/debugger
Systematic debugging with TodoWrite and Memory integration.
> /plugin marketplace add ruvnet/rufloHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/debugger
Context preview
What this command does when you run it.
Systematic debugging with TodoWrite and Memory integration.
Command definition
debugger.mdSPARC Debugger Mode
Purpose
Systematic debugging with TodoWrite and Memory integration.
Activation
Option 1: Using MCP Tools (Preferred in Claude Code)
mcp__claude-flow__sparc_mode {
mode: "debugger",
task_description: "fix authentication issues",
options: {
verbose: true,
trace: true
}
}Option 2: Using NPX CLI (Fallback when MCP not available)
# Use when running from terminal or MCP tools unavailable npx claude-flow sparc run debugger "fix authentication issues" # For alpha features npx claude-flow@alpha sparc run debugger "fix authentication issues"
Option 3: Local Installation
# If claude-flow is installed locally ./claude-flow sparc run debugger "fix authentication issues"
Core Capabilities
- Issue reproduction
- Root cause analysis
- Stack trace analysis
- Memory leak detection
- Performance bottleneck identification
Debugging Workflow
1. Create debugging plan with TodoWrite 2. Systematic issue investigation 3. Store findings in Memory 4. Track fix progress 5. Verify resolution
Tools Integration
- Error log analysis
- Breakpoint simulation
- Variable inspection
- Call stack tracing
- Memory profiling
An agent meta-harness for Claude Code and Codex. Agent = Model + Harness. The model writes; the harness gives it tools, memory, loops, sandboxes, and controls so it can actually work.
Repo: ruvnet/ruflo
Other commands on claude-flow.
- /agent-capabilities
Matrix of agent capabilities and their specializations.
Open command - /agent-coordination
Coordination patterns for multi-agent collaboration.
Open command - /agent-spawning
Guide to spawning agents with Claude Code's Task tool.
Open command - /agent-types
Complete guide to all 54 available agent types in Claude Flow.
Open command - /COMMAND_COMPLIANCE_REPORT
Reviewed all command files in `.claude/commands/analysis/` directory to ensure proper usage of: - `mcp__claude-flow__*` tools (preferred) - `npx claude-flow` commands (as fallback) - No direct implementation calls
Open command - /bottleneck-detect
Analyze performance bottlenecks in swarm operations and suggest optimizations.
Open command

