Agent
Accessibility code review for ARIA correctness, keyboard operability, focus management, screen reader announcements (speak(), aria-live), and WCAG 2.2 AA compliance — covers React/JS components, server-rendered markup (PHP/HTML/templates), and non-visual a11y features in hooks/utilities.
Agent
API contract stability review for backwards-incompatible REST changes, hook/filter argument or caller-side return handling breaks, established runtime behavior, response shape drift, and missing deprecation.
Agent
Software architecture code review for design patterns, SOLID principles, coupling, cohesion, and architectural decisions.
Agent
Code clarity review for naming accuracy, documentation correctness, and intent communication — flags names that lie, docs that contradict code, and semantic confusion that builds wrong mental models.
Agent
Reviews code changes for real issues in context of stated goals. Supports full review or focused review of specific commits.
Agent
Cross-validates PR changes using OpenAI Codex CLI for independent perspective, leveraging its dedicated review command.
Agent
Concurrency and race condition code review for TOCTOU patterns, missing transactions, cache stampede, non-idempotent operations, and concurrent state corruption.
Agent
Data flow and privacy code review for PII in logs, data leakage in API responses, GDPR erasure gaps, payment data handling, and cross-boundary data flow.
Agent
Identifies dead code introduced or exposed by changes — unused functions, unreachable paths, orphaned imports, parameters without callers, and code made obsolete by refactors.
Agent
Stress-test conclusions using structured criticism. Accepts a document path or inline text. Returns STAND/REVISE/ESCALATE verdict with a findings document.
Agent
Questions the fundamental approach of substantial PRs — reframes problems to find simpler, more direct solutions when strong technical evidence supports an alternative. High confidence threshold (85+), evidence-gated.
Agent
Documentation drift review — detects when code changes cause README, CLAUDE.md, AGENTS.md, API docs, or guides to become stale.
Agent
Playwright E2E test quality review for locator strategies, Page Object Model, auto-waiting, network interception, and WordPress/WooCommerce test helpers.
Agent
Integration-correctness and behavioral-alignment review against upstream source — verifies filter/action callback signatures, class override correctness (abstract implementations, final/visibility), REST route schemas, and behavioral assumptions (state, timing, return-value semantics, ordering) by reading Host Context…
Agent
Cross-validates PR changes using Google Gemini CLI for independent perspective on code quality, bugs, and security.
Agent
Go test quality review for standard testing package patterns, table-driven tests, test helpers, httptest, benchmarks, and interface-based mocking.
Agent
Mines git history and GitHub PRs for fixes, enhancements, and lessons learned from similar scenarios elsewhere in the codebase — surfaces what the team already knows.
Agent
JavaScript/TypeScript test quality review for Jest/Vitest assertions, React Testing Library queries, module mocking, async patterns, and snapshot discipline.
Agent
Explores codebase and git history for existing patterns, prevents reinventing the wheel, ensures consistency, and identifies consolidation opportunities.
Agent
WordPress performance-focused code review for database queries, caching, asset loading, and scalability issues.
Agent
PHP test quality review for PHPUnit assertions, WordPress test utilities (WPUnitTestCase, factories), WooCommerce test patterns, and Brain Monkey isolation.
Agent
Python test quality review for pytest fixtures, parametrize, mock/patch patterns, pytest-asyncio, hypothesis property-based testing, and factoryboy.
Agent
Verifies that references in code — plugin slugs, asset paths, URLs, constants, hook names — actually resolve to existing targets, whether internal (codebase files, classes) or external (registries, endpoints).
Agent
Operational resilience code review for logging, error handling, rollback safety, feature flags, and failure-mode handling.