@sellable/install 0.1.76 → 0.1.78

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

@@ -20,11 +20,11 @@ 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 Fast Path below. Do not load the full
-   long-form `generate-messages` subskill in the normal path. Load it only when
-   the fast path is missing a needed campaign-specific rule, the user explicitly
-   asks for deep calibration, or the first fast-path draft fails quality gates
-   and no local reference explains how to repair it.
+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:
 
@@ -46,8 +46,8 @@ Do not write or modify:
 
 Process:
 
-1. Run the embedded fast-path workflow in dry mode from the approved brief,
-   lead-review source decision, and `lead-sample.json`.
+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,
@@ -69,7 +69,8 @@ Process:
 Return a concise final status with:
 
 - artifacts written
-- whether embedded fast-path rules were used or the full fallback was needed
+- 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
@@ -78,12 +79,12 @@ Return a concise final status with:
 Quality bar:
 
 - Do not synthesize a lightweight message from general knowledge. The artifact
-  must prove the embedded fast-path workflow ran.
+  must prove the embedded message-review safety-gate workflow ran.
 - 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 Fast Path
+## 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

package/bin/sellable-install.mjs

@@ -843,15 +843,21 @@ updates.
 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-fast-path.md" })\`.
+   \`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.
    Do not synthesize \`message-validation.md\` from the brief, lead review, or
    general knowledge.
-5. Treat message quality as the gate before minting. Do not create a campaign,
-   show a commit gate, or mint anything until \`message-validation.md\` proves
-   the fast-path message workflow ran and \`message-review.md\` recommends
-   \`approve-message\` against the gold-standard rules.
-6. Do not create or mutate the live campaign until the approval gate returns
-   \`approve\`.
+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
+   \`message-validation.md\` proves the message-review safety-gate workflow ran,
+   \`message-review.md\` approves the template, rubrics are saved, and the
+   approved message set is synced into the campaign brief.
+6. Keep \`selectedLeadListId\` as the source list and \`workflowTableId\` as the
+   campaign table. Do not use disk files as the post-mint source of truth.
 7. Do not ask the user to run another command.
 
 ## Fallback
@@ -1121,15 +1127,24 @@ function agentTemplateRoot() {
 
 function loadCanonicalAgents() {
   const root = agentTemplateRoot();
-  const registry = JSON.parse(readFileSync(join(root, "registry.json"), "utf8"));
+  const registry = JSON.parse(
+    readFileSync(join(root, "registry.json"), "utf8")
+  );
   if (!Array.isArray(registry.agents)) {
     throw new Error("Sellable agent registry is missing agents array.");
   }
 
   return registry.agents.map((agent) => {
     const promptPath = join(root, agent.promptFile || "");
-    if (!agent.id || !agent.name || !agent.promptFile || !existsSync(promptPath)) {
-      throw new Error(`Invalid Sellable agent registry entry: ${agent.id || "unknown"}`);
+    if (
+      !agent.id ||
+      !agent.name ||
+      !agent.promptFile ||
+      !existsSync(promptPath)
+    ) {
+      throw new Error(
+        `Invalid Sellable agent registry entry: ${agent.id || "unknown"}`
+      );
     }
     if (agent.codex?.name && agent.codex.name !== agent.name) {
       throw new Error(
@@ -1165,6 +1180,15 @@ function legacyClaudeCustomAgents() {
   return loadCanonicalAgents().flatMap((agent) => agent.legacy?.claude || []);
 }
 
+function legacyClaudeCommands() {
+  return [
+    {
+      name: "sellable-create-campaign",
+      filename: join("sellable", "create-campaign.md"),
+    },
+  ];
+}
+
 function tomlArray(values) {
   return `[${values.map((value) => quoteToml(value)).join(", ")}]`;
 }
@@ -1240,7 +1264,9 @@ function writeCodexCustomAgents(home, opts) {
   }
   for (const agent of legacyCodexCustomAgents()) {
     const legacyPath = join(home, "agents", agent.filename);
-    logVerbose(`${C.grey}Removing legacy Codex scout agent ${legacyPath}${C.reset}`);
+    logVerbose(
+      `${C.grey}Removing legacy Codex scout agent ${legacyPath}${C.reset}`
+    );
     if (!opts.dryRun) rmSync(legacyPath, { force: true });
   }
 }
@@ -1256,9 +1282,22 @@ function writeClaudeCustomAgents(opts) {
   }
   for (const agent of legacyClaudeCustomAgents()) {
     const legacyPath = join(home, "agents", agent.filename);
-    logVerbose(`${C.grey}Removing legacy Claude scout agent ${legacyPath}${C.reset}`);
+    logVerbose(
+      `${C.grey}Removing legacy Claude scout agent ${legacyPath}${C.reset}`
+    );
     if (!opts.dryRun) rmSync(legacyPath, { force: true });
   }
+  removeLegacyClaudeCommands(home, opts);
+}
+
+function removeLegacyClaudeCommands(home, opts) {
+  for (const command of legacyClaudeCommands()) {
+    const commandPath = join(home, "commands", command.filename);
+    logVerbose(
+      `${C.grey}Removing legacy Claude command ${commandPath}${C.reset}`
+    );
+    if (!opts.dryRun) rmSync(commandPath, { force: true });
+  }
 }
 
 function installCodexDesktopPlugin(opts) {
@@ -1396,8 +1435,12 @@ config_file = ${quoteToml(join(home, "agents", agent.filename))}`
     logVerbose(
       `${C.grey}+ enable [features].default_mode_request_user_input in ${configPath}${C.reset}`
     );
-    logVerbose(`${C.grey}+ write Codex custom agents in ${home}/agents${C.reset}`);
-    logVerbose(`${C.grey}+ register Codex custom agents in ${configPath}${C.reset}`);
+    logVerbose(
+      `${C.grey}+ write Codex custom agents in ${home}/agents${C.reset}`
+    );
+    logVerbose(
+      `${C.grey}+ register Codex custom agents in ${configPath}${C.reset}`
+    );
   }
 
   return {
@@ -1607,6 +1650,23 @@ function verify(opts) {
         ? "Claude scout MCP tool allowlists present"
         : "Claude scout MCP tool allowlists missing",
     });
+    const legacyClaudePaths = [
+      ...legacyClaudeCustomAgents().map((agent) =>
+        join(claudeHome(), "agents", agent.filename)
+      ),
+      ...legacyClaudeCommands().map((command) =>
+        join(claudeHome(), "commands", command.filename)
+      ),
+    ];
+    const hasNoLegacyClaudeArtifacts = legacyClaudePaths.every(
+      (artifactPath) => !existsSync(artifactPath)
+    );
+    checks.push({
+      ok: hasNoLegacyClaudeArtifacts,
+      label: hasNoLegacyClaudeArtifacts
+        ? "Legacy Claude Sellable host artifacts cleaned"
+        : "Legacy Claude Sellable host artifacts still present",
+    });
   }
   if (opts.host === "codex" || opts.host === "all") {
     checks.push({
@@ -1671,6 +1731,19 @@ function verify(opts) {
         ? "Codex custom scout agents registered"
         : "Codex custom scout agents unregistered",
     });
+    const hasNoLegacyCodexAgents = legacyCodexCustomAgents().every((agent) => {
+      const agentPath = join(codexHome(), "agents", agent.filename);
+      return (
+        !existsSync(agentPath) &&
+        !configContent.includes(`[agents.${agent.name}]`)
+      );
+    });
+    checks.push({
+      ok: hasNoLegacyCodexAgents,
+      label: hasNoLegacyCodexAgents
+        ? "Legacy Codex custom scout agents cleaned"
+        : "Legacy Codex custom scout agents still present",
+    });
     const hasFlag = configContent.includes(
       "default_mode_request_user_input = true"
     );
@@ -1899,7 +1972,10 @@ function runUninstall() {
       after = removeTomlSection(after, "marketplaces.sellable");
       after = removeTomlSection(after, 'plugins."sellable@sellable"');
       after = removeTomlSection(after, 'plugins."sellable@sellable-local"');
-      for (const agent of [...codexCustomAgents(), ...legacyCodexCustomAgents()]) {
+      for (const agent of [
+        ...codexCustomAgents(),
+        ...legacyCodexCustomAgents(),
+      ]) {
         after = removeTomlSection(after, `agents.${agent.name}`);
       }
       // Collapse 3+ blank lines that the removals may leave behind.
@@ -1949,7 +2025,10 @@ function runUninstall() {
     skipped.push(`Claude Code CLI not found`);
   }
 
-  for (const agent of [...claudeCustomAgents(), ...legacyClaudeCustomAgents()]) {
+  for (const agent of [
+    ...claudeCustomAgents(),
+    ...legacyClaudeCustomAgents(),
+  ]) {
     const agentPath = join(claudeHome(), "agents", agent.filename);
     if (!existsSync(agentPath)) continue;
     try {
@@ -1961,6 +2040,18 @@ function runUninstall() {
       );
     }
   }
+  for (const command of legacyClaudeCommands()) {
+    const commandPath = join(claudeHome(), "commands", command.filename);
+    if (!existsSync(commandPath)) continue;
+    try {
+      rmSync(commandPath, { force: true });
+      removed.push(`${commandPath}`);
+    } catch (err) {
+      console.log(
+        `  ${C.yellow}!${C.reset} Could not remove ${commandPath}: ${err instanceof Error ? err.message : String(err)}`
+      );
+    }
+  }
 
   // 3) Surgical removal of Sellable-installed artifacts inside ~/.sellable/
   const sellableDir = join(homedir(), ".sellable");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/install",
-  "version": "0.1.76",
+  "version": "0.1.78",
   "type": "module",
   "description": "One-command installer for Sellable MCP in Claude Code and Codex",
   "bin": {

package/skill-templates/create-campaign.md

@@ -490,14 +490,17 @@ updates.
 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-fast-path.md" })`.
+   `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.
    Do not synthesize `message-validation.md` from the brief, lead review, or
    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
-   `message-validation.md` proves the fast-path message workflow ran,
+   `message-validation.md` proves the message-review safety-gate workflow ran,
    `message-review.md` approves the template, rubrics are saved, and the
    approved message set is synced into the campaign brief.
 6. Keep `selectedLeadListId` as the source list and `workflowTableId` as the