sandbox0-ai/sandbox0
skills/sandbox0/SKILL.md
Use this skill when an AI agent developer wants to integrate Sandbox0 sandboxes, templates, volumes, credentials, managed agents, CLI, SDKs, or self-hosted deployment. For current API, CLI, SDK, and Managed Agents details, always consult the live Sandbox0 docs.
$ install --global
skillsauthnpx skillsauth add sandbox0-ai/sandbox0 sandbox0Install this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 9, 2026, 6:03 AM166.0s1 file scanned
SKILL.md
- name:
- sandbox0
- description:
- Use this skill when an AI agent developer wants to integrate Sandbox0 sandboxes, templates, volumes, credentials, managed agents, CLI, SDKs, or self-hosted deployment. For current API, CLI, SDK, and Managed Agents details, always consult the live Sandbox0 docs.
Sandbox0
Use this skill for Sandbox0 integration guidance for AI agent developers.
Source Of Truth
For exact API, CLI, SDK, and Managed Agents behavior, read the live docs first:
- https://sandbox0.ai/llms.txt
- https://sandbox0.ai/docs
- https://sandbox0.ai/docs/managed-agents
This skill is intentionally thin. Do not rely on local bundled docs for product details.
Default Onboarding
Start from Sandbox0 Cloud unless the user explicitly needs self-hosting.
- Install
s0:- macOS/Linux:
curl -fsSL https://raw.githubusercontent.com/sandbox0-ai/s0/main/scripts/install.sh | bash - Windows PowerShell:
irm https://raw.githubusercontent.com/sandbox0-ai/s0/main/scripts/install.ps1 | iex
- macOS/Linux:
- Sign in with
s0 auth login. - If the server did not auto-select a team, use
s0 team list,s0 team create, ands0 team use. - For SDK or raw HTTP usage, create an API key:
export SANDBOX0_TOKEN="$(s0 apikey create --name sdk-quickstart --role developer --expires-in 30d --raw)"export SANDBOX0_BASE_URL="https://api.sandbox0.ai"
If the user is only using the interactive s0 CLI, s0 auth login is usually enough and no API key export is required.
Managed Agents uses https://agents.sandbox0.ai. Sandbox, Template, Volume, and Credential APIs use https://api.sandbox0.ai.
Typical triggers
- Add Sandbox0 to an AI agent project
- Pick between REPL and one-shot execution
- Persist workspace state across runs
- Design a template or custom image
- Restrict network access
- Expose a preview server or local web app
- Receive sandbox events through webhooks
- Decide whether self-hosted Sandbox0 is needed
Stable Guidance
- For long-running coding agents, prefer Sandbox + REPL context + Volume.
- For one-shot work, prefer Sandbox + Cmd context.
- For durable workspace state, use Volumes.
- For restore points, use Volume snapshots.
- For restricted outbound access, use network policy and credentials.
- For Claude Managed Agents-compatible flows, use the official Anthropic SDK against Sandbox0 Managed Agents and store model credentials in vaults.
- Prefer Sandbox0 Cloud unless the user asks for self-hosting, private deployment, or data-plane ownership.
Working rules
- Check live docs before giving exact SDK code, CLI flags, API fields, metadata keys, or deployment commands.
- Prefer s0 CLI- and SDK-oriented guidance over internal implementation details.
- Recommend concrete compositions when helpful, for example
REPL + Volumefor persistent coding sessions. - Use architecture detail only when it changes the user's design choice, security model, persistence model, networking, or deployment tradeoff.
Source Repositories
- Sandbox0 core: https://github.com/sandbox0-ai/sandbox0
- CLI: https://github.com/sandbox0-ai/s0
- Go SDK: https://github.com/sandbox0-ai/sdk-go
- JavaScript SDK: https://github.com/sandbox0-ai/sdk-js
- Python SDK: https://github.com/sandbox0-ai/sdk-py
When reporting issues, include a minimal reproduction and relevant logs, but remove API keys, tokens, kubeconfigs, customer data, private repository URLs, and any other sensitive personal or organizational information.
Related Skills
openclaw/taskflow
tools
VerifiedTrustedCommunity
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,764SKILL.mdUpdated Apr 10, 2026
steipete/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,588SKILL.mdUpdated Apr 13, 2026
steipete/xurl
tools
VerifiedTrustedCommunity
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.
356,423SKILL.mdUpdated Apr 13, 2026