agent-capabilities
CommandMatrix of agent capabilities and their specializations.
Show the agentic-flow plugin's state - MCP server connection, capability profile and the tools it registered, provider defaults, the guard's mode, and ReasoningBank stats
> /plugin marketplace add ruvnet/agentic-flow> /plugin install agentic-flow@agentic-flow
name: agentic-flow-status description: Show the agentic-flow plugin's state - MCP server connection, capability profile and the tools it registered, provider defaults, the guard's mode, and ReasoningBank stats
Report the agentic-flow plugin's status. Read only; change nothing.
1. **MCP server**: check whether tools named `mcp__plugin_agentic-flow_agentic-flow__*` are available. If none are, say the `agentic-flow` server is not connected and suggest `/mcp` to see why (the first start downloads the package with `npx`, which can take a while). 2. **Profile**: from the tools present, name the profile: `agentic_flow_agent` present means `learning` or `admin`; otherwise `readonly` or `retrieval`. Say that `agentic_flow_agent` spawns an agent and that the plugin pre-approves no tool. 3. **Agents**: call `agentic_flow_list_agents` and give the count and a few names. 4. **ReasoningBank**: call `agentdb_stats` and quote what it returns. 5. **Settings**: state the plugin settings that matter (`mcp_profile`, `provider`, `model`, `guardMode`, `allow_bypass_permissions`) and where to change them (`/plugin`, then configure agentic-flow). Never print an API key; say only whether one is set if the user tells you. 6. **Guard**: the status line shows `agentic-flow: guard <mode> · <n> checked · <n> blocked`. Quote it if it is visible.
Keep the report under 15 lines.
Production-ready AI agent orchestration with 66 self-learning agents, 213 MCP tools, and autonomous multi-agent swarms.
Matrix of agent capabilities and their specializations.
Complete guide to all 54 available agent types in Claude Flow.
Reviewed all command files in `.claude/commands/analysis/` directory to ensure proper usage of: - `mcp__claude-flow__*` tools…
Analyze performance bottlenecks in swarm operations and suggest optimizations.
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.