review

name	review
description	Code review for PRs or staged changes. >80% confidence threshold. Verdict: APPROVE, REQUEST CHANGES, or COMMENT. Triggers: review, pr, code review.
user-invocable	true
allowed-tools	Read, Bash, Grep, Glob
kernel	{"kind":"validator","version":1,"side_effects":"none","confirmation":"none"}

Review code changes for quality, correctness, security. Only report issues with >80% confidence.

Load: skills/testing/SKILL.md, skills/security/SKILL.md Reference: _meta/research/ai-code-anti-patterns.md

ai_code_stats: buggier: 1.7x more issues than human code security: 40-62% contain vulnerabilities findings: 10.83 per AI PR vs 6.45 human

priority: check Big 5 first (what AI actually breaks)

<on_start>

agentdb read-start

<identify_scope>

gh pr diff {number}        # For PRs
git diff --staged          # For staged
git diff HEAD~1            # For recent

</identify_scope> </on_start>

<confidence_threshold>

Confidence	Category	Report?
95%+	Definite bug	YES
85-95%	Likely issue	YES
70-85%	Possible issue	MAYBE
<70%	Style preference	NO
</confidence_threshold>

Check these FIRST - what AI actually breaks: - Zod/Pydantic schema for every API endpoint? - Parameterized queries (no string concat)? - File uploads validated (size, type, extension)? detection: grep -r "req\.body" | grep -v "parse\|validate\|z\." - Null/undefined handling present? - Empty arrays handled (length check)? - Zero-length strings rejected? - Timeout handling for external calls? - No empty catch blocks? - Errors logged with context? - User-facing messages generic? detection: grep -r "catch.*{}" (empty catch) - Same logic repeated in multiple places? - Should be extracted to shared utility? - Functions > 30 lines? - Nested ternaries > 2 levels?

- [ ] Edge cases handled - [ ] Error paths covered - [ ] Null checks present - [ ] Type safety

- [ ] Input validation (Zod schema) - [ ] No hardcoded secrets - [ ] SQL injection prevented (parameterized queries) - [ ] XSS prevented (DOMPurify) - [ ] Auth tokens in httpOnly cookies

- [ ] No N+1 queries - [ ] Appropriate caching

<output_format> CODE REVIEW

Files: X changed Findings: Y (Z critical)

CRITICAL

[file:line] Issue (confidence: XX%) → Fix: suggestion

HIGH

[file:line] Issue (confidence: XX%) → Fix: suggestion

Summary: APPROVE | REQUEST CHANGES | COMMENT </output_format>

<ask_user> Use AskUserQuestion when: a finding is between 70-85% confidence (ambiguous) Ask: "Found {issue} at {file:line} (confidence {X}%). Intentional, or should I flag it?" Options: intentional — skip, flag it, investigate deeper </ask_user>

<verdict_rules>

• APPROVE: No critical or high issues
• REQUEST CHANGES: Any critical or high issue
• COMMENT: Only medium/low issues </verdict_rules>

<on_complete>

agentdb write-end '{"command":"review","verdict":"X","critical":N,"high":N,"big5_violations":N}'

</on_complete>