Code Review & Refactor Plugins
168 code review & refactor Claude plugins for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.
#Type
- 1skillsMatt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.Jul 2026
- 2ponytailLazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.Jul 2026
- 3understand-anythingAI-powered codebase understanding — analyze, visualize, and explain any projectJul 2026
- 4open-code-reviewOpen-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.Jul 2026
- 5improvePoint it at a codebase and it figures out what's worth doing — bugs, perf, tech debt, what to build next — then writes plans any agent can execute. It can hand the work to a cheaper model and review the result. It never edits your code.Jun 2026
- 6plannotatorAnnotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.Jul 2026
- 7repowiseCodebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.Jul 2026
- 8socraticodeCodebase intelligence — semantic search workflows, dependency graph analysis, and context artifact exploration for SocratiCodeJul 2026
- 9sentruxReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.Mar 2026
- 10cocoindex-codeAST-based semantic code search via the ccc CLI. Bundles the ccc skill; Grok installs also activate a SessionStart index hook and MCP server (disable either for skill-only).Jul 2026
- 11humanizeHumanize - An iterative development plugin that uses Codex to review Claude's work. Creates a feedback loop where Claude implements plans and Codex independently reviews progress, ensuring quality through continuous refinement.Jul 2026
- 12repobrainRepository knowledge engine plugin. Bundles CLI-backed slash commands (rb-setup / rb-init / rb-refresh / rb-ask) plus the agent-repo-init skill. Works in both Claude Code and Codex CLI.Jul 2026
- 13brooks-lintAI code reviews grounded in twelve classic engineering books — decay risk diagnostics with book citations, severity labels, and six analysis modes (PR review, architecture audit, tech debt, test quality, health dashboard, full-sweep auto-fix)Jul 2026
- 14claude-delegatorGPT expert subagents for Claude Code via Codex CLI. Five specialized experts: Architect, Plan Reviewer, Scope Analyst, Code Reviewer, Security Analyst.Mar 2026
- 15skillsSentry-specific agent skills for code review, commits, and moreJul 2026
- 16critYour feedback loop with the agentJul 2026
- 17aegisCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniquesJul 2026
- 18paperjuryPre-submission AI review and editing for CS-conference papers: direct-edit LaTeX or Markdown (Word via one-time extraction), run an adversarial multi-agent courtroom review with consensus-gated revisions, or run it unattended toward a goal.Jun 2026
- 19revdiffReview diffs, files, and documents with inline annotations in a TUI overlayJul 2026
- 20claude-skills-marketplaceClaude Code Skills for software engineering workflows - Git automation, testing, and code reviewJul 2026
- 21claude-code-skillsFocused engineering review, audit, optimization, testing, discovery, and maintainer skills.Jul 2026
- 22modularityDesign and analyze modular software systems using the Balanced Coupling model by Vlad Khononov. Includes a modularity review skill for analyzing existing codebases and a modular design skill for designing new systems from requirements.Apr 2026
- 23repo-analyzerDeep architectural analysis of open-source projects with professional reportsApr 2026
- 24andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfallsApr 2026
- 25agnixThe missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes.Jul 2026
- 26lean4-skillsLean 4 theorem proving skill and workflow pack for AI coding agentsJul 2026
- 27genieWishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.Jul 2026
- 28open-code-reviewAI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.Jun 2026
- 29linus-torvalds-skillsAggressive AI coding guidelines recast through Linus Torvalds' blunt, data-first engineering styleApr 2026
- 30greenfieldReverse engineer clean behavioral specs from any codebaseJul 2026
- 31agent-reviewsManage GitHub PR review comments. Automatically triage, fix, and respond to review findings.Jul 2026
- 32ringLerian Studio plugin marketplace: Core software engineering skills (TDD, debugging, code review), specialized developer agents (Backend, DevOps, Frontend, QA, SRE) plus 12 code-review reviewers (9 default hard-gate reviewers and 3 conditional stack specialists), product planning…Jul 2026
- 33gem-teamTurn AI coding into an engineering process.Jul 2026
- 34claude-rulesInitialize or update CLAUDE.md coding standards for any project by auto-detecting tech stack and assembling rules from the claude-rules template library. Use when user says 'init rules', 'generate CLAUDE.md', or wants to set up coding standards.Mar 2026
- 35codex-skillGive Claude Code a second opinion using OpenAI Codex - automatic plan review via hooksJul 2026
- 36hanA curated marketplace of Claude Code plugins that embody the principles of ethical and professional software development.Jul 2026
- 37sd0x-dev-flowHarness engineering for Claude Code — hook-enforced review gates, state-machine gates, and fail-closed safety where it counts.Jul 2026
- 38latticeComposable AI skills framework covering the full software delivery lifecycle — design, architecture, implementation, testing, and review.Jul 2026
- 39suede-creator-skillsComplete Suede workflow for Claude Code and Codex: Full Send orchestration, reviewed multi-agent execution, code and release gates, design, copy, SEO, app shipping, and creator utilities. Installs all 28 skills.Jul 2026
- 40skillsAI-powered code review in Claude Code, powered by CodeRabbitJul 2026
- 41senior-engineering-partnerA strict code reviewer, pair programmer, debugger, and mentor for Python, Bash, Google Apps Script, and JavaScript — a security-first, phase-aware engineering discipline with an enforced spec → plan → TDD → verify workflow.Jul 2026
- 42claude-code-configBattle-tested configuration system for Claude Code agents: 28 architectural principles (incl. P-28 Feature-Layer Architecture for project-knowledge-as-a-navigable-tree), 19 safety hooks, 23 skills (incl.Jul 2026
- 43skill-conductorCreate, edit, evaluate, and package Claude Code agent skills — full draft→test→review→improve lifecycle.Jul 2026
- 44mattpocock-skills-zhMatt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.Jul 2026
- 45fallow-skillsAgent skills for fallow, codebase intelligence for TypeScript and JavaScript. Teaches AI agents how to find unused code, duplication, circular deps, complexity hotspots, architecture drift, design-system drift, and (with Fallow Runtime) hot-path and cold-path evidence.Jul 2026
- 46claudekitVerification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements.Jul 2026
- 47buddyPersistent AI coding companion with 21 species and personality stats.Jul 2026
- 48claude-caliperA Claude workflow that measures twice and cuts onceJul 2026
- 49launchworthyProduction readiness audit for apps built with AI coding tools. Detects your stack, audits 5 domains, and produces a scored punch list with copy-paste fixes.Jul 2026
- 50frontierStandards written and audited by Claude Fable 5: make Opus, Sonnet, GPT, or Gemini produce work close to its bar. 21 craft rubrics, best-of-N candidates, convergence sweeps, a taste gate with permanent distillation.Jul 2026
- 51beagleAgent Skills marketplace: framework-aware skills for code review, documentation, test-plan generation, AI-writing detection, architectural analysis, and git workflows — for Python, Go, Rust, Elixir, React, Remix, and iOS/Swift.Jul 2026
- 52ai-software-architectAI-powered architecture documentation framework with ADRs, reviews, and pragmatic modeJul 2026
- 53espalier-engineeringTrain your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as rules, skills, agents, hooks, and a guided pipeline so generated code lands inside your conventions on the first try, not the fifthJul 2026
- 54claude-leveragePersonal Claude Code + Codex dev stack: security hooks, AI-first code conventions, /security-review, /repo-map, /stack-check, portable statusline. Designed to complement other skills-based plugins, not replace them.Jul 2026
- 55better-code-review-graphKnowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.Jul 2026
- 56correctlessThe agent that writes the code never reviews it. Spec-driven TDD with agent separation, adversarial QA, and dynamic rigor for Claude Code.Jul 2026
- 57backpressuredDrive a goal to completion autonomously while enforcing backpressure (lint, tests, verification) at every step.May 2026
- 58claude-war-roomInstant, reliable context for any legacy codebase — reverse-engineering into living docs, plus a multi-agent War Room to hunt down the risks.Jun 2026
- 59codebase-argusMulti-agent PR, CI, and downstream fork-sync review desk for Claude Code.Jul 2026
- 60codescene-mcp-serverThe CodeScene MCP Server exposes CodeScene’s Code Health analysis as local AI-friendly tools.Jul 2026
- 61deep-implementImplement code from /deep-plan sections with TDD, code review, and git workflowJun 2026
- 62claude-pluginAI-powered code review in Claude Code, powered by CodeRabbitApr 2026
- 63conductor_ccConductor: Context-driven development for Claude Code - Measure twice, code onceJun 2026
- 64agile_v_skillsVerifiable AI-Augmented Engineering framework with traceable requirements, independent verification, and compliance-ready artifactsJul 2026
- 65agentlintCheck how well your repo supports AI coding agents.Jul 2026
- 66ai-literacy-superpowersA set of Claude Code and GitHub Copilot plugins providing the AI Literacy framework's complete development workflow — harness engineering, agent orchestration, literate programming, CUPID code review, and the three enforcement loopsJul 2026
- 67beacon-pluginBeacon — semantic code search for Claude CodeMar 2026
- 68claude-git-pr-skillProfessional GitHub PR review skills for Claude CodeDec 2025
- 69pdca-agentic-coding-frameworkHuman-supervised AI code generation using Plan-Do-Check-Act methodology with TDD and refactoring. Works as Claude Code skill or standalone prompts.Jul 2026
- 70cc-settingsDarkroom Engineering AI coding standards. Layered config with portable AGENTS.md, progressive complexity, and two-tier knowledge system.Jul 2026
- 71meet-reviewer-2Rigorous, fair peer review in two modes. (A) Red-team your OWN draft before you submit — a simulated panel (a generous champion, the brutal Reviewer 2, a novelty-hawk Area Chair) predicts the reviews and hands you a prioritized fix list.Jun 2026
- 72coco-searchLocal-first hybrid semantic code search with dependency graphs and cross-repo search. Powered by CocoIndex, Tree-sitter, pgvector, and Ollama.Jul 2026
- 73tale-modeA discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adversarial review, and a self-armed loop that keeps going until a real check passes.Jul 2026
- 74ai-craftsman-superpowersSenior craftsman methodology for AI-assisted development. DDD, Clean Architecture, TDD, and systematic workflows that transform Claude into a disciplined software engineer.Jul 2026
- 75solidifierSOLID principles and design patterns for backend code — applied with restraint. Skill for Claude Code, OpenCode, GitHub Copilot, and OpenAI Codex.Jul 2026
- 76roslyn-codelens-mcpRoslyn-based MCP server giving AI agents deep semantic understanding of .NET/C# codebases — 57 tools for navigation, call graphs, diagnostics & code fixes, code-quality auditing, test intelligence, DI graphs, and IL/external-assembly inspection.Jul 2026
- 77yoinkyoink is an AI agent that removes complex dependencies by reimplementing only what you need.Apr 2026
- 78odin-claude-pluginODIN - advanced code agent with diagram-first engineering and atomic commit workflows for surgical precision in software developmentJul 2026
- 79andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.May 2026
- 80codestoryCodeStory is a codebase grounding engine that preindexes code into a knowledge graph and enriches it with semantic context. Paired with coding agents, it results in fewer tokens, fewer tool calls, and remains 100% local.Jul 2026
- 81pi-plugin-ccDrive the Pi coding agent from Claude Code or Codex: multi-model review panels, model racing, incremental & sharded reviews, automatic model fallback, /pi:rescue with parallel subagent fan-out. Any provider (DeepSeek/OpenAI/Anthropic/local). Adapted from codex-plugin-cc.Jul 2026
- 82nuclear-grade-context-engineeringRisk-graded context engineering for AI-assisted software work — a catalog of agent skills, paste-ready command prompts, and change-record templates that keep agent work questioned, controlled, and reviewable.Jul 2026
- 83codingbuddyCodingbuddy orchestrates 29 specialized AI agents to deliver code quality comparable to a team of human experts through a PLAN → ACT → EVAL workflow.Apr 2026
- 84fluencyloopStay fluent in the code your AI agent writes with a per-feature design, build, teaching, and review loop.Jul 2026
- 85ai-native-toolkitSkills for AI-native development. /assess scores a codebase's readiness for AI agent contributors (0-8 layered contract model) and generates a Codecov-style complexity hotspot SVG plus a colour-blind-safe doc-navigability graph.Jul 2026
- 86codebase-recon-skillAnalyze git history to understand a codebase before reading any code. Reveals hotspots, risk areas, team structure, and development momentum.Apr 2026
- 87blockwatchLanguage agnostic linter that keeps your code and documentation in sync and validJul 2026
- 88agent-review-panelMulti-agent adversarial review panel — 4-6 AI reviewers debate your code/plans, then a judge delivers a structured verdict with epistemic labels. Bundles plan-review-integrator for applying review findings back into implementation plans.Jul 2026
- 89claude-consensusMulti-model consensus code review and plan review plugin for Claude CodeJul 2026
- 90claude-codeRefactored fork of the sourcemap-leaked Claude Code CLIJul 2026
- 91grok-plugin-claude-codeA lightweight Grok plugin for Claude Code — delegate coding and review tasks to the Grok CLI. A simple reimplementation of OpenAI's codex-plugin-cc.Jun 2026
- 9297Skills distilled from the hard-won lessons of world-renowned programmers, in the spirit of '97 Things Every Programmer Should Know'. Your coding agent invokes them when about to refactor, write a test, design an API, or commit.May 2026
- 93do-itMeaning-centric engineering plugin for Claude Code: tier routing, advisory write-quality, focused review, and evidence-backed completion.Jul 2026
- 94refactoringDisciplined refactoring using small, verifiable steps based on Fowler's 'Refactoring' and Feathers' 'Working Effectively with Legacy Code'Jan 2026
- 95roslynmcpserverRoslyn-powered C# refactoring MCP server — 41 tools for code navigation, analysis, generation, and refactoring across entire .NET solutionsMar 2026
- 96se-cove-claude-pluginVerify code, architecture, and bug fixes through factored multi-agent verificationJan 2026
- 97lsp-marketplaceCurated collection of Claude Code plugins: LSP tools for 28 programming languages with automated hooks for linting, formatting, security, and code qualityFeb 2026
- 98gobbyAST-aware code search, symbol navigation, and dependency graph analysisJul 2026
- 99senior-dev-skillsSenior-level Claude Code skills by theSeniorDevJun 2026
- 100claude-rubycritic-skillClaude Code Skill for Ruby code quality analysis with RubyCritic. Model-invoked - Claude autonomously analyzes code quality, identifies smells, and provides refactoring insights.Nov 2025
