }
       if (!token) {
         console.error(
           "Usage: sellable auth set <token>\n" +
@@ -2653,13 +2655,9 @@ async function main() {
       writeJson(
         authPath(),
         { token, activeWorkspaceId: null, apiUrl },
-        { dryRun }
+        { dryRun: false }
       );
-      if (dryRun) {
-        console.log(`Dry run: token would be saved to ${authPath()}`);
-      } else {
-        console.log(`✓ Token saved to ${authPath()}`);
-      }
+      console.log(`✓ Token saved to ${authPath()}`);
       console.log(`  apiUrl: ${apiUrl}`);
       console.log(`  Continue in your agent:`);
       console.log(`    Claude Code: /sellable:create-campaign`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/install",
-  "version": "0.1.151",
+  "version": "0.1.153",
   "type": "module",
   "description": "One-command installer for Sellable MCP in Claude Code and Codex",
   "bin": {

package/skill-templates/create-campaign.md

@@ -203,7 +203,7 @@ are likely. Sales Nav is useful for recent LinkedIn activity, role/title
 precision, and referral paths, but it does not provide hiring-by-role filters;
 say that distinction plainly in the source-plan gate.
 
-    After scouting, ask for a second approval on the concrete source action. For
+    After scouting, ask for a second approval on Start Import. For
     LinkedIn engagement (`signal-discovery` internally), name how many
     recommended posts will be scraped and the target engager/source-candidate
     volume. N must be the smallest right-content post set that clears the source
@@ -253,20 +253,29 @@ scout those angles as independent branches when the host can actually do it:
 LinkedIn posts / people reacting or commenting (internal `signal-discovery`
 provider prompt), Sales Nav / title + company filters, and Prospeo Contact /
 domains, hiring filters, or broad verified-contact expansion when relevant. In
-Codex, explicitly spawn the named custom scouts
+Codex, source discovery is agent-first after the Find Buyers Plan approval. For
+the approved single source lane, explicitly spawn that returned named custom
+scout; for example, choosing LinkedIn posts should spawn
+`source-scout-linkedin-engagement` even when no comparison is needed. When
+multiple source angles are credible, explicitly spawn the named custom scouts
 `source-scout-linkedin-engagement`, `source-scout-sales-nav`, and
 `source-scout-prospeo-contact` for the credible lanes only when the current host
-exposes those names; Codex does not infer subagent fan-out from generic source
-comparison wording. In Claude Code, invoke the generated `source-scout-*`
-Task/Agent subagents for all credible lanes in one assistant message only when
-the current session lists those names. The installer writes them from the same
-canonical Sellable agent registry with explicit Sellable MCP tool allowlists.
+exposes those names; Codex does not infer subagent fan-out from generic wording.
+YOLO/autonomous mode counts as campaign-scoped permission to use Sellable source
+background agents. In Claude Code, invoke the generated `source-scout-*`
+Task/Agent subagent for the approved lane, or all credible lanes in one
+assistant message when comparison/fallback is needed, only when the current
+session lists those names. The installer writes them from the same canonical
+Sellable agent registry with explicit Sellable MCP tool allowlists.
 The create-campaign-v2 subskill calls `get_source_scout_registry` before
 dispatch so the current registry, not this copy, is the runtime source of truth.
-If the host runs them sequentially or the named agents are unavailable, do not
-claim they ran in parallel and do not surface install status to the customer. In
-chat, call the downstream copy stage `message generation`; message validation is
-only an internal approval proof.
+If the named source scout is unavailable, use a generic `gpt-5.5` high
+background agent when the host can spawn generic agents. Continue source
+discovery in the parent thread only when agent launch is impossible or the user
+explicitly says to continue inline. Do not claim a scout ran unless one did, and
+do not surface install status to the customer. In chat, call the downstream copy
+stage `message generation`; message validation is only an internal approval
+proof.
 
 For campaign-attached Signal Discovery sampling, promote/select the exact posts
 with `select_promising_posts` before `fetch_post_engagers` so the user can see
@@ -281,17 +290,17 @@ actually engaging and the source is viable.
 
     After confirmed source rows exist in the campaign table, use the same registry pattern for
 
-post-lead work, but do not load that registry or any deep filter/message prompt
+prospect setup work, but do not load that registry or any deep filter/message prompt
 before the filter-choice question. After `confirm_lead_list`, ask add filters
-vs skip filters immediately. Once the user answers, launch the message scout
+vs skip filters immediately. Once the user answers, launch Message Drafting
 from the same campaign/table basis. If the user chooses filters, also launch the
-filter-leads scout, move to Filter Rules, save rubrics, then ask for filter
+Prospect Filters worker, move to Filter Rules, save rubrics, then ask for filter
 approval. After approval, move to Filter Leads and show `Filters saved + waiting
 for message approval` while the message recommendation is reviewed. If the user
 skips filters, move to Messages/message review. Enrichment/filtering and
 Generate Message cells wait for message approval. AI Generated is an explicit
 opt-out from the template path. If the
-post-lead agents are absent, the main thread still orchestrates the same
+prospect setup agents are absent, the main thread still orchestrates the same
 branches from compact MCP context.
 
 Use rendered Markdown for user review surfaces, not fenced code blocks. Keep
@@ -427,15 +436,15 @@ Treat host capabilities as concrete functions, not prose conventions:
   `mcp__sellable__get_source_scout_registry({})` before any scout dispatch.
 - `load_post_find_leads_scout_registry`: call
   `mcp__sellable__get_post_find_leads_scout_registry({})` after source
-  approval and before dispatching the post-lead filter/message scouts.
+  import and before dispatching Prospect Filters/Message Drafting.
 - `launch_source_scout`: Claude Code uses `Task` with `subagent_type` equal to
   the registry `name` only when the session lists those agents; Codex uses
   named custom agents such as
   `source-scout-linkedin-engagement`, `source-scout-sales-nav`, and
   `source-scout-prospeo-contact` when subagents are available.
 - `launch_post_find_leads_scout`: Claude Code uses `Task` with `subagent_type`
-  equal to the returned post-lead registry `name` only when the session lists
-  those agents; Codex uses the returned custom agents such as
+  equal to the returned prospect-setup registry `name` only when the session
+  lists those agents; Codex uses the returned compatibility agents such as
   `post-find-leads-filter-scout` and `post-find-leads-message-scout` when
   subagents are available.
 
@@ -758,10 +767,23 @@ updates.
    copies of this file; packaged Claude Code and Codex runs must use the MCP
    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. The worker and parent-thread fallback must load
+4. For message generation, keep the parent thread as a lean orchestrator and
+   use the `post-find-leads-message-scout` compatibility agent for Message
+   Drafting whenever the host exposes it
+   and the current host policy allows agent launch. The worker must load
    `mcp__sellable__get_subskill_prompt({ subskillName: "generate-messages" })`.
-   Do not use any alternate or examples-only message prompt. Message review requires Message Draft Builder output:
+   In Codex, YOLO/autonomous mode counts as campaign-scoped permission to use
+   Sellable background agents for pre-launch work. If the user has not enabled
+   YOLO and has not explicitly asked for background agents, subagents, parallel
+   agents, delegation, or a message/bg agent in this campaign, ask once for
+   permission before loading the long message prompt in the parent. If
+   permission is granted but the named custom agent is not
+   available, spawn a generic background agent with `model: "gpt-5.5"` and
+   `reasoning_effort: "xhigh"` using the same campaign/table basis. Do not
+   silently fall back to parent-thread message drafting; parent fallback is
+   allowed only when the user explicitly says to continue without a background
+   agent.
+   Do not use any alternate or examples-only message prompt. Message review requires Message Drafting output:
    do not draft from a checklist, local markdown artifact, or parent-thread
    intuition. Use campaign state, campaign brief content, selected source state, and
    initial campaign-table execution slice rows as the source of truth; do not read stale local