$ loading_
Run coding agents safely in isolated containers with full permissions.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "container" yet — see the docs or source repo.
Launch Claude Code in a secure container with full file and command permissions to inspect the current project, install dependencies, and fix build errors.
Returns execution results from the container, a summary of fixes made, and whether the build succeeds.
Run Codex inside a container with full repository access, refactor the authentication module, add necessary tests, and output a change summary at the end.
Produces safely executed code changes, test results, and a concise refactoring summary.
Run OpenCode in an isolated container with full permissions to scan the codebase, update dependencies, run unit tests, and list potential risks.
Outputs task logs, updated items, test conclusions, and a list of potential risks.
Call Codex inside Claude Code for reviews, second opinions, and delegated coding.
Let AI coding tools safely call Codex for development and automation tasks.
Delegate tasks from Claude Code to OpenCode subagents and retrieve results asynchronously.
Get a safe second opinion from a locally authenticated Claude Code model.
Delegate Claude Code tasks to Codex CLI with traces and persistent sessions.
Delegate code investigation, edits, and verification to Claude Code with background job management.