From spacecode
Run a task in a cloud sandbox. Use when user says "run in cloud", "remote exec", "cloud sandbox", or wants to execute code/commands in an ephemeral environment.
How this skill is triggered — by the user, by Claude, or both
Slash command
/spacecode:code-execThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Dispatch a prompt to an ephemeral cloud sandbox that clones a repo, runs Claude Code with your instructions, and returns logs + git diff.
Dispatch a prompt to an ephemeral cloud sandbox that clones a repo, runs Claude Code with your instructions, and returns logs + git diff.
Determine the repo. Use the current git remote if available:
git remote get-url origin 2>/dev/null
Convert SSH URLs ([email protected]:owner/repo.git) to owner/repo format.
If no git remote, ask the user for the repo.
Get the prompt. If the user provided a task description, use it. Otherwise ask what they want done.
Dispatch the task. Call the remote_exec MCP tool:
repo: The GitHub repository (e.g. owner/repo)prompt: The task instructionsbranch: (optional) Git branch to check out before runningmodel: (optional) Claude model to useReport results. The tool blocks until completion. Present:
On failure, suggest:
/cloud-status to check task historyUser: "Run the test suite for owner/my-app in the cloud"
Call remote_exec with:
owner/my-appRun the full test suite. Report pass/fail counts and any failures.npx claudepluginhub g-a-l-a-c-t-i-c/spacecode-plugin --plugin spacecodeGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Enforces test-driven development: write failing test first, then minimal code to pass. Use when implementing features or bugfixes.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.