Agent Sandbox
Skill Verified ActiveAgent skill for sandbox - invoke with $agent-sandbox
To provide developers and testers with a secure and efficient way to create, manage, and utilize isolated execution environments for code development and testing.
Features
- Create and configure E2B sandboxes
- Execute code safely in isolated environments
- Manage sandbox lifecycles (creation to termination)
- Handle file uploads, downloads, and environment configuration
- Monitor sandbox performance and resource utilization
Use Cases
- Setting up isolated development environments for new projects
- Running code tests in a clean, reproducible environment
- Experimenting with new libraries or frameworks without affecting the local system
- Managing and cleaning up temporary execution environments after use
Non-Goals
- General-purpose code execution outside of a managed sandbox
- Managing cloud infrastructure beyond E2B sandbox instances
- Performing security audits of user-submitted code within the sandbox
Documentation
- info:Configuration & parameter referenceThe SKILL.md provides examples of tool usage with parameters, but a formal reference for all options and defaults is not explicitly laid out.
Code Execution
- info:ValidationWhile the code examples show structured parameters, there's no explicit mention of using a schema validation library like Zod or Pydantic for input sanitization.
- info:Error HandlingThe SKILL.md outlines core responsibilities including 'Proper error handling and logging', but specific details on structured error reporting or fail-closed behavior are not provided.
- info:LoggingThe SKILL.md mentions 'Clear execution logging and debugging support' as a quality standard, but details on a specific audit file or structured logging format are absent.
Errors
- info:Actionable error messagesWhile the SKILL.md mentions proper error handling, specific details on how errors are presented to the user with remediation steps are not fully detailed.
Protocol
- info:Idempotent retry & timeoutsThe `timeout` parameter is shown for `sandbox_create`, suggesting some consideration for timeouts, but idempotency and structured retryable errors are not explicitly detailed.
Practical Utility
- info:Edge casesThe SKILL.md mentions quality standards like 'Implement proper error handling and logging' and 'Scalable sandbox orchestration', but explicit documentation of failure modes and recovery steps for edge cases is not detailed.
Safety
- info:Halt on unexpected stateThe skill aims to manage sandboxes, and while error handling is mentioned, explicit documentation on halting on unexpected pre-state with clear reports is not present.
Installation
npx skills add ruvnet/rufloRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
VerifiedTrust Signals
Similar Extensions
Minimal Run And Audit
100Trusted-lane execution and reporting skill for README-first AI repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, or end-to-end orchestration by itself.
Wasm Agent
99Create and manage sandboxed WASM agents for isolated code execution
Python Executor
99Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D models, automation, pandas, matplotlib
Cloudflare Sandbox SDK
99Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
AgentBay AIO Skills
95用于任何「运行/执行/评估代码」的请求（如 run this code、execute script、用 Python 画图、跑代码/画图/执行脚本）。通过 AgentBay SDK 创建 code_latest 沙箱，调用 run_code 执行并返回结果。支持 Python、JavaScript、R、Java。
Context Mode
100Update context-mode from GitHub and fix hooks/settings. Pulls latest, builds, installs, updates npm global, configures hooks. Trigger: /context-mode:ctx-upgrade