Agent-readable wiki
claude-sandbox Technical Wiki
A Docker sandbox layer that runs Claude Code agents inside isolated per-workspace containers launched by Superset, keeping the host git worktree as the single source of truth.
Pages
- OverviewWhat claude-sandbox is, its core design goals (isolation without Container Use, host worktree as source of truth), and how it integrates with Superset workspaces and Claude Code.
- Setup and Superset IntegrationPrerequisites, building the image, copying the .superset/ launcher into a repo, configuring a Superset agent, and the first workspace launch flow.
- The launch.sh LauncherThe host-side script that performs preflight checks, detects prompts via argv/env/stdin, computes stable container names, decides between docker run and docker exec for reattach, and assembles all Docker arguments.
- Mount Strategies: Worktrees, Symlinks, and GitHow launch.sh bind-mounts the worktree, resolves .git worktree pointers by mounting the parent .git directory, scans external symlinks and mounts their targets, and optionally mounts ~/.ssh read-only.
- Container Image and EntrypointThe Dockerfile that builds an Ubuntu 24.04 image with Claude Code, uv, Node 22, ripgrep, and a UID-1000 claude user; the minimal entrypoint.sh that sources /workdir/.env before exec.
- Environment Variables, Customization, and TroubleshootingAll CLAUDE_SANDBOX_* host and container variables, ANTHROPIC_* forwarding, network modes, per-project Dockerfile extension, and the documented failure modes with exact fixes.
Complete Markdown
The complete agent-readable Markdown files are published separately from this HTML page.