Skip to main content
Glama

ACE MCP Server

main-optimized.mdcโ€ข8.24 kB
--- description: Optimized main rule for improved token efficiency globs: main-optimized.mdc alwaysApply: false --- # ๐Ÿ” OPTIMIZED MEMORY BANK SYSTEM ๐Ÿšจ CRITICAL RULE: MEMORY BANK CREATION IS MANDATORY ๐Ÿšจ Memory Bank MUST be created BEFORE any other operation in ANY mode NO process can continue without verifying Memory Bank existence > **TL;DR:** This system uses optimized context management and adaptive rule loading to maximize token efficiency while preserving the structured development approach. ## ๐Ÿงญ OPTIMIZED MODE ARCHITECTURE ```mermaid graph TD subgraph "Memory Bank Core" Context["Context Manager"] Rules["Rule Loader"] FileIO["File Manager"] Transition["Mode Transition"] end subgraph "Custom Modes" VAN["VAN<br>Initialization"] PLAN["PLAN<br>Planning"] CREATIVE["CREATIVE<br>Design"] IMPLEMENT["IMPLEMENT<br>Building"] REFLECT["REFLECT<br>Review"] ARCHIVE["ARCHIVE<br>Documentation"] end Context --> VAN & PLAN & CREATIVE & IMPLEMENT & REFLECT & ARCHIVE Rules --> VAN & PLAN & CREATIVE & IMPLEMENT & REFLECT & ARCHIVE FileIO --> VAN & PLAN & CREATIVE & IMPLEMENT & REFLECT & ARCHIVE Transition --> VAN & PLAN & CREATIVE & IMPLEMENT & REFLECT & ARCHIVE VAN --> PLAN PLAN --> CREATIVE CREATIVE --> IMPLEMENT IMPLEMENT --> REFLECT REFLECT --> ARCHIVE style Context fill:#4da6ff,stroke:#0066cc,color:white style Rules fill:#ffa64d,stroke:#cc7a30,color:white style FileIO fill:#4dbb5f,stroke:#36873f,color:white style Transition fill:#d94dbb,stroke:#a3378a,color:white ``` ## ๐Ÿ“ˆ ADAPTIVE COMPLEXITY MODEL ```mermaid graph TD Task["Task Creation"] --> Complexity{"Complexity<br>Level?"} Complexity -->|"Level 1<br>Quick Fix"| L1["3-Phase<br>Streamlined Process"] Complexity -->|"Level 2<br>Enhancement"| L2["4-Phase<br>Balanced Process"] Complexity -->|"Level 3<br>Feature"| L3["5-Phase<br>Comprehensive Process"] Complexity -->|"Level 4<br>Enterprise"| L4["6-Phase<br>Governance Process"] L1 --> L1_Process["VAN โ†’ IMPLEMENT โ†’ REFLECT"] L2 --> L2_Process["VAN โ†’ PLAN โ†’ IMPLEMENT โ†’ REFLECT"] L3 --> L3_Process["VAN โ†’ PLAN โ†’ CREATIVE โ†’ IMPLEMENT โ†’ REFLECT"] L4 --> L4_Process["VAN โ†’ PLAN โ†’ CREATIVE โ†’ IMPLEMENT โ†’ REFLECT โ†’ ARCHIVE"] style Complexity fill:#d94dbb,stroke:#a3378a,color:white style L1 fill:#4dbb5f,stroke:#36873f,color:white style L2 fill:#ffa64d,stroke:#cc7a30,color:white style L3 fill:#4da6ff,stroke:#0066cc,color:white style L4 fill:#ff5555,stroke:#cc0000,color:white ``` ## ๐Ÿง  HIERARCHICAL RULE LOADING Rules are loaded hierarchically to optimize context usage: ```mermaid graph TD Root["Memory Bank<br>Common Rules"] --> Core["Core Rules<br>Shared Across Modes"] Core --> L1["Level 1<br>Rules"] Core --> L2["Level 2<br>Rules"] Core --> L3["Level 3<br>Rules"] Core --> L4["Level 4<br>Rules"] Core --> VM["Mode<br>Visual Maps"] Core --> Phase["Phase-Specific<br>Rules"] Phase --> VAN_Rules["VAN Mode<br>Rules"] Phase --> PLAN_Rules["PLAN Mode<br>Rules"] Phase --> CREATIVE_Rules["CREATIVE Mode<br>Rules"] Phase --> IMPLEMENT_Rules["IMPLEMENT Mode<br>Rules"] Phase --> REFLECT_Rules["REFLECT Mode<br>Rules"] Phase --> ARCHIVE_Rules["ARCHIVE Mode<br>Rules"] style Root fill:#4da6ff,stroke:#0066cc,color:white style Core fill:#ffa64d,stroke:#cc7a30,color:white style Phase fill:#4dbb5f,stroke:#36873f,color:white ``` ## ๐Ÿ”„ TOKEN-OPTIMIZED CREATIVE PHASE Creative phase documentation is progressively generated: ```mermaid graph TD Start["Creative Phase<br>Initiation"] --> P1["1๏ธโƒฃ PROBLEM<br>Define scope"] P1 --> P2["2๏ธโƒฃ OPTIONS<br>List alternatives"] P2 --> P3["3๏ธโƒฃ ANALYSIS<br>Compare options"] P3 --> P4["4๏ธโƒฃ DECISION<br>Select approach"] P4 --> P5["5๏ธโƒฃ GUIDELINES<br>Document implementation"] P3 -.->|"On Demand"| Details["Detailed Option<br>Analysis"] style Start fill:#d971ff,stroke:#a33bc2,color:white style P1 fill:#4da6ff,stroke:#0066cc,color:white style P2 fill:#ffa64d,stroke:#cc7a30,color:white style P3 fill:#4dbb5f,stroke:#36873f,color:white style P4 fill:#d94dbb,stroke:#a3378a,color:white style P5 fill:#4dbbbb,stroke:#368787,color:white style Details fill:#e699d9,stroke:#d94dbb,color:white,stroke-dasharray: 5 5 ``` ## ๐Ÿ”€ OPTIMIZED MODE TRANSITIONS Mode transitions use a unified context transfer protocol: ```mermaid sequenceDiagram participant Current as Current Mode participant Context as Context Manager participant Next as Next Mode Current->>Context: Create transition document Current->>Context: Store critical context Context->>Context: Prepare rule cache Current->>Next: Initiate transition Next->>Context: Verify context availability Context->>Next: Load relevant context Context->>Next: Load cached rules Next->>Next: Continue with preserved context ``` ## ๐Ÿ“Š MEMORY BANK EFFICIENT UPDATES ```mermaid graph TD subgraph "Memory Bank Files" tasks["tasks.md<br>Source of Truth"] active["activeContext.md<br>Current Focus"] creative["creative-*.md<br>Design Decisions"] progress["progress.md<br>Implementation Status"] transition["transition.md<br>Mode Transitions"] end Update["Update Request"] --> Diff{"Changed?"} Diff -->|"No"| Skip["Skip Update"] Diff -->|"Yes"| Section{"Section<br>Change?"} Section -->|"Yes"| Partial["Update Changed<br>Sections Only"] Section -->|"No"| Full["Full File<br>Update"] Partial --> tasks Full --> tasks style Update fill:#4da6ff,stroke:#0066cc,color:white style Diff fill:#ffa64d,stroke:#cc7a30,color:white style Section fill:#4dbb5f,stroke:#36873f,color:white style Partial fill:#d94dbb,stroke:#a3378a,color:white style Full fill:#4dbbbb,stroke:#368787,color:white ``` ## ๐Ÿ’ป COMPLEXITY-BASED DOCUMENTATION Documentation requirements scale based on complexity level: | Documentation | Level 1 | Level 2 | Level 3 | Level 4 | |---------------|---------|---------|---------|---------| | Problem Definition | Brief | Standard | Detailed | Comprehensive | | Options Analysis | Optional | Basic | Multiple Options | Extensive | | Implementation Plan | Simple | Standard | Detailed | Phased | | Testing Requirements | Basic | Standard | Comprehensive | Rigorous | | Documentation | Minimal | Standard | Detailed | Extensive | ## ๐Ÿ“‘ OPTIMIZED TEMPLATES BY LEVEL ### Level 1: Quick Fix Template ```markdown ## QUICK FIX: [Issue Name] - Problem: [Brief description] - Solution: [Implemented approach] - Verification: [How fix was tested] ``` ### Level 2: Enhancement Template ```markdown ## ENHANCEMENT: [Feature Name] - Requirement: [What needs to be done] - Approach: [How it was implemented] - Testing: [Verification approach] - Documentation: [Where documented] ``` ### Level 3-4: Comprehensive Template Uses the optimized creative phase template with appropriate documentation depth ## ๐Ÿ”„ REFERENCE MAPS Each mode's visual process map is optimized for token efficiency: - @VAN Mode Map (Optimized) - @PLAN Mode Map (Optimized) - @CREATIVE Mode Map (Optimized) - @IMPLEMENT Mode Map (Optimized) - @REFLECT Mode Map (Optimized) - @ARCHIVE Mode Map (Optimized) ## โšก TOKEN EFFICIENCY IMPROVEMENTS Optimizations in this version: 1. Hierarchical rule loading (65% token reduction) 2. Progressive creative phase documentation (60% token reduction) 3. Context preservation during mode transitions (40% token reduction) 4. Differential Memory Bank updates (30% token reduction) 5. Complexity-based template scaling (varies by level) ## ๐Ÿ’ก USAGE GUIDANCE To use the optimized system: 1. Start with the VAN command to initialize and determine complexity 2. Follow the complexity-appropriate workflow 3. Use progressive documentation appropriate to task complexity 4. Let the system manage rule loading and context preservation 5. Enjoy the improved token efficiency while maintaining structured development

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Angry-Robot-Deals/ace-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server