Managed Agent
技能 已验证 活跃Run an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the local wasm-agent runtime
Run and manage Anthropic's cloud-based agents for long-running or resource-intensive tasks, offering a persistent environment and capabilities beyond local sandboxes.
功能
- Create and provision cloud agent sessions
- Send messages and poll for agent responses
- Inspect agent status and event transcripts
- List active agent sessions
- Terminate cloud agent sessions to prevent ongoing billing
使用场景
- Running tasks that require significant compute or long execution times
- Leveraging pre-installed packages and network access in a cloud environment
- Maintaining persistent agent state across multiple turns or sessions
- Collaborating with cloud-based AI agents for complex workflows
非目标
- Running agents locally without Anthropic cloud infrastructure
- Managing local WASM agents (this skill is for the cloud counterpart)
- Directly executing arbitrary shell commands on the host system
Protocol
- info:Idempotent retry & timeoutsThe documentation mentions `maxWaitMs` for the prompt tool, suggesting timeouts are considered, but explicit guidance on idempotency for mutating operations is not provided.
安装
请先添加 Marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-agent@ruflo质量评分
已验证类似扩展
Mcp Setup
100Configure popular MCP servers for enhanced agent capabilities
Deepinit
100Deep codebase initialization with hierarchical AGENTS.md documentation
Agent Worker Specialist
100Agent skill for worker-specialist - invoke with $agent-worker-specialist
Orchestrate
100Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
Context Compression
100This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Init
100Initializes an optional repo-local agent collaboration preference file at `.ai/swe.json` by running a short interview or a zero-question quick mode. Use when a user says `initialize agent settings for this repo`, `set up my local agent prefs here`, `run quick init for this project`, or `create .ai/swe.json for how I like to work`. Do NOT use for `npm init`, project scaffolding, dependency installation, or environment bootstrap.