learnship 1.9.11 → 1.9.12

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "learnship",
   "description": "Agentic engineering done right — 42 structured workflows, persistent memory across sessions, integrated learning partner, and impeccable UI design system. Works with Claude Code, Windsurf, Cursor, Gemini CLI, OpenCode, and Codex.",
-  "version": "1.9.11",
+  "version": "1.9.12",
   "author": {
     "name": "Favio Vazquez",
     "email": "favio.vazquezp@gmail.com"

package/.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "learnship",
   "displayName": "learnship",
   "description": "Agentic engineering done right — 42 structured workflows, persistent memory across sessions, integrated learning partner, and impeccable UI design system.",
-  "version": "1.9.11",
+  "version": "1.9.12",
   "logo": "assets/logo.png",
   "author": {
     "name": "Favio Vazquez",

package/gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "learnship",
-  "version": "1.9.11",
+  "version": "1.9.12",
   "description": "Agentic engineering done right — 42 structured workflows, persistent memory across sessions, integrated learning partner, and impeccable UI design system.",
   "author": "Favio Vazquez",
   "homepage": "https://faviovazquez.github.io/learnship/",

package/learnship/workflows/new-project.md

@@ -132,7 +132,9 @@ Wait for their response. Then follow the thread — each answer opens new questi
 
 Use the questioning techniques from `@./references/questioning.md`.
 
-When you have enough to write a clear PROJECT.md, ask:
+> **⚠ MANDATORY MINIMUM — Do not ask to create PROJECT.md until you have asked AT LEAST 3 follow-up questions after the user's first answer. No matter how detailed the first response is, one answer is never enough. A single detailed prompt is not a project definition — it is a starting point. Ask follow-ups about: who uses it, what the edge cases are, what success looks like, what they've already tried, what must NOT happen. Only after at least 3 follow-ups have been exchanged may you proceed.**
+
+When you have enough depth (minimum 3 follow-ups exchanged), ask:
 
 "I think I understand what you're after. Ready to create PROJECT.md, or do you want to explore more?"
 
@@ -145,6 +147,15 @@ Loop until ready.
 
 Synthesize all gathered context into `.planning/PROJECT.md` using `@./templates/project.md` as the template.
 
+Once written, **show the user the full contents of `.planning/PROJECT.md`** and ask:
+
+"Here's the PROJECT.md I've written from our conversation. Does this accurately capture what you want to build, or should we adjust anything?"
+
+- **Looks good** → continue
+- **Needs changes** → ask what to adjust, update PROJECT.md, re-present, loop until confirmed
+
+> **⚠ STOP — do not proceed to Step 5 until the user has explicitly confirmed PROJECT.md. This is a mandatory gate. Do not interpret silence or a brief "ok" as confirmation — wait for a clear positive signal.**
+
 **If `commit_mode` is `auto`:**
 ```bash
 git add .planning/PROJECT.md && git commit -m "docs: initialize project"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "learnship",
-  "version": "1.9.11",
+  "version": "1.9.12",
   "description": "Learn as you build. Build with intent. — A multi-platform agentic engineering system for Windsurf, Claude Code, Cursor, OpenCode, Gemini CLI, and Codex: spec-driven workflows, integrated learning, and production-grade design.",
   "keywords": [
     "agentic",