Reviews implemented code for simplicity, DRY, elegance, bugs, and project conventions using parallel reviewer agents. Presents findings and helps prioritize fixes. Use after implementation is complete.
Reviews implemented code for bugs, DRY violations, and project conventions using parallel agents.
/plugin marketplace add astrosteveo/harness/plugin install harness@astrosteveo-marketplaceThis skill is limited to using the following tools:
You are helping a developer review implemented code for quality and correctness.
Progress is saved to .artifacts/{feature-slug}/ for session continuity.
Ensure code is simple, DRY, elegant, easy to read, and functionally correct.
Feature context: $ARGUMENTS
Launch 3 code-reviewer agents in parallel with different focuses:
Consolidate findings and identify highest severity issues that you recommend fixing
Present findings to user and ask what they want to do:
Address issues based on user decision
## Code Review Findings
### High Priority (Recommend Fixing Now)
1. **{Issue}** in `{file}:{line}`
- Problem: {description}
- Suggestion: {how to fix}
### Medium Priority (Consider Fixing)
1. **{Issue}** in `{file}:{line}`
- Problem: {description}
- Suggestion: {how to fix}
### Low Priority (Nice to Have)
1. **{Issue}** in `{file}:{line}`
- Problem: {description}
- Suggestion: {how to fix}
### Positive Observations
- {What was done well}
Update progress.md with review findings and resolutions.
Add a section:
## Code Review Results
### Issues Found
| Severity | Issue | Resolution |
|----------|-------|------------|
| High | {issue} | Fixed / Deferred / Accepted |
### Review Summary
- Total issues: {N}
- Fixed: {N}
- Deferred: {N}
- Accepted as-is: {N}
docs({feature-slug}): record review findingsfix({feature-slug}): {describe fix from review}After review is complete, guide the user to use:
/harness:verify-testing to perform manual testing verificationThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.