wasm-agent
Create and manage sandboxed WASM agents for isolated code execution
Best for untrusted code executionWorks with GitHubLow risk
⌘source
- author
@ruvnet- repo
- ruvnet/ruflo
- language
- TypeScript
★46kstars
5.1kforks
May 5, 2026
✦overview.md
Key Features
- ·Sandboxed WASM execution
- ·Create, prompt, list, terminate agents
- ·Tool and file management within sandbox
- ·Export agents for sharing
- ·Portable across WASM runtimes
Use Cases
- →Run untrusted code in isolation
- →Experiment with agent configurations
- →Create portable agents for different environments
Best for
- ✓untrusted code execution
- ✓portable agent development
Not ideal for
- !high-performance computing
- !direct host system access
FAQs
name
wasm-agent
description
Create and manage sandboxed WASM agents for isolated code execution
argument-hint:<create|list|prompt|terminate> [options]
allowed-tools:mcp__claude-flow__wasm_agent_create mcp__claude-flow__wasm_agent_list mcp__claude-flow__wasm_agent_prompt mcp__claude-flow__wasm_agent_tool mcp__claude-flow__wasm_agent_files mcp__claude-flow__wasm_agent_export mcp__claude-flow__wasm_agent_terminate Bash
WASM Agent
Create sandboxed agents that run in WebAssembly for safe, isolated execution.
When to use
When you need to run untrusted code, experiment with agent configurations, or create portable agents that run anywhere WASM is supported.
Steps
- Create agent — call
mcp__claude-flow__wasm_agent_createwith agent configuration - Send prompt — call
mcp__claude-flow__wasm_agent_promptto interact with the agent - Use tools — call
mcp__claude-flow__wasm_agent_toolto give the agent access to specific tools - Manage files — call
mcp__claude-flow__wasm_agent_filesto read/write files in the sandbox - Export — call
mcp__claude-flow__wasm_agent_exportto package the agent for sharing - List agents — call
mcp__claude-flow__wasm_agent_listto see all running WASM agents - Terminate — call
mcp__claude-flow__wasm_agent_terminateto stop an agent
Benefits
- Full sandbox isolation — agents cannot access the host filesystem
- Portable — export and run on any WASM runtime
- Reproducible — same behavior across platforms
- Safe — no risk of system damage from agent actions
$install
1-click copynpx skills add ruvnet/ruflo --skill wasm-agentSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.