2c1acda2f3
- Update DQN trainer with gradient collapse detection warmup - Add portfolio tracker improvements - Include hyperopt trial results (multiple Sharpe ratio experiments) - Add new test files for action/position sign convention, early stopping, cash reserve bugs, and portfolio execution - Update trained model files - Add Claude Code configuration and skills 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
29 lines
727 B
Markdown
29 lines
727 B
Markdown
# agent-spawning
|
|
|
|
Guide to spawning agents with Claude Code's Task tool.
|
|
|
|
## Using Claude Code's Task Tool
|
|
|
|
**CRITICAL**: Always use Claude Code's Task tool for actual agent execution:
|
|
|
|
```javascript
|
|
// Spawn ALL agents in ONE message
|
|
Task("Researcher", "Analyze requirements...", "researcher")
|
|
Task("Coder", "Implement features...", "coder")
|
|
Task("Tester", "Create tests...", "tester")
|
|
```
|
|
|
|
## MCP Coordination Setup (Optional)
|
|
|
|
MCP tools are ONLY for coordination:
|
|
```javascript
|
|
mcp__claude-flow__swarm_init { topology: "mesh" }
|
|
mcp__claude-flow__agent_spawn { type: "researcher" }
|
|
```
|
|
|
|
## Best Practices
|
|
1. Always spawn agents concurrently
|
|
2. Use Task tool for execution
|
|
3. MCP only for coordination
|
|
4. Batch all operations
|