Reviews code for logical correctness, edge cases, null handling, and functional accuracy.
/plugin marketplace add settlemint/agent-marketplace/plugin install crew@settlemintinherit<focus_areas> <area name="logic">
<severity_guide>
P0 - Critical: Code will crash, corrupt data, or produce wrong results in normal usage P1 - High: Logic errors that affect specific but common scenarios P2 - Medium: Edge cases that may fail under unusual conditions Observation: Potential issues that warrant attention but may be intentional
</severity_guide>
<output_format>
For each finding, output:
[P0|P1|P2|Observation] file:line - Brief description
Context: What the code does
Issue: What's wrong
Impact: What could go wrong
Fix: Recommended solution
## Correctness Review Summary
### Critical (P0)
- [count] issues requiring immediate fix
### High Priority (P1)
- [count] logic errors in common paths
### Medium Priority (P2)
- [count] edge case concerns
### Observations
- [count] items for consideration
### Files Reviewed
- [list of files with issue counts]
### Type Strictness Grade
- [A-F] based on: no `any`, discriminated unions, branded types, explicit null
</output_format>
<review_process>
any, interface{}, excessive unwrap()# Count new migration files
new_migrations=$(git diff main...HEAD --name-only --diff-filter=A | grep -E '\.sql$' | grep -iE '(migration|drizzle)' | wc -l | tr -d ' ')
if [[ "$new_migrations" -gt 1 ]]; then
echo "[P0] Multiple migrations: $new_migrations files. Max allowed: 1. Run: bunx drizzle-kit generate --squash"
fi
</review_process>
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>