@sellable/install 0.1.100 → 0.1.102

package/README.md

@@ -55,12 +55,15 @@ starts in one registry entry instead of scattered prompt edits.
 
 ## Names
 
-Use the same public entrypoint in both hosts:
+Use the same public entrypoints in both hosts:
 
 - Claude Code: `/sellable:create-campaign`
+- Claude Code: `/sellable:interview`
 - Codex: `$sellable:create-campaign`
+- Codex: `$sellable:interview`
 - Codex Desktop plugin: `sellable@sellable`
 - Codex visible skill: `Sellable Create Campaign`
+- Codex visible skill: `Sellable Identity Interview`
 - Internal MCP workflow prompt: `create-campaign-v2`
 
 Do not ask users to run `/sellable:create-campaign-v2`,

package/bin/sellable-install.mjs

@@ -134,7 +134,7 @@ Usage:
   npx -y @sellable/install@latest -- [options]
 
 Commands:
-  create                   Show how to launch the create-campaign workflow.
+  create                   Show how to launch public Sellable workflows.
   auth set <token>         Save a Sellable API token for first-run auth.
   uninstall                Remove Sellable host config and installed artifacts.
 
@@ -167,7 +167,7 @@ Auth:
 function printCreateCommandHint() {
   printBanner();
   console.log(
-    `  ${C.bold}Create campaigns from Claude Code or Codex.${C.reset}`
+    `  ${C.bold}Run Sellable from Claude Code or Codex.${C.reset}`
   );
   console.log("");
   console.log(
@@ -175,14 +175,20 @@ function printCreateCommandHint() {
   );
   console.log("");
   console.log(`   ${"═".repeat(63)}`);
-  console.log(`    ${C.bold}Start a Sellable campaign:${C.reset}`);
+  console.log(`    ${C.bold}Start a Sellable workflow:${C.reset}`);
   console.log(`   ${"═".repeat(63)}`);
   console.log("");
   console.log("");
-  printAgentBox("Using Claude Code?", "claude", "/sellable:create-campaign");
+  printAgentBox("Using Claude Code?", "claude", [
+    { label: "Campaign", command: "/sellable:create-campaign" },
+    { label: "Identity", command: "/sellable:interview" },
+  ]);
   console.log("");
   console.log("");
-  printAgentBox("Using Codex?", "codex", "$sellable:create-campaign");
+  printAgentBox("Using Codex?", "codex", [
+    { label: "Campaign", command: "$sellable:create-campaign" },
+    { label: "Identity", command: "$sellable:interview" },
+  ]);
   console.log("");
   console.log(`   ${"─".repeat(63)}`);
   console.log(`    ${C.grey}If those commands are missing, run:${C.reset}`);
@@ -640,6 +646,25 @@ data, compare sources by source volume, sampled ICP fit, activity/warmth
 signals, cleanup risk, and confidence basis. If a user asks for a forecast,
 label it explicitly as not estimated from this run.
 
+Before any provider prompt, search, source scout, or signal-discovery call,
+show a short source-plan gate and ask for approval. The gate should say:
+
+- given this campaign, the viable source options
+- the recommended first lane
+- why that lane fits the buyer, offer, and likely public activity
+- what will be tested next
+- the fallback lane if relevant posts or ICP engagement look thin
+- that approval authorizes scouting/search only, not lead import or sending
+
+If active prospects likely engage with relevant LinkedIn content, recommend
+LinkedIn post engagement / Signal Discovery and name the post themes you will
+look for. If the niche is too private, low-volume, or unlikely to have relevant
+public posts, recommend Sales Nav recent activity, broader Sales Nav role/title
+filters, or Prospeo, and explain the tradeoff. Do not call \`search_signals\`,
+\`search_sales_nav\`, \`search_prospeo\`, \`fetch_post_engagers\`, or provider-scoped
+subagents until the user approves this source plan or explicitly chooses a
+different source.
+
 For campaign-attached Signal Discovery sampling, promote/select the exact posts
 with \`select_promising_posts\` before \`fetch_post_engagers\` so the user can see
 which posts are being sampled in the watched app. The watch guide should say
@@ -937,15 +962,19 @@ updates.
    queue workflow cells, attach a sequence, or start until filter choice is
    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.
+   is synced into the campaign brief. When filters are approved, immediately
+   call \`mcp__sellable__update_campaign({ campaignId, enableICPFilters: true, currentStep: "create-icp-rubric", watchNarration })\`
+   so the watched app moves to Filter Rules while rubrics are drafted/saved.
+   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. AI Generated uses the
    product's AI-generated path and cancels or ignores the background template
    draft.
 6. The main thread owns watch navigation: use \`filter-choice\` after the 15-row
-   review batch, \`messages\` for the Use Template / AI Generated mode choice,
+   review batch, \`create-icp-rubric\` as soon as filters are approved,
+   \`messages\` for the Use Template / AI Generated mode choice,
    \`auto-execute-messaging\` for approved message work or the product's
    AI-generated path, and \`awaiting-user-greenlight\` for the final handoff.
    \`validate-sample\` is recovery/legacy only if reached.
@@ -1000,6 +1029,59 @@ If subskill lookup fails, use \`mcp__sellable__search_subskill_prompts({ query:
 `;
 }
 
+function interviewSkillMd() {
+  return `---
+name: interview
+description: Build Sellable core identity/company memory for writing workflows.
+allowed-tools:
+  - mcp__sellable__get_subskill_prompt
+  - mcp__sellable__get_subskill_asset
+  - mcp__sellable__search_subskill_prompts
+  - Read
+  - Write
+  - Edit
+  - Glob
+  - Grep
+---
+
+# Sellable Identity Interview
+
+Use this as the customer-facing entrypoint for the Sellable \`interview\`
+workflow. It builds durable identity/company memory, proof hygiene, reusable
+answers, transcript references, and anti-AI writing rules for downstream
+Sellable writing workflows.
+
+## Bootstrap
+
+MCP prompt access is required. Do not inspect repo files, run shell commands,
+use \`npm\`, \`node\`, local harness scripts, or read local prompt files to
+emulate this workflow.
+
+If the Sellable MCP prompt tools are unavailable, stop and say this is a Codex
+install/reload problem. Tell the user to run
+\`npx -y ${INSTALL_PACKAGE_SPEC} --host all\`, fully quit and reopen Codex
+Desktop, then start a new thread.
+
+## Execute Workflow
+
+1. Load the canonical prompt via
+   \`mcp__sellable__get_subskill_prompt({ subskillName: "interview" })\`.
+   If the response has \`hasMore=true\`, continue with \`nextOffset\` until
+   \`hasMore=false\`.
+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/**\`.
+
+## MCP Prompt Fallback
+
+If exact subskill lookup fails, use
+\`mcp__sellable__search_subskill_prompts({ query: "interview", includePublic: true })\`,
+then retry \`get_subskill_prompt\`.
+`;
+}
+
 function createCampaignSoulMd() {
   return `# Sellable Campaign GTM Engineer Soul
 
@@ -1189,6 +1271,12 @@ function codexPluginSkills() {
       skillMd: createCampaignSkillMd(),
       soulMd: createCampaignSoulMd(),
     },
+    {
+      dir: "sellable-interview",
+      displayName: "Sellable Identity Interview",
+      description: "Build durable identity and company memory",
+      skillMd: interviewSkillMd(),
+    },
   ];
 }
 
@@ -1795,16 +1883,21 @@ function verify(opts) {
       ".codex-plugin",
       "plugin.json"
     );
-    const skillPath = join(
-      codexHome(),
-      "plugins",
-      "cache",
-      "sellable",
-      "sellable",
-      CODEX_PLUGIN_VERSION,
-      "skills",
-      "sellable-create-campaign",
-      "SKILL.md"
+    const skillPaths = codexPluginSkills().map((skill) =>
+      join(
+        codexHome(),
+        "plugins",
+        "cache",
+        "sellable",
+        "sellable",
+        CODEX_PLUGIN_VERSION,
+        "skills",
+        skill.dir,
+        "SKILL.md"
+      )
+    );
+    const hasSkillBundles = skillPaths.every((skillPath) =>
+      existsSync(skillPath)
     );
     checks.push({
       ok: existsSync(pluginPath),
@@ -1813,10 +1906,10 @@ function verify(opts) {
         : "Codex Desktop plugin missing",
     });
     checks.push({
-      ok: existsSync(skillPath),
-      label: existsSync(skillPath)
-        ? "Codex skill bundle present"
-        : "Codex skill bundle missing",
+      ok: hasSkillBundles,
+      label: hasSkillBundles
+        ? "Codex skill bundles present"
+        : "Codex skill bundles missing",
     });
     const codexAgentPaths = codexCustomAgents().map((agent) =>
       join(codexHome(), "agents", agent.filename)
@@ -1878,10 +1971,13 @@ function visibleLen(s) {
   return s.replace(/\x1b\[[0-9;]*m/g, "").length;
 }
 
-function printAgentBox(title, terminalCmd, agentCmd) {
+function printAgentBox(title, terminalCmd, agentCommands) {
   // Inner width between │ ... │ — i.e. the printable area excluding the borders.
   const W = 58;
   const agentName = title.replace("Using ", "").replace("?", "");
+  const commands = Array.isArray(agentCommands)
+    ? agentCommands
+    : [{ label: "", command: agentCommands }];
 
   const line = (text) => {
     const pad = Math.max(0, W - visibleLen(text));
@@ -1902,7 +1998,10 @@ function printAgentBox(title, terminalCmd, agentCmd) {
   console.log(blank());
   console.log(line(` ${C.bold}STEP 2${C.reset}   Then in ${agentName}, run:`));
   console.log(blank());
-  console.log(line(`           ${C.cyan}${agentCmd}${C.reset}`));
+  for (const item of commands) {
+    const label = item.label ? `${item.label.padEnd(8)} ` : "";
+    console.log(line(`           ${label}${C.cyan}${item.command}${C.reset}`));
+  }
   console.log(blank());
   console.log(bot);
 }
@@ -2015,18 +2114,24 @@ function printNextSteps(installedHosts, authReused) {
   console.log("");
   console.log("");
   console.log(`   ${"═".repeat(63)}`);
-  console.log(`    ${C.bold}To launch your first campaign:${C.reset}`);
+  console.log(`    ${C.bold}To launch a Sellable workflow:${C.reset}`);
   console.log(`   ${"═".repeat(63)}`);
   console.log("");
   console.log("");
 
   if (hasClaude) {
-    printAgentBox("Using Claude Code?", "claude", "/sellable:create-campaign");
+    printAgentBox("Using Claude Code?", "claude", [
+      { label: "Campaign", command: "/sellable:create-campaign" },
+      { label: "Identity", command: "/sellable:interview" },
+    ]);
     console.log("");
     console.log("");
   }
   if (hasCodex) {
-    printAgentBox("Using Codex?", "codex", "$sellable:create-campaign");
+    printAgentBox("Using Codex?", "codex", [
+      { label: "Campaign", command: "$sellable:create-campaign" },
+      { label: "Identity", command: "$sellable:interview" },
+    ]);
     console.log("");
   }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/install",
-  "version": "0.1.100",
+  "version": "0.1.102",
   "type": "module",
   "description": "One-command installer for Sellable MCP in Claude Code and Codex",
   "bin": {

package/skill-templates/create-campaign.md

@@ -117,6 +117,25 @@ data, compare sources by source volume, sampled ICP fit, activity/warmth
 signals, cleanup risk, and confidence basis. If a user asks for a forecast,
 label it explicitly as not estimated from this run.
 
+Before any provider prompt, search, source scout, or signal-discovery call,
+show a short source-plan gate and ask for approval. The gate should say:
+
+- given this campaign, the viable source options
+- the recommended first lane
+- why that lane fits the buyer, offer, and likely public activity
+- what will be tested next
+- the fallback lane if relevant posts or ICP engagement look thin
+- that approval authorizes scouting/search only, not lead import or sending
+
+If active prospects likely engage with relevant LinkedIn content, recommend
+LinkedIn post engagement / Signal Discovery and name the post themes you will
+look for. If the niche is too private, low-volume, or unlikely to have relevant
+public posts, recommend Sales Nav recent activity, broader Sales Nav role/title
+filters, or Prospeo, and explain the tradeoff. Do not call `search_signals`,
+`search_sales_nav`, `search_prospeo`, `fetch_post_engagers`, or provider-scoped
+subagents until the user approves this source plan or explicitly chooses a
+different source.
+
 When the user has not supplied a source and multiple source angles are viable,
 scout those angles as independent branches when the host can actually do it:
 LinkedIn Engagement / active post engagers (internal `signal-discovery`
@@ -577,9 +596,12 @@ updates.
    queue workflow cells, attach a sequence, or start until the filter choice is
    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.
+   is synced into the campaign brief. When filters are approved, immediately
+   call `mcp__sellable__update_campaign({ campaignId, enableICPFilters: true, currentStep: "create-icp-rubric", watchNarration })`
+   so the watched app moves to Filter Rules while rubrics are drafted/saved.
+   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
@@ -588,8 +610,9 @@ updates.
    `mcp__sellable__update_campaign({ campaignId, currentStep })` before major
    visible work so the user can watch progress in the app: `create-offer` for
    the brief, `pick-provider` or the selected provider step while sourcing,
-   `filter-choice` after the 15-row review batch, `messages` for the Use
-   Template / AI Generated mode choice, `auto-execute-messaging` for approved
+   `filter-choice` after the 15-row review batch, `create-icp-rubric` as soon
+   as filters are approved, `messages` for the Use Template / AI Generated mode
+   choice, `auto-execute-messaging` for approved
    message work or the product's AI-generated path, `awaiting-user-greenlight`
    for the final handoff, `settings` for sender selection, `sequence` after
    sender attach, and `send` once the recommended sequence is attached.