How this skill is triggered — by the user, by Claude, or both
Slash command
/ruflo-agent:wasm-agent <create|list|prompt|terminate> [options]<create|list|prompt|terminate> [options]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create sandboxed agents that run in WebAssembly for safe, isolated execution.
Create sandboxed agents that run in WebAssembly for safe, isolated execution.
When you need to run untrusted code, experiment with agent configurations, or create portable agents that run anywhere WASM is supported.
mcp__plugin_ruflo-core_ruflo__wasm_agent_create with agent configurationmcp__plugin_ruflo-core_ruflo__wasm_agent_prompt to interact with the agentmcp__plugin_ruflo-core_ruflo__wasm_agent_tool to give the agent access to specific toolsmcp__plugin_ruflo-core_ruflo__wasm_agent_files to read/write files in the sandboxmcp__plugin_ruflo-core_ruflo__wasm_agent_export to package the agent for sharingmcp__plugin_ruflo-core_ruflo__wasm_agent_list to see all running WASM agentsmcp__plugin_ruflo-core_ruflo__wasm_agent_terminate to stop an agentnpx claudepluginhub edisplay/ruflo --plugin ruflo-agentCreates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.