From spacecode
Dispatch a code review to a cloud sandbox. Use when user says "cloud review", "remote review", "review my code remotely", or wants an independent code review from a separate Claude instance.
How this skill is triggered — by the user, by Claude, or both
Slash command
/spacecode:code-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Dispatch a code review to a remote Claude Code instance running in an ephemeral sandbox. Gets an independent review of your code changes.
Dispatch a code review to a remote Claude Code instance running in an ephemeral sandbox. Gets an independent review of your code changes.
Detect the repo and branch. Run:
git remote get-url origin 2>/dev/null
git branch --show-current 2>/dev/null
Convert SSH URLs to owner/repo format.
Identify what to review. Check for:
git diff --statgit log origin/main..HEAD --oneline (or appropriate base branch)Construct the review prompt. Build a prompt that:
Example prompt:
Review the code changes on branch '{branch}' compared to the main branch.
Run: git diff main...HEAD
Provide a structured review covering:
1. Critical Issues — Bugs, security vulnerabilities, data loss risks
2. Logic Errors — Incorrect behavior, edge cases, race conditions
3. Style & Quality — Naming, structure, duplication, missing docs
4. Missing Tests — Untested code paths, edge cases without coverage
For each finding, include the file, line, and a specific fix suggestion.
Dispatch via remote_exec. Call the MCP tool with the repo, review prompt, and branch.
Present findings in a clear, actionable format.
User: "Review my code before I create a PR"
remote_exec with review promptnpx 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.