docker-sandbox

Solid

Create, manage, and execute agent tools (claude, codex) inside Docker sandboxes for isolated code execution. Use when running agent loops, spawning tool subprocesses, or any task requiring process isolation. Triggers on "sandbox", "isolated execution", "docker sandbox", "safe agent execution", or when working on agent loop infrastructure.

DevOps & Infrastructure 57 stars 3 forks Updated 4 days ago

Install

View on GitHub

Quality Score: 77/100

Stars 20%
59
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
0
Description 5%
100

Skill Content

# Docker Sandbox for Agent Tools Isolated execution of `claude`, `codex`, and other agent tools using Docker Desktop's `docker sandbox` (v0.11.0+). Uses existing Claude Max and ChatGPT Pro subscriptions — no API key billing. **ADR**: [ADR-0023](https://joelclaw.com/adrs/0023-docker-sandbox-for-agent-loops) ## Prerequisites - Docker Desktop running (OrbStack works) - `docker sandbox version` returns ≥0.11.0 - Auth secrets stored in `agent-secrets`: - `claude_setup_token` — from `claude setup-token` (1-year token, Max subscription) - `codex_auth_json` — contents of `~/.codex/auth.json` (ChatGPT Pro subscription) ## Quick Reference ```bash # Create a sandbox docker sandbox create --name my-sandbox claude /path/to/project # Run a command in it docker sandbox exec -e "CLAUDE_CODE_OAUTH_TOKEN=..." -w /path/to/project my-sandbox \ claude -p "implement the feature" --output-format text --dangerously-skip-permissions # List sandboxes docker sandbox ls # Remove docker sandbox rm my-sandbox ``` ## Auth Setup (One-Time) ### Claude (Max subscription) Run interactively on the host (needs browser for OAuth): ```bash claude setup-token ``` This opens a browser, completes OAuth, and prints a token like `sk-ant-oat01-...`. Valid for **1 year**. Store it: ```bash secrets add claude_setup_token --value "sk-ant-oat01-..." ``` Use in sandbox: ```bash TOKEN=$(secrets lease claude_setup_token --ttl 1h --raw) docker sandbox exec -e "CLAUDE_CODE_OAUTH_TOKEN=$TOKEN" my-sandbox cla...

Details

Author
joelhooks
Repository
joelhooks/joelclaw
Created
3 months ago
Last Updated
4 days ago
Language
TypeScript
License
None

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

codex-agent

用 OpenClaw 驱动 Codex CLI 的受管运行时。支持交互式 tmux 会话、一次性 exec 任务、会话状态查询、显式 session-id 路由、启动阻塞识别与完成通知。

159 Updated 2 months ago
dztabel-happy
AI & Automation Listed

claude-code-dispatch

Dispatch development tasks to Claude Code with automatic callback on completion. Supports Agent Teams (multi-agent parallel dev with dedicated Testing Agent), cost controls (--max-budget-usd), model fallback, git worktree isolation, custom subagents via --agents JSON, and MCP server integration. Use when: (1) dispatching a coding task to Claude Code and wanting automatic Telegram notification on completion, (2) running Agent Teams for parallel dev+test workflows, (3) needing zero-polling task execution with Stop Hook callback, (4) the user says 'use Claude Code to build/develop/create X', (5) the user asks to dispatch or run a Claude Code task. THIS IS THE DEFAULT for any 'build/develop/create a project' request — prefer this over claude-code-clawdbot for anything that takes >2 min or needs background execution.

44 Updated 2 months ago
win4r
AI & Automation Solid

collaborating-with-claude-code

Delegate code implementation/review/debugging/alternatives to Claude Code via a JSON bridge script. Multi-turn via SESSION_ID.

37 Updated 3 months ago
ZhenHuangLab
Data & Documents Solid

sandbox0

Use this skill when an AI agent developer wants to add Sandbox0 sandboxing to their own agent through the CLI or SDK, or needs help choosing templates, contexts, volumes, network policy, ports, webhooks, or self-hosted deployment. It uses only files bundled inside the skill.

39 Updated today
sandbox0-ai