Overview
The/review command provides a local workflow for analyzing code changes with AI-powered insights. It offers multiple review modes to fit different development scenarios—from reviewing uncommitted changes to analyzing full branches or specific commits.
When you run /review, droid guides you through selecting a review type, configuring parameters, and then performs a comprehensive analysis of your code changes based on industry-standard review guidelines.
Quick start
Select a review type
Choose from four review presets:
- Review against a base branch - PR-style review comparing your branch to a base branch
- Review uncommitted changes - Analyze working directory changes (staged, unstaged, and untracked)
- Review a commit - Examine a specific commit from history
- Custom review instructions - Define your own review criteria
Configure parameters
Depending on your selection:
- For base branch reviews: Select the target branch (e.g.,
main,develop) - For commit reviews: Choose a commit from the interactive list
- For custom reviews: Enter your review instructions
Review types
Review against a base branch
Compare your current branch against a base branch (like a pull request review). This is ideal for pre-PR reviews or checking what changes would be merged. How it works:- Select “Review against a base branch”
- Choose your target base branch from the list (local and remote branches shown)
- Droid finds the merge base and reviews the diff
- Pre-commit PR reviews
- Checking branch changes before creating a pull request
- Validating feature branch against main/develop
Review uncommitted changes
Analyze all current working directory changes—staged files, unstaged modifications, and untracked files. Use cases:- Quick sanity check before committing
- Reviewing work in progress
- Finding issues early in development
Review a commit
Examine the changes introduced by a specific commit in your repository history. How it works:- Select “Review a commit”
- Browse commits with hash, message, author, and date
- Select a commit to review
- Reviewing recent commits for issues
- Understanding changes in a specific commit
- Post-merge review of teammate’s work
Custom review instructions
Define your own review criteria for specialized analysis. Use cases:- Performance analysis
- Checking specific coding standards
- Domain-specific validations
Review guidelines
All code reviews follow a structured rubric designed to provide actionable, high-quality feedback:Severity levels
Reviews categorize findings using priority levels:- [P0] - Critical issues blocking release or operations
- [P1] - Urgent issues that should be addressed in the next cycle
- [P2] - Normal priority issues to fix eventually
- [P3] - Low priority nice-to-have improvements
Bug detection criteria
The AI only flags issues as bugs when they meet ALL of these criteria:- Meaningful impact - Affects accuracy, performance, security, or maintainability
- Discrete and actionable - Clear, specific issue with a clear fix
- Appropriate rigor - Fix doesn’t demand more rigor than the rest of the codebase
- Introduced in changes - Bug was added in the reviewed changes (not pre-existing)
- Worth fixing - Author would likely fix if made aware
- No unstated assumptions - Based on verifiable facts, not speculation
- Provably affected - Can identify specific affected code, not theoretical
- Not intentional - Clearly not a deliberate design choice
Comment style
Review comments follow these principles:- Clear reasoning - Explains why something is an issue
- Appropriate severity - Communicates impact accurately
- Brief - Maximum 1 paragraph per finding
- Minimal code - Code chunks limited to 3 lines in markdown
- Scenario-specific - Describes affected environments/conditions
- Matter-of-fact tone - Avoids accusatory language
- Immediately graspable - Easy for the author to understand
- No excessive flattery - Focuses on actionable feedback
Output format
Each finding includes:- Clear title (≤80 characters, imperative mood)
- Explanation of why this is a problem
- File path and line numbers where applicable
- Priority level [P0-P3]
- Suggested fix (when concrete replacement code is available)
- Whether changes are correct or incorrect
- 1-3 sentence summary
Tips and best practices
When to use each review type
When to use each review type
- Uncommitted changes: During active development, before staging commits
- Base branch review: Before creating PRs, to catch issues early
- Commit review: After merging, to understand historical changes or review teammate’s commits
- Custom instructions: When you need focused analysis (security, performance, specific patterns)
Making the most of reviews
Making the most of reviews
- Run reviews frequently during development, not just before commits
- Use custom instructions for domain-specific concerns your team cares about
- Treat P0/P1 findings seriously—they represent real issues worth addressing
- Review the overall assessment for context on whether changes are sound
Integration with workflows
Integration with workflows
The See the Automated Code Review guide for automation setup.
/review command is meant for local CLI sessions. For automated reviews in CI/CD, use:Examples
Pre-PR review
Quick WIP check
Post-merge review
Automated reviews in CI
For automated PR reviews, use the Automated Code Review workflow. It supports:- Automatic PR reviews triggered by pull request events or comments
- Review depth (
deeporshallow) to control thoroughness and cost - Custom review guidelines for repository-specific checks
See also
- CLI Reference - Complete command reference including
/review - Automated Code Review guide - Set up automated PR reviews with deep/shallow modes
- Common use cases - Other workflows and patterns
- How to talk to a droid - Getting better results from AI reviews
