菜单
Build background agents in sandboxed environments. Use for hosted coding agents, sandboxed VMs, Modal sandboxes, and remote coding environments.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Create forensically sound bit-for-bit disk images using dd and dcfldd while preserving evidence integrity through hash verification.
Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware.
Route tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.
基于 SOC 职业分类
| name | hosted-agents |
| description | Build background agents in sandboxed environments. Use for hosted coding agents, sandboxed VMs, Modal sandboxes, and remote coding environments. |
| risk | unknown |
| source | community |
| category | ai-agents |
Hosted agents run in remote sandboxed environments rather than on local machines. When designed well, they provide unlimited concurrency, consistent execution environments, and multiplayer collaboration. The critical insight is that session speed should be limited only by model provider time-to-first-token, with all infrastructure setup completed before the user starts their session.
Activate this skill when:
Hosted agents address the fundamental limitation of local agent execution: resource contention, environment inconsistency, and single-user constraints. By moving agent execution to remote sandboxed environments, teams gain unlimited concurrency, reproducible environments, and collaborative workflows.
The architecture consists of three layers: sandbox infrastructure for isolated execution, API layer for state management and client coordination, and client interfaces for user interaction across platforms. Each layer has specific design requirements that enable the system to scale.
The Core Challenge Spinning up full development environments quickly is the primary technical challenge. Users expect near-instant session starts, but development environments require cloning repositories, installing dependencies, and running build steps.
Image Registry Pattern Pre-build environment images on a regular cadence (every 30 minutes works well). Each image contains:
When starting a session, spin up a sandbox from the most recent image. The repository is at most 30 minutes out of date, making synchronization with the latest code much faster.
Snapshot and Restore Take filesystem snapshots at key points:
This enables instant restoration for follow-up prompts without re-running setup.
Git Configuration for Background Agents Since git operations are not tied to a specific user during image builds:
user.name and user.email when committing and pushing changesWarm Pool Strategy Maintain a pool of pre-warmed sandboxes for high-volume repositories:
Server-First Architecture Choose an agent framework structured as a server first, with TUI and desktop apps as clients. This enables:
Code as Source of Truth Select frameworks where the agent can read its own source code to understand behavior. This is underrated in AI development: having the code as source of truth prevents hallucination about the agent's own capabilities.
Plugin System Requirements The framework should support plugins that:
tool.execute.before)Predictive Warm-Up Start warming the sandbox as soon as a user begins typing their prompt:
Parallel File Reading Allow the agent to start reading files immediately, even if sync from latest base branch is not complete:
Maximize Build-Time Work Move everything possible to the image build step:
Agent-Spawned Sessions Create tools that allow agents to spawn new sessions:
Frontier models are capable of containing themselves. The tools should:
Prompt Engineering for Self-Spawning Engineer prompts to guide when agents spawn sub-sessions:
Per-Session State Isolation Each session requires its own isolated state storage:
Real-Time Streaming Agent work involves high-frequency updates:
WebSocket connections with hibernation APIs reduce compute costs during idle periods while maintaining open connections.
Synchronization Across Clients Build a single state system that synchronizes across:
All changes sync to the session state, enabling seamless client switching.
Why Multiplayer Matters Multiplayer enables:
Implementation Requirements
With proper synchronization architecture, multiplayer support is nearly free to add.
User-Based Commits Use GitHub authentication to:
Sandbox-to-API Flow
Slack Integration The most effective distribution channel for internal adoption:
Build a classifier to determine which repository to work in:
Web Interface Core features:
Statistics page showing:
Chrome Extension For non-engineering users:
Decide how to handle messages sent during execution:
Queueing is simpler to manage and lets users send thoughts on next steps while agent works. Build mechanism to stop agent mid-execution when needed.
Track metrics that indicate real value:
Internal adoption patterns that work:
This skill builds on multi-agent-patterns for agent coordination and tool-design for agent-tool interfaces. It connects to:
Internal reference:
Related skills in this collection:
External resources:
Created: 2026-01-12 Last Updated: 2026-01-12 Author: Agent Skills for Context Engineering Contributors Version: 1.0.0
Use this skill when tackling tasks related to its primary domain or functionality as described above.