| name | review-loop |
| description | Iterative review loop with subagent reviewer. Use when: reviewing code changes, reviewing plans, auditing implementations, validating fixes, running code review, performing quality checks, or when /review is invoked. Spawns a fresh subagent to review a user-specified target, reports severity-tagged findings, applies approved fixes, and repeats until the user is satisfied. |
| argument-hint | Describe or reference the target to review (file paths, plan, diff, etc.) |
Review Loop
Iteratively review a target (code or plan) using a fresh subagent reviewer,
present findings, apply fixes, and repeat until the user approves.
When to Use
- After implementing a non-trivial change
- Validating a plan before execution
- Auditing code for correctness, style, or security issues
- Any time you want an independent second opinion on work in progress
Severity Levels
Findings are tagged with one of four severities:
| Severity | Meaning |
|---|
| critical | Correctness bug, security vulnerability, or data loss risk. Must fix. |
| high | Likely bug, race condition, or significant design flaw. Should fix. |
| medium | Code smell, unclear logic, missing edge case, or maintainability concern. Recommended fix. |
| low | Style nit, naming suggestion, minor improvement. Fix at discretion. |
Procedure
1. Identify the Review Target
