fix: Added more upcoming premium features

Author: maxritter

.claude/commands/implement.md

@@ -6,6 +6,13 @@ model: opus
 
 **Execute ALL tasks continuously. NO stopping unless context manager says context is full.**
 
+## CRITICAL: No Sub-Agents During Implementation
+
+**NEVER use the Task tool or spawn sub-agents during implementation.** Sub-agents slow down execution and waste context. Instead:
+- Use direct tools: Read, Grep, Glob, Bash, Write, Edit
+- Use MCP tools directly: Exa, Cipher, Claude Context
+- If you need external docs, use `mcp__exa__get_code_context_exa()` directly
+
 ## MCP Servers - Use Throughout Implementation
 
 | Server | Purpose | When to Use |
@@ -34,6 +41,19 @@ model: opus
    - Claude Context: Related patterns and components
    - Exa: External documentation if needed
 
+## TDD is MANDATORY
+
+**No production code without a failing test first.** Follow the TDD rules in your context.
+
+| Requires TDD | Skip TDD |
+|--------------|----------|
+| New functions/methods | Documentation changes |
+| API endpoints | Config file updates |
+| Business logic | IaC code (CDK, Terraform, Pulumi) |
+| Bug fixes | Formatting/style changes |
+
+**The TDD enforcer hook will warn you if you skip this.**
+
 ## Per-Task Execution Flow
 
 **For EVERY task, follow this exact sequence:**
@@ -45,16 +65,16 @@ model: opus
    - **Side Effects:** Check for database, cache, external system impacts
 3. **Mark task as in_progress** in TodoWrite
 4. **Check diagnostics** - `mcp__ide__getDiagnostics()`
-5. **Execute TDD Flow:**
-   - Write failing test first (RED phase)
-   - Implement minimal code to pass (GREEN phase)
-   - Refactor if needed (REFACTOR phase)
+5. **Execute TDD Flow (RED → GREEN → REFACTOR):**
+   - Write failing test first, **verify it fails**
+   - Implement minimal code to pass
+   - Refactor if needed (keep tests green)
 6. **Verify tests pass** - `uv run pytest tests/path/to/test.py -v`
 7. **Run actual program** - Show real output with sample data
 8. **Check diagnostics again** - Must be zero errors
 9. **Validate Definition of Done** - Check all criteria from plan
 10. **Mark task completed** in TodoWrite
-11. **Update plan file** - Change `[ ]` to `[x]`
+11. **Update plan's Progress Tracking** - Change `[ ]` to `[x]`, update Completed/Remaining counts
 12. **Check context usage**
 
 ## Critical Task Rules
@@ -76,7 +96,15 @@ Before marking complete:
 
 ## When All Tasks Complete
 
+**⚠️ CRITICAL: Follow these steps exactly:**
+
 1. Quick verification: `mcp__ide__getDiagnostics()` and `uv run pytest`
 2. Store learnings in Cipher
-3. Inform user: "✅ All tasks complete. Run `/verify`"
-4. DO NOT run /verify yourself
+3. **MANDATORY: Update plan status to COMPLETE**
+   ```
+   Edit the plan file and change the Status line:
+   Status: PENDING  →  Status: COMPLETE
+   ```
+   This triggers the Rules Supervisor on your next response.
+4. Inform user: "✅ All tasks complete. Run `/verify`"
+5. DO NOT run /verify yourself

.claude/commands/plan.md

@@ -223,7 +223,12 @@ Questions:
 > **IMPORTANT:** Start with fresh context. Run `/clear` before `/implement`.
 
 Created: [Date]
-Status: PENDING APPROVAL
+Status: PENDING
+
+> **Status Lifecycle:** PENDING → COMPLETE → VERIFIED
+> - PENDING: Initial state, awaiting implementation
+> - COMPLETE: All tasks implemented (set by /implement)
+> - VERIFIED: Rules supervisor passed (set automatically)
 
 ## Summary
 **Goal:** [One sentence describing what this builds]
@@ -253,10 +258,14 @@ Status: PENDING APPROVAL
 - [Integration points or dependencies]
 
 ## Progress Tracking
+
+**MANDATORY: Update this checklist as tasks complete. Change `[ ]` to `[x]`.**
+
 - [ ] Task 1: [Brief summary]
 - [ ] Task 2: [Brief summary]
+- [ ] ...
 
-**Total Tasks:** [Number] (Max: 12)
+**Total Tasks:** [Number] | **Completed:** 0 | **Remaining:** [Number]
 
 ## Implementation Tasks
 

.claude/commands/verify.md

@@ -131,4 +131,15 @@ newman run postman/collections/api-tests.json \
 - Code review checklist complete
 - No breaking changes in call chains
 
+### Step 10: Update Plan Status
+
+**When all verification passes:**
+
+1. **MANDATORY: Update plan status to VERIFIED**
+   ```
+   Edit the plan file and change the Status line:
+   Status: REVIEWED  →  Status: VERIFIED
+   ```
+2. Inform user: "✅ Verification complete. Plan status updated to VERIFIED."
+
 **Fix immediately | Test after each fix | No "should work" - verify it works | Keep fixing until green**

.claude/settings.local.template.json

@@ -61,6 +61,17 @@
   "enableAllProjectMcpServers": true,
   "enabledMcpjsonServers": ["exa", "claude-context", "cipher", "mcp-funnel"],
   "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "{{PROJECT_DIR}}/.claude/bin/ccp-premium tdd-enforcer"
+          }
+        ]
+      }
+    ],
     "PostToolUse": [
       {
         "matcher": "Write|Edit|MultiEdit",
@@ -84,6 +95,17 @@
           }
         ]
       }
+    ],
+    "Stop": [
+      {
+        "matcher": ".*",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "{{PROJECT_DIR}}/.claude/bin/ccp-premium rules-supervisor-hook"
+          }
+        ]
+      }
     ]
   },
   "statusLine": {

.github/workflows/release.yml

@@ -56,6 +56,7 @@ jobs:
 
       - name: Decrypt premium folder
         env:
+          # yamllint disable-line rule:truthy
           GIT_CRYPT_KEY: ${{ secrets.GIT_CRYPT_KEY }}
         run: |
           echo "$GIT_CRYPT_KEY" | base64 -d > /tmp/git-crypt.key
@@ -74,7 +75,7 @@ jobs:
               apt-get install -y python3 python3-pip && \
               python3 -m pip install --upgrade pip && \
               python3 -m pip install pyinstaller && \
-              python3 build.py
+              python3 build_cicd.py
             "
 
       - name: Upload artifact
@@ -108,6 +109,7 @@ jobs:
 
       - name: Decrypt premium folder
         env:
+          # yamllint disable-line rule:truthy
           GIT_CRYPT_KEY: ${{ secrets.GIT_CRYPT_KEY }}
         run: |
           echo "$GIT_CRYPT_KEY" | base64 -d > /tmp/git-crypt.key
@@ -124,7 +126,7 @@ jobs:
         run: |
           python -m pip install --upgrade pip
           python -m pip install pyinstaller
-          python build.py
+          python build_cicd.py
 
       - name: Upload artifact
         uses: actions/upload-artifact@v5

README.md

@@ -13,7 +13,7 @@ Start shipping systematically with Spec-Driven Development, Skills, TDD, Semanti
 ![TDD](https://img.shields.io/badge/TDD-Test--Driven--Development-green.svg)
 [![PRs Welcome](https://img.shields.io/badge/PRs-Welcome-brightgreen.svg)](http://makeapullrequest.com)
 
-#### [⭐ Star this repo](https://github.com/maxritter/claude-codepro) • [🎓 Join the Academy](https://www.claude-code.pro) • [📦 Releases](https://github.com/maxritter/claude-codepro/releases)
+#### [⭐ Star this repo](https://github.com/maxritter/claude-codepro) • [💎 Premium Features (Coming Soon!)](https://www.claude-code.pro)
 
 </div>
 
@@ -107,35 +107,25 @@ The installer will guide you through the setup process with interactive prompts.
 
 Add custom rules by creating `.md` files in `.claude/rules/custom/` - they'll be included automatically on next `ccp` start.
 
-## ⚖️ What Makes This Different
+---
 
-**Compared to Other Spec-Driven Frameworks (SpecKit, AgentOS, OpenSpec):**
+## 💎 Premium Features (Coming Soon!)
 
-- 📦 **One-Line Installation** - No containers, no complex setup, just one curl command
-- 🤓 **Language Agnostic** - Works with Python, Node.js, Go, Rust, or any language
-- 💾 **Persistent Memory** - Cross-session memory maintains knowledge between resets
-- ⚡ **Token-Optimized** - No tokens wasted during too complex planning, just works
-- ✅ **Production-Grade** - Actively used in client and enterprise projects
-- 📝 **Enforced TDD** - Code written before tests gets deleted automatically
-- 💯 **Real Verification** - Must show actual outputs based on tests, not assumptions
-- 🛠️ **Complete Ecosystem** - Skills, MCP servers, testing tools are integrated and configured
+Take your Claude Code workflow to the next level with these powerful premium features:
 
----
+### 🔍 AI Rules Supervisor
 
-## 👥 Who This Is For
+AI-powered session analysis using Gemini 3.0 Pro that checks your entire coding session against project rules. When violations are found, Claude Code is automatically instructed to fix them - ensuring full compliance before you finish.
 
-- **Professional Developers** - Shipping to production with quality standards
-- **Solo Builders** - Managing complex features without losing context
-- **Engineering Teams** - Ensuring consistent TDD and code quality
-- **Frustrated Coders** - Tired of half-tested, "should work" implementations
+### 🧪 Automated TDD Enforcer
 
----
+Automatically enforces Test-Driven Development by blocking code edits when no failing tests exist. Ensures you always write tests first, with a smart override mechanism for edge cases.
 
-## 🎓 Claude CodePro Academy Coming Soon!
+### 📊 Intelligent Context Monitor
 
-If you want to dive deeper into the setup and advanced usage of Claude CodePro, check out the upcoming academy that starts with 10 comprehensive modules where we do a deep-dive into all important topics:
+Automatic context management that kicks in when you reach 100% context usage. Claude CodePro automatically stores learnings in cross-session memory and updates the plan file, so you can seamlessly continue after `/clear` without losing progress.
 
-➡️ **[www.claude-code.pro](https://www.claude-code.pro)**
+➡️ **[Coming soon at www.claude-code.pro](https://www.claude-code.pro)**
 
 ---