learnship 1.9.20 → 1.9.21

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": "1.9.20",
+  "version": "1.9.21",
   "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": "1.9.20",
+  "version": "1.9.21",
   "logo": "assets/logo.png",
   "author": {
     "name": "Favio Vazquez",

package/cursor-rules/learnship.mdc

@@ -5,6 +5,54 @@ description: Activate learnship agentic engineering workflows — structured pha
 
 You are working inside a project that uses **learnship** — a multi-platform agentic engineering system for building real products with spec-driven workflows, integrated learning, and impeccable design.
 
+## Mandatory Gate — No Project, No Work
+
+**Before responding to any user message, check:**
+
+```
+Does .planning/PROJECT.md exist?
+```
+
+- **No** → The project has not been initialized. **Do NOT implement anything.** Tell the user:
+
+  > "This project hasn't been set up with learnship yet. Run `/new-project` to initialize it — that takes about 10 minutes and sets up the spec, roadmap, and phase structure before any code gets written.
+  >
+  > This is not optional: working without a spec means building the wrong thing. `/new-project` first."
+
+  Then stop. Do not offer to help with the task. Do not say "but I can also just fix it directly." Wait for the user to run `/new-project`.
+
+- **Yes** → Continue normally. Apply the workflow routing logic.
+
+**This gate applies to ALL messages** — bug reports, feature requests, "quick fixes", detailed specs, anything. The only exception: if the user is currently mid-ceremony in `/new-project` (i.e., they are answering your questions), their messages are workflow answers, not tasks to route.
+
+## New Project Ceremony — /new-project
+
+When the user runs `/new-project`, execute these **9 mandatory steps in order**. Do not skip, defer, or abbreviate any step.
+
+**Checklist (check off as you go):**
+- [ ] Step 1 — Setup & codebase check
+- [ ] Step 1b — Existing codebase scan (if applicable)
+- [ ] Step 2 — Configuration questions
+- [ ] Step 3 — Deep questioning (4 exchanges minimum)
+- [ ] Step 4 — Write and confirm PROJECT.md
+- [ ] Step 5 — Research decision (ask user, wait for answer)
+- [ ] Step 6 — Define requirements (interactive)
+- [ ] Step 7 — Create and approve roadmap
+- [ ] Step 8 — Generate AGENTS.md ← **mandatory, never skip**
+- [ ] Step 9 — Done banner + next step
+
+**Critical gates:**
+
+1. **Exchange 1 answer does NOT skip Exchanges 2–4.** No matter how detailed the user's answer to "What do you want to build?" — it is raw material for follow-ups, not a replacement. You MUST still ask Exchanges 2, 3, and 4.
+
+2. **After Step 4 (PROJECT.md confirmed):** Do NOT write REQUIREMENTS.md or ROADMAP.md. First ask: "Before I write the requirements — do you want me to research the domain ecosystem first?" Wait for reply.
+
+3. **After Step 7 (roadmap approved):** Do NOT display the done banner or suggest next steps. Generate AGENTS.md (Step 8) first.
+
+4. **Step 9 next step is `/discuss-phase 1` — not `/plan-phase`.** The phase loop is: `discuss-phase` → `plan-phase` → `execute-phase` → `verify-work`. `discuss-phase` is mandatory first — it writes the CONTEXT.md that planning depends on.
+
+**Routing protocol suspended during `/new-project`.** Every user message while the ceremony is in progress is an answer to a workflow question, not a task to route.
+
 ## Core Workflows
 
 Suggest the appropriate workflow slash command when relevant:

package/gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "learnship",
-  "version": "1.9.20",
+  "version": "1.9.21",
   "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

@@ -6,6 +6,19 @@ description: Initialize a new project — questioning → research → requireme
 
 Initialize a new project with full context gathering, optional research, requirements scoping, and roadmap creation. This is the most leveraged moment in any project — deep questioning now means better plans, better execution, better outcomes.
 
+> **This workflow has 9 mandatory steps. You must complete every step in order. Do not skip, defer, or abbreviate any step. Check each one off as you complete it:**
+>
+> - [ ] Step 1 — Setup & codebase check
+> - [ ] Step 1b — Existing codebase scan (if applicable)
+> - [ ] Step 2 — Configuration questions
+> - [ ] Step 3 — Deep questioning (4 exchanges)
+> - [ ] Step 4 — Write and confirm PROJECT.md
+> - [ ] Step 5 — Research decision (ask user, wait for answer)
+> - [ ] Step 6 — Define requirements (interactive)
+> - [ ] Step 7 — Create and approve roadmap
+> - [ ] Step 8 — Generate AGENTS.md ← **mandatory, never skip**
+> - [ ] Step 9 — Done banner + next step
+
 ## Step 1: Setup
 
 <!-- LEARNSHIP_PLATFORM_LABEL -->
@@ -208,15 +221,15 @@ If user requests changes: update PROJECT.md, show the full file again, re-ask th
 git add .planning/PROJECT.md && git commit -m "docs: initialize project"
 ```
 
-> 🛑 STOP. Do not proceed to Step 5 until you have asked the research question below AND received the user's explicit answer to it.
+> 🛑 STOP — **Step 4 complete. You MUST now ask the research question (Step 5) before writing any other file.** Do not write REQUIREMENTS.md. Do not write ROADMAP.md. Do not proceed to any other step. The next action is to ask the user exactly one question: whether to research the domain first.
 
 ## Step 5: Research Decision
 
-Ask: "Research the domain ecosystem before defining requirements?"
+Ask: **"Before I write the requirements — do you want me to research the domain ecosystem first?"**
 - **Research first** (recommended) — Discover standard stacks, expected features, architecture patterns
 - **Skip research** — I know this domain well, go straight to requirements
 
-> 🛑 STOP. Wait for the user's explicit choice before continuing. Do not default to "Research first" — wait for the user's actual reply.
+> 🛑 STOP. Wait for the user's explicit choice. Do not default to either option. Do not write REQUIREMENTS.md yet. Do not proceed until the user replies.
 
 **If Research first:**
 
@@ -325,6 +338,8 @@ Ask for approval:
 git add .planning/ROADMAP.md .planning/STATE.md .planning/REQUIREMENTS.md && git commit -m "docs: create roadmap ([N] phases)"
 ```
 
+> 🛑 STOP — **Step 7 complete. You MUST now generate AGENTS.md (Step 8) before anything else.** Do not display the done banner. Do not suggest next steps. Do not end the workflow. The roadmap is approved — AGENTS.md is next.
+
 ## Step 8: Generate AGENTS.md
 
 > **🔴 MANDATORY — This step must always be completed. Do not skip it, do not defer it, do not move to Step 9 without writing AGENTS.md to the project root. AGENTS.md is the persistent memory file that every future session depends on.**
@@ -378,7 +393,10 @@ Files created:
 - .planning/config.json
 [- .planning/research/ (if research was run)]
 
-▶ Next: discuss-phase 1 → plan-phase 1 → execute-phase 1
+▶ Next: `/discuss-phase 1` — **start here, not `/plan-phase`**
+
+The phase loop is: `discuss-phase` → `plan-phase` → `execute-phase` → `verify-work`
+`discuss-phase` is mandatory before planning — it captures your intent and writes the CONTEXT.md that plan-phase depends on. Skipping it means planning without context.
 
 > **Platform detected:** `[PLATFORM]` — parallelization is `[true/false]`
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "learnship",
-  "version": "1.9.20",
+  "version": "1.9.21",
   "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",