Multi-agent deep review for code PRs in any repo. Use when asked to "deep review this PR," "multi-agent review," "review #N with subagents," "thorough review of this branch," or "is this PR ready to merge." Orchestrates Copilot + parallel subagents (adversarial, operational, reference-comparison) with scope-based escalation, stale-finding triage, and a hard iteration cap.
AI-driven code review workflow that reviews uncommitted changes using a discoverable reviewer profile, presents findings for human decision, and iterates until approved. Supports --unattended for automated iteration. Use when reviewing code before commit or PR. Activated by commands: /start, /continue, /clean.
Performs a thorough code review of the current changes or a specified file / pull request. Covers correctness, security, performance, readability, and adherence to project conventions. Outputs prioritised, actionable feedback. TRIGGER when the user writes /code-review or asks for a code review, PR review, or feedback on their code.
Review Luau code for style compliance, type safety, server authority, error handling, and performance. Use for reviewing a file, a PR-sized change, or a whole module.
Systematic code review with structured output and actionable findings. Use when reviewing code, auditing quality, checking for bugs, security vulnerabilities, or performance issues.
Use before commit, deploy, or PR merge, or when operator asks "review this diff" / "is this safe?"; reviews diff vs spec, decisions, maintainability, scope, tests, rollback. Do NOT write or fix code — review only.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
name: code-review
description: Default target is the current branch diff vs main.
--
# code-review - E2E healer team review
The team's own review procedure. It layers **things
Code review a pull request or recent changes using git diff and agent teams. Reviews code usage, efficiency, bugs, and comments. Backs up unused files to bk/.
Automated code review analyzing diffs for test coverage, code quality, architecture conformance, and security. Produces structured findings and optionally creates beads for issues found. Use when user says "review code", "code review", "review my changes", "check this branch", "/code-review", or wants automated quality analysis before merging.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.