@sellable/install 0.1.147 → 0.1.149

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

@@ -37,13 +37,14 @@ the branch input.
 
 ## Required First Steps
 
-1. Load the full long-form generate-messages prompt:
+1. Load the compact normal-path message prompt:
 
-   `get_subskill_prompt({ subskillName: "generate-messages", offset, limit })`
-   until `hasMore` is false.
+   `get_subskill_prompt({ subskillName: "generate-messages-compact" })`
 
-2. Use that prompt as the drafting contract. Do not use create-campaign
-   safety/checklist instructions as a substitute for the full prompt.
+2. Use that prompt as the drafting contract. Load
+   `generate-messages-compact/references/examples-critique-revision.md` only for
+   critique, revision, or close-call examples. Do not use create-campaign
+   safety/checklist instructions as a substitute for the message prompt.
 3. Draft only from the campaign brief, selected source context, and initial
    campaign-table execution slice rows supplied by the parent.
 4. Keep the work provisional until the user chooses `Use Template` in Messages.
@@ -56,7 +57,7 @@ Return the following to the parent thread:
 - token fill rules and fallbacks
 - 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
+- pass/fail notes against the generate-messages-compact quality gates
 - compact runtime status: `ready`, `blocked`, `retry-needed`, or `stale`
 - basis token containing campaign revision/updatedAt, brief hash,
   `selectedLeadListId`, `workflowTableId`, execution-slice row ids/hash, filter
@@ -136,7 +137,7 @@ enablement`, or omit it.
 
 Return a concise status with:
 
-- prompt basis loaded: `generate-messages`
+- prompt basis loaded: `generate-messages-compact`
 - live campaign basis used
 - proposed template
 - token fill rules/fallbacks

package/agents/registry.json

@@ -197,7 +197,7 @@
       "kind": "post-find-leads-scout",
       "promptFile": "post-find-leads-message-scout.md",
       "displayName": "Message Draft Builder",
-      "target": "generate-messages",
+      "target": "generate-messages-compact",
       "inputs": [
         "campaignId",
         "campaignBrief",
@@ -225,7 +225,7 @@
         ]
       },
       "claude": {
-        "description": "Use proactively as Message Draft Builder after confirm_lead_list imports a non-empty bounded review batch; load the full generate-messages prompt and draft only from scoped campaign/tool state.",
+        "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.",
         "model": "inherit",
         "background": true,
         "maxTurns": 10,

package/bin/sellable-install.mjs

@@ -592,7 +592,11 @@ const CREATE_CAMPAIGN_ALLOWED_TOOLS = [
   "mcp__sellable__check_rubric",
   "mcp__sellable__create_campaign",
   "mcp__sellable__save_rubrics",
-  "mcp__sellable__wait_for_rubric_results",
+  "mcp__sellable__get_campaign_table_schema",
+  "mcp__sellable__select_campaign_cells",
+  "mcp__sellable__queue_campaign_cells",
+  "mcp__sellable__wait_for_campaign_processing",
+  "mcp__sellable__revise_message_template_and_rerun",
   "mcp__sellable__update_campaign_brief",
   "mcp__sellable__update_campaign",
   "mcp__sellable__get_campaign",
@@ -608,7 +612,6 @@ const CREATE_CAMPAIGN_ALLOWED_TOOLS = [
   "mcp__sellable__get_table_rows",
   "mcp__sellable__load_csv_linkedin_leads",
   "mcp__sellable__load_csv_domains",
-  "mcp__sellable__queue_cells",
   "mcp__sellable__get_campaign_messages_preview",
   "mcp__sellable__attach_sequence",
   "mcp__sellable__attach_recommended_sequence",
@@ -701,9 +704,10 @@ label it explicitly as not estimated from this run.
 Before any provider prompt, search, source scout, or signal-discovery call, show
 one source-plan gate and ask for approval. Write this like a fifth grader could
 understand it: short sentences, no internal labels, and no GTM shorthand. The
-plan must be visible before the question, and this first approval only
-authorizes finding the best places to look for buyers. It does not add anyone
-to the campaign yet. The gate should say:
+order is strict: first show the plan in chat, then open the approval question.
+Do not open a generic approval first and reuse it after the plan. This first
+approval only authorizes finding the best places to look for buyers. It does
+not add anyone to the campaign yet. The gate should say:
 
 - the buyer groups or places we could check
 - the best place to start
@@ -752,9 +756,11 @@ instead and explain it in plain words once. Do not call \`search_signals\`,
 \`fetch_post_engagers\`, or provider-scoped subagents until the user approves this
 source plan or explicitly chooses a different source.
 
-If the user already answered a provider approval such as "Approve Prospeo plan",
-that answer satisfies the source-plan gate. Persist the approved provider and
-run the scouting/search next; do not ask a second source-plan approval question.
+If the user answers a provider approval such as "Approve Prospeo plan" after
+seeing the source plan, that answer satisfies the source-plan gate. Persist the
+approved provider and run the scouting/search next; do not ask a second
+source-plan approval question. A brief approval, generic "approve plan", or
+provider state from before the visible source plan does not satisfy this gate.
 
 For hiring-led campaigns, do not default to Sales Nav just because the target is
 a role search. Prospeo is the primary lane when the brief asks for companies
@@ -1103,10 +1109,9 @@ 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. 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\`. Message review requires Message Draft Builder output:
+   available. The worker and parent-thread fallback must load
+   \`mcp__sellable__get_subskill_prompt({ subskillName: "generate-messages-compact" })\`.
+   Load lazy examples/critique/revision references only when needed. Message review requires Message Draft Builder 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

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/install",
-  "version": "0.1.147",
+  "version": "0.1.149",
   "type": "module",
   "description": "One-command installer for Sellable MCP in Claude Code and Codex",
   "bin": {

package/skill-templates/create-campaign.md

@@ -36,7 +36,11 @@ allowed-tools:
   - mcp__sellable__check_rubric
   - mcp__sellable__create_campaign
   - mcp__sellable__save_rubrics
-  - mcp__sellable__wait_for_rubric_results
+  - mcp__sellable__get_campaign_table_schema
+  - mcp__sellable__select_campaign_cells
+  - mcp__sellable__queue_campaign_cells
+  - mcp__sellable__wait_for_campaign_processing
+  - mcp__sellable__revise_message_template_and_rerun
   - mcp__sellable__update_campaign_brief
   - mcp__sellable__update_campaign
   - mcp__sellable__get_campaign
@@ -52,7 +56,6 @@ allowed-tools:
   - mcp__sellable__get_table_rows
   - mcp__sellable__load_csv_linkedin_leads
   - mcp__sellable__load_csv_domains
-  - mcp__sellable__queue_cells
   - mcp__sellable__get_campaign_messages_preview
   - mcp__sellable__attach_sequence
   - mcp__sellable__attach_recommended_sequence
@@ -132,9 +135,10 @@ label it explicitly as not estimated from this run.
 Before any provider prompt, search, source scout, or signal-discovery call, show
 one source-plan gate and ask for approval. Write this like a fifth grader could
 understand it: short sentences, no internal labels, and no GTM shorthand. The
-plan must be visible before the question, and this first approval only
-authorizes finding the best places to look for buyers. It does not add anyone
-to the campaign yet. The gate should say:
+order is strict: first show the plan in chat, then open the approval question.
+Do not open a generic approval first and reuse it after the plan. This first
+approval only authorizes finding the best places to look for buyers. It does
+not add anyone to the campaign yet. The gate should say:
 
 - the buyer groups or places we could check
 - the best place to start
@@ -183,9 +187,11 @@ instead and explain it in plain words once. Do not call `search_signals`,
 `fetch_post_engagers`, or provider-scoped subagents until the user approves this
 source plan or explicitly chooses a different source.
 
-If the user already answered a provider approval such as "Approve Prospeo plan",
-that answer satisfies the source-plan gate. Persist the approved provider and
-run the scouting/search next; do not ask a second source-plan approval question.
+If the user answers a provider approval such as "Approve Prospeo plan" after
+seeing the source plan, that answer satisfies the source-plan gate. Persist the
+approved provider and run the scouting/search next; do not ask a second
+source-plan approval question. A brief approval, generic "approve plan", or
+provider state from before the visible source plan does not satisfy this gate.
 
 For hiring-led campaigns, do not default to Sales Nav just because the target is
 a role search. Prospeo is the primary lane when the brief asks for companies
@@ -748,10 +754,9 @@ 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. 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`. Message review requires Message Draft Builder output:
+   available. The worker and parent-thread fallback must load
+   `mcp__sellable__get_subskill_prompt({ subskillName: "generate-messages-compact" })`.
+   Load lazy examples/critique/revision references only when needed. Message review requires Message Draft Builder 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