Remove mem0/ACE/Curator, fix hook errors, simplify map-review

.claude-plugin/PLUGIN.md

@@ -4,37 +4,36 @@ Official Claude Code plugin for MAP Framework - Modular Agentic Planner with cog
 
 ## What is MAP Framework?
 
-MAP (Modular Agentic Planner) is a cognitive architecture that orchestrates 12 specialized agents to improve code quality through systematic validation and iterative refinement.
+MAP (Modular Agentic Planner) is a cognitive architecture that orchestrates 11 specialized agents to improve code quality through systematic validation and iterative refinement.
 
 **Based on research:**
 - [MAP Paper - Nature Communications (2025)](https://github.com/Shanka123/MAP) — 74% improvement in planning tasks
-- [ACE Paper - arXiv:2510.04618v1](https://arxiv.org/abs/2510.04618v1) — continuous learning from experience
+
 
 ## Features
 
-### 12 Specialized Agents
+### 11 Specialized Agents
 
 1. **TaskDecomposer** — breaks goals into atomic subtasks
 2. **Actor** — generates code and solutions
 3. **Monitor** — validates quality, security, correctness
 4. **Predictor** — analyzes change impact across codebase
 5. **Evaluator** — scores solution quality (functionality, security, testability)
 6. **Reflector** — extracts lessons from successes and failures
-7. **Curator** — manages knowledge base (playbook)
-8. **DocumentationReviewer** — checks documentation completeness
-9. **Debate-Arbiter** — cross-evaluates variants with reasoning (Opus)
-10. **Synthesizer** — merges multiple variants (Self-MoA)
-11. **Research-Agent** — isolated codebase research
-12. **Final-Verifier** — adversarial verification (Ralph Loop)
+7. **DocumentationReviewer** — checks documentation completeness
+8. **Debate-Arbiter** — cross-evaluates variants with reasoning (Opus)
+9. **Synthesizer** — merges multiple variants (Self-MoA)
+10. **Research-Agent** — isolated codebase research
+11. **Final-Verifier** — adversarial verification (Ralph Loop)
 
 ### Claude Code Integration
 
 **5 Automated Hooks:**
 - `validate-agent-templates` — prevents accidental removal of template variables
-- `auto-store-knowledge` — automatically saves successful patterns
 - `enrich-context` — enriches prompts with relevant knowledge
-- `session-init` — loads ACE playbook at session start
+- `session-init` — loads workflow context at session start
 - `track-metrics` — tracks agent performance
+- `workflow-gate` — enforces workflow step sequencing
 
 **10 Slash Commands:**
 - `/map-efficient` — implement features, refactor code, complex tasks with full MAP workflow
@@ -48,13 +47,6 @@ MAP (Modular Agentic Planner) is a cognitive architecture that orchestrates 12 s
 - `/map-resume` — resume interrupted workflows
 - `/map-learn` — extract and preserve lessons
 
-### ACE Learning System
-
-- **Persistent Knowledge** — solutions saved and reused via mem0 MCP
-- **Semantic Search** — find patterns by meaning (optional)
-- **Quality Tracking** — monitor pattern effectiveness
-- **Continuous Learning** — each workflow improves future ones
-
 ### Cost Optimization
 
 Intelligent model selection per agent:
@@ -95,11 +87,9 @@ cp map-framework/.claude/settings.hooks.json your-project/.claude/
 ## Requirements
 
 - **Claude Code CLI** — installed and configured
-- **MCP Servers** (essential):
-  - `claude-reviewer` — professional code review
-  - `sequential-thinking` — chain-of-thought reasoning
 
 **Recommended MCP Servers:**
+- `sequential-thinking` — chain-of-thought reasoning
 - `context7` — library documentation
 - `deepwiki` — GitHub repository analysis
 
@@ -146,8 +136,8 @@ cp map-framework/.claude/settings.hooks.json your-project/.claude/
     │  └──────────┬───────────┘       │
     │             │                    │
     │  ┌──────────▼───────────┐       │
-    │  │ REFLECTOR → CURATOR  │       │
-    │  │ (learn → knowledge)  │       │
+    │  │ REFLECTOR             │       │
+    │  │ (learn → patterns)   │       │
     │  └──────────────────────┘       │
     └──────────────────────────────────┘
 ```

.claude-plugin/marketplace.json

@@ -18,7 +18,6 @@
       "repository": "https://github.com/azalio/map-framework",
       "keywords": [
         "MAP",
-        "ACE",
         "cognitive-architecture",
         "planning",
         "agents",
@@ -32,8 +31,7 @@
         "development"
       ],
       "features": [
-        "12 specialized agents (TaskDecomposer, Actor, Monitor, Predictor, Evaluator, Reflector, Curator, DocumentationReviewer, Debate-Arbiter, Synthesizer, Research-Agent, Final-Verifier)",
-        "ACE learning system with persistent knowledge base",
+        "11 specialized agents (TaskDecomposer, Actor, Monitor, Predictor, Evaluator, Reflector, DocumentationReviewer, Debate-Arbiter, Synthesizer, Research-Agent, Final-Verifier)",
         "5 Claude Code hooks for automation",
         "10 slash commands (/map-efficient, /map-debug, /map-fast, /map-debate, /map-review, /map-check, /map-plan, /map-release, /map-resume, /map-learn)",
         "Professional code review integration",
@@ -56,8 +54,7 @@
         "hooks": "https://github.com/azalio/map-framework/blob/main/.claude/hooks/README.md"
       },
       "research": {
-        "map_paper": "https://github.com/Shanka123/MAP",
-        "ace_paper": "https://arxiv.org/abs/2510.04618v1"
+        "map_paper": "https://github.com/Shanka123/MAP"
       }
     }
   ],

.claude-plugin/plugin.json

@@ -1,14 +1,13 @@
 {
   "name": "map-framework",
   "version": "1.0.0",
-  "description": "Modular Agentic Planner (MAP) - Cognitive architecture for AI agents with 12 specialized agents, ACE learning system, and professional code review integration",
+  "description": "Modular Agentic Planner (MAP) - Cognitive architecture for AI agents with 11 specialized agents and professional code review integration",
   "author": "azalio",
   "license": "MIT",
   "repository": "https://github.com/azalio/map-framework",
   "homepage": "https://github.com/azalio/map-framework",
   "keywords": [
     "MAP",
-    "ACE",
     "cognitive-architecture",
     "planning",
     "agents",
@@ -34,8 +33,7 @@
     ]
   },
   "features": [
-    "12 specialized MAP agents (TaskDecomposer, Actor, Monitor, Predictor, Evaluator, Reflector, Curator, DocumentationReviewer, Debate-Arbiter, Synthesizer, Research-Agent, Final-Verifier)",
-    "ACE (Agentic Context Engineering) learning system with persistent knowledge base",
+    "11 specialized MAP agents (TaskDecomposer, Actor, Monitor, Predictor, Evaluator, Reflector, DocumentationReviewer, Debate-Arbiter, Synthesizer, Research-Agent, Final-Verifier)",
     "5 Claude Code hooks for automation (validate-agent-templates, auto-store-knowledge, enrich-context, session-init, track-metrics)",
     "10 slash commands (/map-efficient, /map-debug, /map-fast, /map-debate, /map-review, /map-check, /map-plan, /map-release, /map-resume, /map-learn)",
     "Professional code review with claude-reviewer MCP",
@@ -66,7 +64,6 @@
       "evaluator",
       "orchestrator",
       "reflector",
-      "curator",
       "documentation-reviewer"
     ],
     "commands": [