🔧 chore: remove memory MCP server and context-manager documentation

Remove the memory MCP server configuration and all references to the context-manager agent with persistent memory capabilities from CLAUDE.md.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Lorenz Hilpert
2025-11-05 14:04:52 +01:00
parent d46bf462cb
commit a52928d212
2 changed files with 1 additions and 45 deletions

View File

@@ -17,13 +17,6 @@
"figma-desktop": {
"type": "http",
"url": "http://127.0.0.1:3845/mcp"
},
"memory": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-memory"],
"env": {
"MEMORY_FILE_PATH": "~/Projects/ISA-Frontend/memory.json"
}
}
}
}

View File

@@ -8,10 +8,6 @@ This file contains meta-instructions for how Claude should work with the ISA-Fro
- **`docs-researcher`**: For ALL documentation (packages, libraries, READMEs)
- **`docs-researcher-advanced`**: Auto-escalate when docs-researcher fails
- **`Explore`**: For ALL code pattern searches and multi-file analysis
- **`context-manager`**: For complex projects and knowledge preservation with **persistent memory**
- **Direct tools (Read/Bash)**: ONLY for single specific files or commands
**NEW**: The `context-manager` now autonomously stores project knowledge (decisions, patterns, solutions) in persistent memory for cross-session learning.
**Violations of this rule degrade performance and context quality. NO EXCEPTIONS.**
@@ -26,7 +22,7 @@ This file contains meta-instructions for how Claude should work with the ISA-Fro
## Researching and Investigating the Codebase
**🔴 MANDATORY: You MUST use subagents for research. Direct file reading/searching is FORBIDDEN except for single specific files.**
**🔴 MANDATORY: You MUST use subagents for research. Direct file reading/searching.**
### Required Agent Usage
@@ -61,36 +57,3 @@ This file contains meta-instructions for how Claude should work with the ISA-Fro
```
**Remember: Using subagents is NOT optional - it's mandatory for maintaining context efficiency and search quality.**
## Project Knowledge Management with Context-Manager
**NEW CAPABILITY**: The `context-manager` subagent has **persistent memory** that autonomously stores and retrieves project knowledge across sessions.
### What Gets Stored Automatically
- **Assigned Tasks**: User-assigned tasks with context ("Remember to look up X because of Y"), TODO items, status tracking
- **Architectural Decisions**: State management patterns, API integration approaches, component architecture choices
- **Reusable Patterns**: Code conventions, testing patterns, error handling approaches
- **Integration Points**: API contracts, data flows, module boundaries
- **Domain Knowledge**: Business workflows, business rules, user roles/permissions
- **Technical Solutions**: Bug fixes with root causes, performance optimizations
### When to Use Context-Manager
Use the `context-manager` subagent PROACTIVELY for:
- **Task Management**: Assigning tasks for later ("Remember to investigate X because of Y")
- **Session Continuity**: Starting a new session (it will remind you of pending tasks)
- Complex, multi-step projects requiring coordination
- Long-running tasks that span multiple sessions
- Preserving architectural context
- Learning about resolved issues and their solutions
### How It Works
1. **Task Capture**: Listens for "Remember to...", "TODO:", "Don't forget...", stores them with full context
2. **Automatic Storage**: Proactively stores important discoveries in persistent memory
3. **Knowledge Retrieval**: Queries stored knowledge before starting new work
4. **Task Reminders**: Proactively reminds you of pending/incomplete tasks at session start
5. **Cross-Session Persistence**: Information persists across Claude Code sessions
**Benefits**: Eliminates context loss, maintains project knowledge, provides task continuity across sessions.