@claude-flow/cli 3.0.2 → 3.1.0-alpha.2

package/.claude/commands/agents/agent-capabilities.md

@@ -0,0 +1,140 @@
+---
+name: agent-capabilities
+description: Capability matrix for all agent types
+type: reference
+---
+
+# Agent Capabilities Reference
+
+Matrix of agent capabilities and their specializations for Claude Flow V3.
+
+## Capability Matrix
+
+### Core Development
+
+| Agent | Code | Test | Review | Design | Research |
+|-------|:----:|:----:|:------:|:------:|:--------:|
+| coder | **5** | 3 | 2 | 2 | 2 |
+| reviewer | 3 | 2 | **5** | 3 | 2 |
+| tester | 2 | **5** | 2 | 1 | 2 |
+| planner | 2 | 1 | 2 | **5** | 4 |
+| researcher | 2 | 1 | 2 | 3 | **5** |
+
+### V3 Specialized
+
+| Agent | Security | Memory | Performance | Architecture |
+|-------|:--------:|:------:|:-----------:|:------------:|
+| security-architect | **5** | 2 | 3 | **5** |
+| security-auditor | **5** | 2 | 2 | 3 |
+| memory-specialist | 3 | **5** | 4 | 3 |
+| performance-engineer | 2 | 3 | **5** | 4 |
+| core-architect | 3 | 3 | 3 | **5** |
+
+### Swarm Coordination
+
+| Agent | Coordination | Consensus | Scaling | Fault Tolerance |
+|-------|:------------:|:---------:|:-------:|:---------------:|
+| hierarchical-coordinator | **5** | 4 | 4 | 4 |
+| mesh-coordinator | 4 | 4 | **5** | 4 |
+| adaptive-coordinator | **5** | 4 | **5** | 4 |
+| collective-intelligence-coordinator | 4 | **5** | 4 | 4 |
+
+### GitHub Integration
+
+| Agent | PR | Issues | CI/CD | Release | Review |
+|-------|:--:|:------:|:-----:|:-------:|:------:|
+| pr-manager | **5** | 3 | 2 | 3 | 4 |
+| code-review-swarm | 4 | 2 | 2 | 2 | **5** |
+| issue-tracker | 2 | **5** | 2 | 2 | 2 |
+| release-manager | 3 | 3 | 4 | **5** | 2 |
+| workflow-automation | 2 | 3 | **5** | 4 | 2 |
+
+## Capability Levels
+
+| Level | Description |
+|-------|-------------|
+| **5** | Expert - Primary specialization |
+| 4 | Advanced - Strong capability |
+| 3 | Intermediate - Good capability |
+| 2 | Basic - Limited capability |
+| 1 | Minimal - Not a focus |
+
+## V3 Performance Capabilities
+
+| Capability | Agents | Performance Gain |
+|------------|--------|------------------|
+| Flash Attention | memory-specialist, performance-engineer | 2.49x-7.47x |
+| HNSW Search | memory-specialist | 150x-12,500x |
+| Quantization | performance-engineer | 50-75% memory |
+| SONA Adaptation | sona-learning-optimizer | <0.05ms |
+
+## Consensus Capabilities
+
+| Agent | BFT | Raft | Gossip | CRDT |
+|-------|:---:|:----:|:------:|:----:|
+| byzantine-coordinator | **5** | 2 | 2 | 2 |
+| raft-manager | 2 | **5** | 2 | 2 |
+| gossip-coordinator | 2 | 2 | **5** | 3 |
+| crdt-synchronizer | 2 | 2 | 3 | **5** |
+| quorum-manager | 4 | 4 | 3 | 3 |
+
+## Tool Access by Agent Type
+
+### Code Tools
+```
+coder: Read, Write, Edit, MultiEdit, Glob, Grep, Bash
+reviewer: Read, Glob, Grep
+tester: Read, Write, Bash, Glob
+```
+
+### Swarm Tools
+```
+hierarchical-coordinator: mcp__claude-flow__swarm_*, mcp__claude-flow__agent_*
+mesh-coordinator: mcp__claude-flow__swarm_*, mcp__claude-flow__coordination_*
+adaptive-coordinator: mcp__claude-flow__topology_*, mcp__claude-flow__swarm_*
+```
+
+### GitHub Tools
+```
+pr-manager: mcp__github__*, Bash (gh CLI)
+code-review-swarm: mcp__github__*, mcp__claude-flow__swarm_*
+release-manager: mcp__github__*, mcp__claude-flow__workflow_*
+```
+
+## Querying Capabilities
+
+```bash
+# List all capabilities for an agent type
+npx claude-flow agent spawn -t coder --help
+
+# View agent definition
+cat .claude/agents/core/coder.md
+```
+
+## Capability-Based Selection
+
+### For Security Tasks
+1. `security-architect` - Design and threat modeling
+2. `security-auditor` - Vulnerability assessment
+3. `security-manager` - Consensus security
+
+### For Performance Tasks
+1. `performance-engineer` - Optimization
+2. `memory-specialist` - Memory/search optimization
+3. `performance-analyzer` - Bottleneck analysis
+
+### For Multi-Agent Coordination
+1. `hierarchical-coordinator` - Complex hierarchical tasks
+2. `mesh-coordinator` - Research and exploration
+3. `adaptive-coordinator` - Dynamic requirements
+
+### For GitHub Workflows
+1. `pr-manager` - PR lifecycle
+2. `code-review-swarm` - Comprehensive reviews
+3. `workflow-automation` - CI/CD automation
+
+## See Also
+
+- [agent-types](./agent-types.md) - All 87 agent types
+- [agent-coordination](./agent-coordination.md) - Coordination patterns
+- [spawn](./spawn.md) - Spawn command

package/.claude/commands/agents/agent-coordination.md

@@ -0,0 +1,28 @@
+# agent-coordination
+
+Coordination patterns for multi-agent collaboration.
+
+## Coordination Patterns
+
+### Hierarchical
+Queen-led with worker specialization
+```bash
+npx claude-flow swarm init --topology hierarchical
+```
+
+### Mesh
+Peer-to-peer collaboration
+```bash
+npx claude-flow swarm init --topology mesh
+```
+
+### Adaptive
+Dynamic topology based on workload
+```bash
+npx claude-flow swarm init --topology adaptive
+```
+
+## Best Practices
+- Use hierarchical for complex projects
+- Use mesh for research tasks
+- Use adaptive for unknown workloads

package/.claude/commands/agents/agent-spawning.md

@@ -0,0 +1,28 @@
+# 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

package/.claude/commands/agents/agent-types.md

@@ -0,0 +1,216 @@
+---
+name: agent-types
+description: Complete guide to all 87 available agent types in Claude Flow V3
+type: reference
+---
+
+# Agent Types Reference
+
+Complete guide to all 87 available agent types in Claude Flow V3.
+
+## Core Development (5)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `coder` | Code implementation with neural patterns | Feature development, bug fixes |
+| `reviewer` | Code quality assurance | PR reviews, security checks |
+| `tester` | Testing with automation | Unit tests, integration tests |
+| `planner` | Strategic task planning | Project planning, roadmaps |
+| `researcher` | Information gathering | Requirements, documentation |
+
+## V3 Specialized (12)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `security-architect` | Security architecture | Threat modeling, design |
+| `security-auditor` | CVE remediation | Vulnerability scanning |
+| `memory-specialist` | AgentDB unification | 150x-12,500x search |
+| `performance-engineer` | Optimization targets | 2.49x-7.47x speedup |
+| `core-architect` | DDD restructure | Domain modeling |
+| `adr-architect` | Architecture decisions | ADR documentation |
+| `claims-authorizer` | Access control | Claims-based auth |
+| `ddd-domain-expert` | Domain design | Bounded contexts |
+| `reasoningbank-learner` | Pattern learning | Self-improvement |
+| `sona-learning-optimizer` | Neural optimization | SONA adaptation |
+| `sparc-orchestrator` | SPARC methodology | Development workflow |
+| `v3-integration-architect` | V3 integration | System integration |
+
+## Swarm Coordination (6)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `hierarchical-coordinator` | Queen-led coordination | Complex projects |
+| `mesh-coordinator` | P2P peer networks | Research tasks |
+| `adaptive-coordinator` | Dynamic topology | Unknown workloads |
+| `collective-intelligence-coordinator` | Consensus decisions | Group decisions |
+| `swarm-memory-manager` | Distributed memory | Data sharing |
+| `coordinator-swarm-init` | Swarm initialization | Setup |
+
+## Consensus Agents (7)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `byzantine-coordinator` | BFT consensus | Fault tolerance |
+| `raft-manager` | Leader-based consensus | Consistent state |
+| `gossip-coordinator` | Eventual consistency | Scalability |
+| `crdt-synchronizer` | CRDT replication | Conflict-free sync |
+| `quorum-manager` | Quorum consensus | Voting systems |
+| `security-manager` | Consensus security | Secure coordination |
+| `consensus-coordinator` | General consensus | Distributed systems |
+
+## GitHub Integration (14)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `pr-manager` | PR lifecycle | Pull requests |
+| `code-review-swarm` | Multi-agent review | Comprehensive reviews |
+| `issue-tracker` | Issue management | Bug tracking |
+| `release-manager` | Release coordination | Versioning |
+| `workflow-automation` | CI/CD automation | GitHub Actions |
+| `github-modes` | GitHub operations | Multi-mode GitHub |
+| `multi-repo-swarm` | Cross-repo sync | Monorepo management |
+| `project-board-sync` | Project boards | Kanban/Projects |
+| `release-swarm` | Release automation | Deployments |
+| `repo-architect` | Repository structure | Architecture |
+| `swarm-issue` | Issue-based swarms | Task decomposition |
+| `swarm-pr` | PR-based swarms | Review workflows |
+| `sync-coordinator` | Multi-repo sync | Version alignment |
+| `github-pr-manager` | PR management template | PR workflows |
+
+## SPARC Methodology (5)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `sparc-coordinator` | SPARC orchestration | Full SPARC cycle |
+| `specification` | Requirements phase | Specs writing |
+| `pseudocode` | Algorithm design | Logic design |
+| `architecture` | System design | Architecture |
+| `refinement` | Iteration phase | Improvements |
+
+## Optimization (6)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `topology-optimizer` | Swarm topology | Network optimization |
+| `load-balancer` | Task distribution | Workload balancing |
+| `resource-allocator` | Resource management | Capacity planning |
+| `performance-monitor` | Metrics tracking | Observability |
+| `benchmark-suite` | Performance testing | Benchmarks |
+| `performance-analyzer` | Analysis | Bottleneck detection |
+
+## Sublinear Algorithms (5)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `matrix-optimizer` | Matrix analysis | Linear systems |
+| `pagerank-analyzer` | Graph analysis | Network influence |
+| `performance-optimizer` | System optimization | Resource efficiency |
+| `trading-predictor` | Market analysis | Financial predictions |
+| `consensus-coordinator` | Fast consensus | Distributed coordination |
+
+## Analysis (2)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `analyze-code-quality` | Code quality | Static analysis |
+| `code-analyzer` | Code analysis | Pattern detection |
+
+## Architecture (1)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `arch-system-design` | System design | High-level architecture |
+
+## Data & ML (1)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `data-ml-model` | ML models | Machine learning |
+
+## Development (1)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `dev-backend-api` | Backend APIs | REST/GraphQL |
+
+## DevOps (1)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `ops-cicd-github` | CI/CD pipelines | GitHub Actions |
+
+## Documentation (1)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `docs-api-openapi` | API documentation | OpenAPI specs |
+
+## Flow Nexus (9)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `app-store` | App marketplace | App publishing |
+| `authentication` | User auth | Login/registration |
+| `challenges` | Coding challenges | Gamification |
+| `neural-network` | Neural training | ML deployment |
+| `payments` | Payment processing | Credits/billing |
+| `sandbox` | E2B sandboxes | Isolated execution |
+| `swarm` | Cloud swarms | Cloud coordination |
+| `user-tools` | User management | Profile/storage |
+| `workflow` | Workflow automation | Event-driven |
+
+## Goal Planning (2)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `goal-planner` | GOAP planning | Goal achievement |
+| `agent` | General goal agent | Multi-purpose |
+
+## Payments (1)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `agentic-payments` | AI commerce | Autonomous payments |
+
+## Specialized (1)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `spec-mobile-react-native` | React Native | Mobile development |
+
+## Templates (8)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `automation-smart-agent` | Smart automation | Auto-spawning |
+| `coordinator-swarm-init` | Swarm setup | Initialization |
+| `github-pr-manager` | PR workflows | GitHub PRs |
+| `implementer-sparc-coder` | SPARC coding | Implementation |
+| `memory-coordinator` | Memory management | State coordination |
+| `orchestrator-task` | Task orchestration | Workflow management |
+| `performance-analyzer` | Performance | Analysis |
+| `sparc-coordinator` | SPARC | Methodology |
+
+## Testing (3)
+
+| Agent | Description | Best For |
+|-------|-------------|----------|
+| `tdd-london-swarm` | TDD London School | Mock-first TDD |
+| `production-validator` | Deployment validation | Pre-deploy checks |
+| `test-long-runner` | Long-running tests | Complex test suites |
+
+## Quick Reference
+
+```bash
+# List all agent types
+npx claude-flow agent spawn --help
+
+# Spawn any agent
+npx claude-flow agent spawn -t <agent-type>
+```
+
+## See Also
+
+- [agent-capabilities](./agent-capabilities.md) - Capability matrix
+- [agent-coordination](./agent-coordination.md) - Coordination patterns
+- [spawn](./spawn.md) - Spawn command details

package/.claude/commands/agents/health.md

@@ -0,0 +1,139 @@
+---
+name: health
+description: Show agent health and metrics
+type: command
+---
+
+# Agent Health Command
+
+Monitor agent health status, resource usage, and detect issues.
+
+## Usage
+
+```bash
+npx claude-flow agent health [agent-id] [options]
+```
+
+## Options
+
+| Option | Short | Description | Default |
+|--------|-------|-------------|---------|
+| `--watch` | `-w` | Continuous monitoring | false |
+| `--interval` | `-i` | Watch interval in seconds | 5 |
+| `--format` | | Output format (table, json) | table |
+
+## Examples
+
+```bash
+# Overall health check
+npx claude-flow agent health
+
+# Specific agent health
+npx claude-flow agent health coder-lx7m9k2
+
+# Continuous monitoring
+npx claude-flow agent health --watch
+
+# Custom interval
+npx claude-flow agent health -w -i 10
+
+# JSON output
+npx claude-flow agent health --format json
+```
+
+## Output
+
+```
+Agent Health Status
+
+Overall: HEALTHY
+
++--------------------+---------+--------+--------+---------+
+| Agent              | Status  | Memory | CPU    | Tasks   |
++--------------------+---------+--------+--------+---------+
+| coder-lx7m9k2      | healthy | 45MB   | 2.3%   | 5/5     |
+| researcher-abc123  | healthy | 38MB   | 1.8%   | 3/3     |
+| tester-def456      | warning | 120MB  | 8.5%   | 12/14   |
++--------------------+---------+--------+--------+---------+
+
+Alerts
+  - tester-def456: High memory usage (120MB > 100MB threshold)
+  - tester-def456: Task failure rate above threshold (14.3%)
+
+Recommendations
+  - Consider restarting tester-def456
+  - Review failed tasks for error patterns
+```
+
+## Health Status Values
+
+| Status | Description |
+|--------|-------------|
+| `healthy` | All metrics within normal range |
+| `warning` | Some metrics approaching thresholds |
+| `critical` | Metrics exceeded critical thresholds |
+| `unknown` | Unable to determine health |
+
+## Health Checks
+
+### Resource Checks
+- Memory usage vs threshold
+- CPU utilization
+- Active connections
+- Queue depth
+
+### Performance Checks
+- Response time
+- Task success rate
+- Error frequency
+- Throughput
+
+### Connectivity Checks
+- MCP server connection
+- Memory backend
+- Neural services
+- Swarm coordination
+
+## Watch Mode
+
+Continuous monitoring with real-time updates:
+
+```bash
+npx claude-flow agent health --watch
+
+# Output updates every 5 seconds:
+# [10:30:15] Agent Health: 3 healthy, 0 warning, 0 critical
+# [10:30:20] Agent Health: 3 healthy, 0 warning, 0 critical
+# [10:30:25] Agent Health: 2 healthy, 1 warning, 0 critical
+#   - tester-def456: Memory usage increased to 115MB
+```
+
+Press `Ctrl+C` to stop watching.
+
+## JSON Output
+
+```json
+{
+  "overall": "healthy",
+  "agents": [
+    {
+      "id": "coder-lx7m9k2",
+      "status": "healthy",
+      "metrics": {
+        "memoryMB": 45,
+        "cpuPercent": 2.3,
+        "tasksCompleted": 5,
+        "tasksTotal": 5
+      }
+    }
+  ],
+  "alerts": [],
+  "recommendations": []
+}
+```
+
+## Related Commands
+
+- `npx claude-flow agent status` - Detailed agent info
+- `npx claude-flow agent metrics` - Performance metrics
+- `npx claude-flow doctor` - System-wide health

package/.claude/commands/agents/list.md

@@ -0,0 +1,100 @@
+---
+name: list
+description: List all active agents
+aliases: [ls]
+type: command
+---
+
+# Agent List Command
+
+List all active agents in the Claude Flow system with filtering options.
+
+## Usage
+
+```bash
+npx claude-flow agent list [options]
+npx claude-flow agent ls [options]  # Alias
+```
+
+## Options
+
+| Option | Short | Description | Default |
+|--------|-------|-------------|---------|
+| `--all` | `-a` | Include inactive/terminated agents | false |
+| `--type` | `-t` | Filter by agent type | All |
+| `--status` | `-s` | Filter by status (active, idle, terminated) | active |
+| `--format` | | Output format (table, json) | table |
+
+## Examples
+
+```bash
+# List all active agents
+npx claude-flow agent list
+
+# List all agents including inactive
+npx claude-flow agent list --all
+
+# Filter by type
+npx claude-flow agent list -t coder
+
+# Filter by status
+npx claude-flow agent list -s idle
+
+# JSON output for scripting
+npx claude-flow agent list --format json
+
+# Combined filters
+npx claude-flow agent list -t researcher -s active
+```
+
+## Output
+
+```
+Active Agents
+
++--------------------+-----------+--------+----------+---------------+
+| ID                 | Type      | Status | Created  | Last Activity |
++--------------------+-----------+--------+----------+---------------+
+| coder-lx7m9k2      | coder     | active | 10:30:15 | 10:45:23      |
+| researcher-abc123  | researcher| idle   | 09:15:00 | 10:20:45      |
+| tester-def456      | tester    | active | 11:00:00 | 11:12:30      |
++--------------------+-----------+--------+----------+---------------+
+
+Total: 3 agents
+```
+
+## JSON Output
+
+```json
+{
+  "agents": [
+    {
+      "id": "coder-lx7m9k2",
+      "agentType": "coder",
+      "status": "active",
+      "createdAt": "2026-01-08T10:30:15.000Z",
+      "lastActivityAt": "2026-01-08T10:45:23.000Z"
+    }
+  ],
+  "total": 3
+}
+```
+
+## Status Values
+
+| Status | Description |
+|--------|-------------|
+| `active` | Agent is currently executing tasks |
+| `idle` | Agent is waiting for tasks |
+| `terminated` | Agent has been stopped |
+
+## Agent Type Categories
+
+Use `--type` with any of the 87 agent types:
+
+- Core: `coder`, `reviewer`, `tester`, `planner`, `researcher`
+- V3: `security-architect`, `memory-specialist`, `performance-engineer`
+- Swarm: `hierarchical-coordinator`, `mesh-coordinator`, `adaptive-coordinator`
+- Consensus: `byzantine-coordinator`, `raft-manager`, `gossip-coordinator`
+- GitHub: `pr-manager`, `code-review-swarm`, `release-manager`
+- SPARC: `sparc-coordinator`, `specification`, `architecture`