Code Review & Refactor Subagents
809 code review & refactor subagents for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.
#Type
- 1code-reviewerSenior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.Jul 2026
- 2code-reviewerMeticulous, constructive reviewer for correctness, clarity, security, and maintainability.Jul 2026
- 3code-reviewerExpert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategyJul 2026
- 4code-simplifierSimplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.Jul 2026
- 5criticWork plan and code review expert — thorough, structured, multi-perspective (Opus)Jul 2026
- 6godot-gdscript-specialistThe GDScript specialist owns all GDScript code quality: static typing enforcement, design patterns, signal architecture, coroutine patterns, performance optimization, and GDScript-specific idioms.…May 2026
- 7lead-programmerThe Lead Programmer owns code-level architecture, coding standards, code review, and the assignment of programming work to specialist programmers.May 2026
- 8ue-blueprint-specialistThe Blueprint specialist owns Blueprint architecture decisions, Blueprint/C++ boundary guidelines, Blueprint optimization, and ensures Blueprint graphs stay maintainable and performant. They prevent…May 2026
- 9unity-specialistThe Unity Engine Specialist is the authority on all Unity-specific patterns, APIs, and optimization techniques. They guide MonoBehaviour vs DOTS/ECS decisions, ensure proper use of Unity subsystems…May 2026
- 10unreal-specialistThe Unreal Engine Specialist is the authority on all Unreal-specific patterns, APIs, and optimization techniques. They guide Blueprint vs C++ decisions, ensure proper use of UE subsystems (GAS,…May 2026
- 11code-reviewerUse this agent when you need to review recently written or modified code for quality, security, and maintainability. This agent should be invoked immediately after code changes are made to ensure…Jul 2026
- 12trellis-checkCode quality check expert. Reviews code changes against specs and self-fixes issues.Jul 2026
- 13code-reviewerCode-review sub-agent. Reviews MemOS diffs for contract consistency, Ruff / typing / optional-dependency handling, and test evidence; returns APPROVE or CHANGES_REQUESTED.Jul 2026
- 14design-reviewerDesign-review sub-agent. Reviews design docs across the four dimensions of architecture, interface, performance, and security, covering MemOS's multi-memory / multi-storage backend constraints.Jul 2026
- 15architectReviews changes for how they fit the broader Uno Platform framework — flags tech debt, bad patterns, scalability issues, layering violations, and wrong platform-specialization choices. Use after a…Jul 2026
- 16contractReviews changes for contract stability — public API surface vs WinUI parity (binary/source compat, [Uno.NotImplemented] handling, DependencyProperty registration), public surface minimality, and test…Jul 2026
- 17jeromeThe Socratic questioner of the review panel — surfaces the questions the author didn't ask: unstated intent, hidden assumptions, unconsidered platform/parity alternatives, and missing evidence.Jul 2026
- 18operabilityReviews changes for diagnosability and resilience — structured logging discipline, CancellationToken propagation (incl. source generators), async-void safety, and the diagnosability of tooling…Jul 2026
- 19performanceAudits changes for performance hazards on all targets — blocking calls, async void time-bombs, source-generator allocation/cancellation discipline, layout/render hot-path allocations, property-system…Jul 2026
- 20qualityValidates that a change correctly addresses its stated requirement, evaluates solution elegance, checks for duplication across platform partials and missed refactoring, verifies sample/test coverage,…Jul 2026
- 21skepticChallenges decisions, questions assumptions, and surfaces edge cases other agents missed — with WinUI-parity and cross-platform correctness front of mind. Use after a completed change to stress-test…Jul 2026
- 22code-architecture-reviewerUse this agent when you need to review recently written code for adherence to best practices, architectural consistency, and system integration.Jul 2026
- 23code-refactor-masterUse this agent when you need to refactor code for better organization, cleaner architecture, or improved maintainability. This includes reorganizing file structures, breaking down large components…Jul 2026
- 24refactor-plannerUse this agent when you need to analyze code structure and create comprehensive refactoring plans. This agent should be used PROACTIVELY for any refactoring requests, including when users ask to…Jul 2026
- 25skill-reviewerFresh-context reviewer for Claude Ads skill and agent routing, progressive disclosure, prompt contracts, safety boundaries, examples, and runnable verification.Jul 2026
- 26code-reviewerMUST BE USED PROACTIVELY after writing or modifying any code. Reviews against project standards, TypeScript strict mode, and coding conventions. Checks for anti-patterns, security issues, and…Jan 2026
- 27simple-code-reviewerLightweight code reviewer for quick quality checks. Use PROACTIVELY after code changes to catch common issues.Jul 2026
- 28code-reviewerPre-commit code reviewer — checks for correctness, security, and MockServer conventions. Spawn this agent when you need a focused review of staged/unstaged changes before committing.Jul 2026
- 29review-cheapIntermediate deep reviewer for quality loops — non-authoritative PASS. Spawn this agent as a cost-effective first-pass review before escalating to review-final. Its PASS verdict is not binding.Jul 2026
- 30review-finalAuthoritative final reviewer — issues binding PASS/BLOCK verdicts. Spawn this agent as the last gate before committing. Its verdict is definitive. It reviews the full change set independently,…Jul 2026
- 31simplifierCode simplification specialist — reduces implementation changes to the smallest correct form. Spawn this agent after implementing a feature to remove over-engineering, dead code, and unnecessary…Jul 2026
- 32code-reviewerExpert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.Jul 2026
- 33powersync-sync-reviewerUse to review any change that touches PowerSync synced tables before merging — diffs that modify shared/powersync-tables.ts, a config.yaml sync rule, backend or frontend Drizzle schema,…Jul 2026
- 34react-effect-reviewerUse to review React (.tsx) changes for the project's useEffect discipline and React conventions before merging — flags effects used for derived state, prop→state syncing, parent notification,…Jul 2026
- 35review-fact-checkerVerify every factual claim in a review draft against vault sources. Returns verified/unverified/flagged claims.Jul 2026
- 36code-reviewerCode review expert for quality analysis, security vulnerabilities, and production reliabilityJul 2026
- 37criticFeature and implementation code reviewJan 2026
- 38phoenixRefactoring planning AND migration planningJan 2026
- 39research-codebaseDocument the codebase comprehensivelyJan 2026
- 40review-agentReview implementation by comparing plan (intent) vs Braintrust session (reality) vs git diff (changes)Jan 2026
- 41quality-fixerUse this agent when the user wants to fix all code quality issues in the project, including linting, formatting, and unused code detection.May 2026
- 42self-critic在完成阶段性工作后使用此 agent 进行"治病救人"式的工作审查。基于毛泽东"批评与自我批评"的方法论，对已完成的工作进行系统性审视，找出问题并提出改进建议。Jul 2026
- 43codebase-explorerDeep codebase exploration using SocratiCode. Combines semantic search, dependency graphs, and context artifacts to answer questions about code structure and behaviour.Jul 2026
- 44reviewerCode review specialist that verifies every finding against actual code before reporting. Use before committing, for PR reviews, or after major changes.Jul 2026
- 45skill-auditorAudit and fix Claude Code SKILL.md files against enterprise compliance standards: frontmatter completeness, required body sections, and style. Use when validating or repairing skills in a plugin…Jul 2026
- 46reviewerCode review specialist — analyzes code quality and suggests improvementsJul 2026
- 47alignment-reviewerReview code changes for bugs (Tier 1) and alignment with OpenEnv principles (Tier 2). Use when reviewing PRs or before committing.Jul 2026
- 48coder-reviewerUse this agent for code quality review of completed implementations — assessing maintainability, performance, test coverage, and standards compliance as the final quality gate before security review.Jul 2026
- 49code-auditorDelegates to this agent when the user wants a secure-code review of application source — static analysis for injection, auth, secrets, deserialization, and OWASP issues; SAST tooling guidance…Jun 2026
- 50code-reviewerUse this agent when you need to conduct comprehensive code reviews focusing on code quality, security vulnerabilities, and best practices.Jul 2026
- 51code-deduplicatorUse this agent when you need to identify and eliminate code duplication through systematic refactoring. Examples: <example>Context: User has written several similar functions with repeated logic…Apr 2026
- 52code-reviewerReviews code for ToolHive best practices, security patterns, Go conventions, and architectural consistencyJul 2026
- 53code-reviewerReviews TypeScript changes in this monorepo for correctness, security, and maintainability. Use after implementing a feature or before opening a PR.Jul 2026
- 54code-reviewer资深代码审查（Code Review）专家。主动审查代码的质量、安全性与可维护性。在编写或修改代码后立即使用。所有代码变更**必须使用**此工具。Mar 2026
- 55go-reviewer专家级 Go 代码审查员 (Expert Go code reviewer)，专注于地道的 Go 编写习惯、并发模式、错误处理和性能。适用于所有 Go 代码变更。Go 项目必须使用。Mar 2026
- 56python-reviewer专业的 Python 代码审查员，擅长 PEP 8 规范、Pythonic 惯用法、类型提示（Type Hints）、安全性与性能。适用于所有 Python 代码变更。在 Python 项目中必须使用（MUST BE USED）。Mar 2026
- 57refactor-cleaner冗余代码清理与合并专家。主动用于移除未使用的代码、重复项并进行重构。运行分析工具（knip、depcheck、ts-prune）来识别冗余代码并安全地将其移除。Mar 2026
- 58github-issue-fixerGitHub issue resolution specialist. Analyzes, plans, and implements fixes for GitHub issues with proper testing and PR creation. Use when fixing specific GitHub issues.Jul 2026
- 59pr-reviewerExpert code reviewer for GitHub pull requests. Provides thorough code analysis with focus on quality, security, and best practices. Use when reviewing PRs for code quality and potential issues.Jul 2026
- 60code-reviewerReview TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packagesJul 2026
- 61scout-report-suggestUse proactively to scout codebase issues, identify problem locations, and suggest resolutions. Specialist for read-only analysis and reporting without making changes.Feb 2026
- 62quarto-criticAdversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.Jun 2026
- 63quarto-fixerImplements fixes from the quarto-critic agent. Applies changes to QMD files, re-renders slides, and verifies fixes. Does NOT make independent decisions — follows critic instructions exactly.Jun 2026
- 64r-reviewerR code reviewer for academic scripts. Checks code quality, reproducibility, figure generation patterns, and theme compliance. Use after writing or modifying R scripts.Jun 2026
- 65code-reviewerDeprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.Jul 2026
- 66code-reviewerExpert code review specialist. Use PROACTIVELY after writing or modifying code, before commits, when asked to review changes, PR review, code quality check, lint, or standards audit. Focuses on…Jul 2026
- 67refactorerCode refactoring specialist for improving code quality, reducing technical debt, eliminating code smells, reducing complexity, and applying design patterns. Use PROACTIVELY when code needs…Jul 2026
- 68architecture-auditorSoftware architecture and design pattern specialist. Use PROACTIVELY when adding new features, refactoring code, or reviewing system design. MUST BE USED for architectural decisions and major code…Mar 2026
- 69code-auditorProactive code quality assurance specialist. MUST BE USED after any code changes to ensure quality, security, and performance standards. Use PROACTIVELY to review code quality, identify issues, and…Mar 2026
- 70READMEProfessional slash commands for Claude Code that provide structured workflows for software development tasks including code review, feature creation, security auditing, and architectural analysis.Mar 2026
- 71WORKFLOW_EXAMPLESProfessional slash commands for Claude Code that provide structured workflows for software development tasks including code review, feature creation, security auditing, and architectural analysis.Mar 2026
- 72sv-code-reviewerCorrectness + threading + minimality reviewer for a SceneView change. Filament JNI main-thread rule, Compose/SwiftUI idiom, behavior-preservation, edge cases. Read-only; ERROR = blocks merge.Jul 2026
- 73sv-impact-reviewerCross-platform public-API impact reviewer for SceneView. The autonomous-merge SAFETY GATE — a breaking public-API change or an unmirrored cross-platform divergence is an ERROR that BLOCKS auto-merge.…Jul 2026
- 74eval-curatorAuthors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that…Jul 2026
- 75code-reviewerExpert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.Jul 2026
- 76code-reviewerUse this agent when you need to review code for adherence to project conventions and best practices. Examples: <example>Context: User has just written a new React component and wants to ensure it…Apr 2026
- 77vc-code-reviewerComprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.Jun 2026
- 78vc-code-simplifierSimplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.Jun 2026
- 79code-simplifierSimplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.May 2026
- 80code-reviewerReview code changes for quality, security, and best practices. Proactively use this after code modifications.Jul 2026
- 81agent-refactorerPrincipal Clean Code Specialist specializing in code simplification, performance tuning, and refactoring loops.Jul 2026
- 82agent-reviewerSenior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.Jul 2026
- 83code-simplifier<!-- Based on Anthropic's code-simplifier subagent: https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-simplifier/agents/code-simplifier.md -->Jul 2026
- 84senpaiUse this agent when a user needs mentoring, guidance, or explanations about Sentry's infrastructure, engineering practices, or technical concepts as a new hire. Examples:Jul 2026
- 85backend-reviewerReview backend route and hook logic for regressions, data integrity risks, and missing tests.Jul 2026
- 86frontend-reviewerReview React UI changes for behavior regressions, state consistency, and UX breakage.Jul 2026
- 87code-quality-reviewerUse this agent when you need to review code for quality, maintainability, and adherence to best practices. Examples:\n\n- After implementing a new feature or function:\n user: 'I've just written a…Jul 2026
- 88arch-reviewerRead-only architecture reviewer. Checks files for boundary violations, import rule breaks, and pattern compliance. Does not modify files.Jul 2026
- 89code-reviewer코드 품질·보안·유지보수성 2단계 리뷰 (스펙 준수 → 코드 품질). 심각도 등급 이슈와 수정 제안 산출. Use proactively when 코드 변경 완료 후, PR 머지 전, "리뷰해줘" 요청 시. 보안 전용은 security-reviewer, DB 쿼리는 database-reviewer, 아키텍처 판단은 architect 사용.Jul 2026
- 90refactor-cleaner데드 코드·미사용 exports·의존성 제거, 중복 통합 전문. knip/depcheck/ts-prune 감지 → Grep 참조 검증 → 안전 제거. 피처 브랜치에서만 동작. Use proactively when "데드 코드", "미사용 코드", "정리해줘", "클린업", "리팩토링" 요청 시. 빌드 에러 수정은 build-error-resolver, 새…Jul 2026
- 91js-analyzerJavaScript static analysis agent for client-side security review. Use for analyzing JS bundles, finding hardcoded secrets, tracing DOM XSS source-sink flows, identifying postMessage handlers,…Jun 2026
- 92fixerUse for quick fixes, hotfixes, urgent patches, and time-sensitive bug repairs.Jul 2026
- 93refactorerCode refactoring and tech debt reduction. Use for improving code structure, extracting abstractions, reducing duplication, and improving maintainability without changing behavior.Jul 2026
- 94code-reviewerExpert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.Jan 2026
- 95refactor-cleanerDead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely…Jan 2026
- 96code-reviewerValidates Design Doc compliance and implementation completeness from third-party perspective. Use PROACTIVELY after implementation completes or when "review/implementation check/compliance" is…Jul 2026
- 97codebase-analyzerAnalyzes existing codebase objectively for facts about implementation, user behavior patterns, and technical architecture. Use when existing code needs to be understood without hypothesis bias.…Jul 2026
- 98quality-fixerSpecialized agent for fixing quality issues in software projects. Executes all verification and fixing tasks related to code quality, correctness guarantees, testing, and building in a completely…Jul 2026
- 99tdd-refactoring-agentImproves code structure while keeping all tests green during the TDD REFACTOR phase using proven refactoring patterns. Use proactively after tests pass to clean up implementation code. Use when…Jun 2026
- 100code-reviewerRead-only code review agent. Catches type issues, pattern violations, missing tests. Cannot modify files.Jul 2026
