HartmutandClaude Sonnet 4.6
f80808482d
Restores the entire .claude/ infrastructure that was accidentally deleted
in commit 1df208d ('feat(timeline): add pulse animation for in-flight drag
mutations'). Recovered via git checkout 1df208d^.
Restored:
- .claude/commands/ (gitlooper, sparc/, github/, automation/, monitoring/,
optimization/, hooks/, plan, implement, research, review, perf, visualaudit)
- .claude/agents/ (core/, github/, sparc/, v3/, swarm/, templates/, ...)
- .claude/helpers/ (41 scripts incl. hook-handler.cjs, statusline.cjs)
- .claude/skills/ (20 skills incl. sparc-methodology, github-*, v3-*)
- .claude/settings.json (hooks configuration)
Also updated all CapaKraken → Nexus references in affected command files.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2.5 KiB
2.5 KiB
auto agent
Automatically spawn and manage agents based on task requirements.
Usage
npx claude-flow auto agent [options]
Options
--task, -t <description>- Task description for agent analysis--max-agents, -m <number>- Maximum agents to spawn (default: auto)--min-agents <number>- Minimum agents required (default: 1)--strategy, -s <type>- Selection strategy: optimal, minimal, balanced--no-spawn- Analyze only, don't spawn agents
Examples
Basic auto-spawning
npx claude-flow auto agent --task "Build a REST API with authentication"
Constrained spawning
npx claude-flow auto agent -t "Debug performance issue" --max-agents 3
Analysis only
npx claude-flow auto agent -t "Refactor codebase" --no-spawn
Minimal strategy
npx claude-flow auto agent -t "Fix bug in login" -s minimal
How It Works
-
Task Analysis
- Parses task description
- Identifies required skills
- Estimates complexity
- Determines parallelization opportunities
-
Agent Selection
- Matches skills to agent types
- Considers task dependencies
- Optimizes for efficiency
- Respects constraints
-
Topology Selection
- Chooses optimal swarm structure
- Configures communication patterns
- Sets up coordination rules
- Enables monitoring
-
Automatic Spawning
- Creates selected agents
- Assigns specific roles
- Distributes subtasks
- Initiates coordination
Agent Types Selected
- Architect: System design, architecture decisions
- Coder: Implementation, code generation
- Tester: Test creation, quality assurance
- Analyst: Performance, optimization
- Researcher: Documentation, best practices
- Coordinator: Task management, progress tracking
Strategies
Optimal
- Maximum efficiency
- May spawn more agents
- Best for complex tasks
- Highest resource usage
Minimal
- Minimum viable agents
- Conservative approach
- Good for simple tasks
- Lowest resource usage
Balanced
- Middle ground
- Adaptive to complexity
- Default strategy
- Good performance/resource ratio
Integration with Claude Code
// In Claude Code after auto-spawning
mcp__claude-flow__auto_agent {
task: "Build authentication system",
strategy: "balanced",
maxAgents: 6
}
See Also
agent spawn- Manual agent creationswarm init- Initialize swarm manuallysmart spawn- Intelligent agent spawningworkflow select- Choose predefined workflows