@sellable/mcp 0.1.6 → 0.1.7

package/README.md

@@ -83,14 +83,14 @@ The token is provided when you generate it. Use `list_workspaces` +
 For customer/package installs, use the public installer:
 
 ```bash
-npx -y @sellable/install@0.1.6 --host codex --token skt_live_your_token_here --workspace-id your_workspace_id
+npx -y @sellable/install@0.1.7 --host codex --token skt_live_your_token_here --workspace-id your_workspace_id
 ```
 
 If you already have `~/.sellable/config.json`, rerun/verify without rewriting
 auth:
 
 ```bash
-npx -y @sellable/install@0.1.6 --host codex
+npx -y @sellable/install@0.1.7 --host codex
 sellable --verify-only --host codex
 ```
 
@@ -110,6 +110,31 @@ thread and select `Sellable Create Campaign`, or invoke
 The skill being visible only proves skill discovery; the plugin is what mounts
 the Sellable MCP tools for Codex Desktop.
 
+## Public Names And Host Commands
+
+Use these names consistently:
+
+- Claude Code command: `/sellable:create-campaign`
+- Codex command: `$sellable:create-campaign`
+- Codex Desktop plugin: `sellable@sellable`
+- Codex visible skill: `Sellable Create Campaign`
+- Codex skill frontmatter name: `create-campaign`
+- MCP server name: `sellable`
+- Internal workflow prompt: `create-campaign-v2`
+
+Never tell users to run `/sellable:create-campaign-v2`,
+`$sellable:create-campaign-v2`, or `$sellable:sellable:create-campaign`.
+`create-campaign-v2` is an internal MCP subskill loaded by
+`get_subskill_prompt({ subskillName: "create-campaign-v2" })`.
+
+## Structured Question Parity
+
+Claude Code should ask intake and approval gates with `AskUserQuestion`.
+Codex should ask them with `request_user_input` when it is exposed in an
+interactive Plan/collaboration-mode session. `codex exec` is non-interactive
+and cannot show the structured questionnaire UI, so it is only useful for smoke
+checks that stop before human intake/approval.
+
 ## Usage
 
 ### From Sellable UI

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.6",
+  "version": "0.1.7",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

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

@@ -76,11 +76,15 @@ Validated draft directory:
   compatibility run where all upstream artifacts already exist.
 - Use the host-native structured question gate whenever it is exposed. In
   Claude Code, this is `AskUserQuestion`. In Codex, this is
-  `request_user_input`. Treat them as equivalent approval/intake gates and
-  persist the same draft artifacts after the user answers. If the session is
-  non-interactive or the host does not expose either structured question tool,
-  fall back to a normal chat question with the exact same choices and make the
-  fallback explicit to the user.
+  `request_user_input` (usually exposed in Plan/collaboration-mode interactive
+  sessions, not `codex exec`). Treat them as equivalent approval/intake gates and
+  persist the same draft artifacts after the user answers. If an interactive
+  Codex session does not expose `request_user_input`, do not silently degrade to
+  a plain chat question; stop and tell the user: `Codex has not exposed
+request_user_input in this session. Switch to Plan mode / collaboration mode
+for the structured questionnaire, then rerun $sellable:create-campaign.` In
+  non-interactive `codex exec`, structured user input is unavailable by design;
+  ask in chat only when the run is explicitly a non-interactive smoke/rehearsal.
 - Fast Intake Mode is mandatory for hosted/rehearsal net-new runs. Ask the
   first founder strategy/source question packet in under 60 seconds. Before
   that first packet, the first assistant turn may only call

package/skills/create-campaign-v2/references/approval-gate-framing.md

@@ -101,10 +101,13 @@ Status: approval-packet
 The same assistant turn must then use the host-native structured question gate
 with the six commit choices. In Claude Code, call `AskUserQuestion`. In Codex,
 call `request_user_input` when that tool is available. Do not show a standalone
-commit-gate question in a later turn without the approval packet above it. If
-the session is non-interactive or neither structured question tool is exposed,
-fall back to a normal chat question with the exact same choices and say that the
-structured gate is unavailable in this session.
+commit-gate question in a later turn without the approval packet above it. If an
+interactive Codex session does not expose `request_user_input`, do not silently
+fall back to chat. Stop and tell the user to switch to Plan mode /
+collaboration mode so Codex exposes the structured questionnaire tool, then
+rerun `$sellable:create-campaign`. A normal chat question is acceptable only for
+non-interactive `codex exec` smoke/rehearsal runs because structured user input
+is unavailable by design there.
 
 The packet should read like an AI GTM engineer explaining the campaign, not an
 internal validation report. Start with the practical direction in plain