Agent Claude Code
Identifies dead code introduced or exposed by changes — unused functions, unreachable paths, orphaned imports, parameters without callers, and code made obsolete by refactors.
Agent Claude Code
Stress-test conclusions using structured criticism. Accepts a document path or inline text. Returns STAND/REVISE/ESCALATE verdict with a findings document.
Agent Claude Code
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 (0.85+), evidence-gated.
Agent Claude Code
Documentation drift review — detects when code changes cause README, CLAUDE.md, AGENTS.md, API docs, or guides to become stale.
Agent Claude Code
Playwright E2E test quality review for locator strategies, Page Object Model, auto-waiting, network interception, and WordPress/WooCommerce test helpers.
Agent Claude Code
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 Claude Code
Cross-validates PR changes using Google Gemini CLI for independent perspective on code quality, bugs, and security.
Agent Claude Code
Go test quality review for standard testing package patterns, table-driven tests, test helpers, httptest, benchmarks, and interface-based mocking.
Agent Claude Code
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 Claude Code
JavaScript/TypeScript test quality review for Jest/Vitest assertions, React Testing Library queries, module mocking, async patterns, and snapshot discipline.
Agent Claude Code
Explores codebase and git history for existing patterns, prevents reinventing the wheel, ensures consistency, and identifies consolidation opportunities.
Agent Claude Code
WordPress performance-focused code review for database queries, caching, asset loading, and scalability issues.
Agent Claude Code
PHP test quality review for PHPUnit assertions, WordPress test utilities (WPUnitTestCase, factories), WooCommerce test patterns, and Brain Monkey isolation.
Agent Claude Code
Python test quality review for pytest fixtures, parametrize, mock/patch patterns, pytest-asyncio, hypothesis property-based testing, and factoryboy.
Agent Claude Code
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 Claude Code
Operational resilience code review for logging, error handling, rollback safety, feature flags, and failure-mode handling.
Agent Claude Code
Adapter that runs a reviewer prompt contributed by the repository under review (declared in .pirategoat/config.json) and normalizes its output into pirategoat's standard findings format. Dispatched once per declared repo reviewer, parameterized with a reference to that reviewer's prompt. Not for direct use.
Agent Claude Code
Consumes pre-gathered reconciliation context (all agent findings, source snippets, scope annotations), performs semantic deduplication, scope checking, and fact verification in one pass, then produces clean review findings.
Agent Claude Code
Rust test quality review for built-in test framework patterns, assert macros, async tests, mockall, proptest, rstest, insta snapshots, criterion benchmarks, and serialtest isolation.
Agent Claude Code
WordPress security-focused code review for sanitization, escaping, nonces, capabilities, SQL injection, and data exposure.
Agent Claude Code
Reviews code changes for unnecessary complexity — over-abstraction, premature generalization, defensive code for impossible cases, unnecessary indirection, and verbose logic where concise alternatives exist.
Agent Claude Code
Creates documentation - use after feature completion.
Agent Claude Code
Adversarial mutation testing that temporarily mutates production code to verify tests catch real bugs. Must run SOLO (no other review agents). Integrates with reconciliation workflow.
Agent Claude Code
Developer toolchain review for package manager configs, build tools, linting configs, version constraints, CI pipelines, and supply chain settings — actively searches changelogs for deprecations and behavior changes.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: