From sdw
Review recent code changes for quality, security, and correctness. Run before committing.
How this command is triggered — by the user, by Claude, or both
Slash command
/sdw:code-reviewThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Code Review Review recent code changes thoroughly before committing. Problems found here are free to fix — problems found after merging are not. **Output**: Save to `.claude/ai/review-YYYY-MM-DD-topic.md` ## Review scope Run `git diff` to see what changed. Focus on modified files and their immediate context. ## What to look for **Security** - No exposed secrets, API keys, or credentials in code or config - Input is validated at system boundaries - No obvious injection vulnerabilities **Correctness** - Logic does what it claims to do - Edge cases are handled - Errors are surfaced, n...
Review recent code changes thoroughly before committing. Problems found here are free to fix — problems found after merging are not.
Output: Save to .claude/ai/review-YYYY-MM-DD-topic.md
Run git diff to see what changed. Focus on modified files and their immediate context.
Security
Correctness
Test integrity — zero tolerance
Code quality
Feature creep
Run the project's test suite and include results in the report:
Don't skip this step.
Gather git metadata first (commit hash, branch, repo name), then save to .claude/ai/review-YYYY-MM-DD-topic.md:
---
date: [ISO date with timezone]
git_commit: [current commit hash]
branch: [current branch]
repository: [repo name]
status: complete
---
# Code Review: [Description]
**Date**: [date]
**Git Commit**: [hash]
**Branch**: [branch]
**Status**: Review Complete
## Summary
- **Overall**: ✅ APPROVED / ⚠️ APPROVED WITH CONDITIONS / ❌ REJECTED
- **Critical**: [N] issues — must fix before commit
- **Warnings**: [N] issues — should fix
- **Suggestions**: [N] items — optional
## Files Reviewed
[List of changed files]
## Test Results
✅ Passed: N | ⏭️ Skipped: N | ❌ Failed: N
[Full details for any failures]
## 🚨 Critical (Must Fix)
- **Issue**: [description — file:line]
- **Problem**: [what's wrong]
- **Fix**: [what to change]
## ⚠️ Warnings (Should Fix)
- **Issue**: [description — file:line]
- **Problem**: [concern]
- **Fix**: [recommendation]
## 💡 Suggestions (Optional)
- **Issue**: [description — file:line]
- **Benefit**: [improvement]
- **Approach**: [how]
## Approval
**Status**: [✅ APPROVED / ⚠️ APPROVED WITH CONDITIONS / ❌ REJECTED]
[Reasoning]
Present the path and a short summary. Highlight any critical issues clearly.
If the review finds critical issues: fix them, then run /sdw:code-review again.
/code-reviewReviews local uncommitted changes or GitHub pull requests for security, code quality, and best practices. Also supports PR review mode with full file context.
/code-reviewPerforms automated multi-agent code review on current GitHub pull request: audits CLAUDE.md, bugs, git history, prior PRs, code comments; scores issue confidence.
/code-reviewReviews source files changed during a phase for bugs, security issues, and code quality problems. Produces a REVIEW.md artifact with severity-classified findings at configurable depth (quick, standard, deep). Also supports --fix to auto-apply fixes.
/code-reviewReviews uncommitted changes for security vulnerabilities, code quality issues, and best practices using git diff. Generates report with severity levels, locations, descriptions, fixes; blocks commits on critical/high issues.
/code-reviewPerforms comprehensive code quality review of repository structure, code, security, performance, architecture, testing, and documentation. Produces prioritized issues and actionable recommendations with examples.
/code-reviewPerforms comprehensive code quality review of repository structure, code, security, performance, architecture, testing, and documentation. Produces prioritized issues and actionable recommendations with examples.
npx claudepluginhub visma-tech-lt/ai-workshop-marketplace --plugin sdw