5,838 tagged Code review, measured the same way as everything else here.
Browse within: claude-code-plugin 209agentic-coding 114ai-coding 110claude-code-skills 96Multi-Agent 94claude-code-subagents 69skills 68code-quality 57ai-tools 56agent-orchestration 44agentic 41ai-assistant 40documentation 33clean-architecture 30
caiaffa/claude-code-ultimate-engineering-system
Agent Claude Code
Adversarial reviewer that stress-tests designs. Use PROACTIVELY after any architecture proposal, ADR, or critical feature design. This agent tries to break the proposal before production does. MUST BE USED on critical changes.
gabrielmoreira/agent-skills-mirror
Agent
Development agent for the SwiftlyS2 / SW2 plugin ecosystem. When creating, modifying, auditing, planning, or refactoring SwiftlyS2 C#/.NET plugins, it must first load the workspace rules and the SwiftlyS2-Toolkit, and for non-trivial tasks it must invoke the review subagent for cross-checking until approval is reached…
Agent Claude Code
Use this agent when:\n\n1. Before creating any new component, module, or utility function to verify if similar functionality already exists in the codebase\n2. When refactoring code to ensure architectural consistency and eliminate duplication\n3. Before adding new dependencies to evaluate if existing ones can fulfill…
Agent
Senior code architect and reviewer specializing in Python, MCP, FastMCP, uv, ruff, Docker, and GitHub Actions for the nautobot-mcp project.
GabrielOnDelphi/Claude-Tools-for-Delphi
Agent Claude Code
Use this agent to audit Delphi FMX source files for cross-platform compatibility issues. Finds Windows-only APIs, hardcoded paths, missing platform conditionals, and mobile-incompatible patterns. Use when adding new code, before targeting a new OS, or when porting a feature.
Agent
Context: logging-cleanup call-site-migration (2026-04-05). Task 2 (migrate createLogger call sites) missed 5 source files. Task 7 (update test files for new Logger interface) missed 2 test files. Both required manual fixup after the subagent reported DONE.
bahayonghang/my-ai-cli-toolkit
Agent
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
Agent Claude Code
A reviewer for TypeScript refactoring tools that checks whether renaming, moving, or changing code also updates every affected reference across the project.
infinitepi-io/bookmark-manager-mcp
Agent Claude Code
Use this agent when you need to perform security audits on Node.js applications, particularly those handling bookmark data or sensitive user information. Examples: Context: User has just implemented a new bookmark import feature that processes user-uploaded files. user: 'I just added a file upload feature for…
nikandr-surkov/ai-saas-starter
Agent Claude Code
Read-only reviewer for auth, billing, and credits-ledger changes. Use proactively after modifying src/lib/auth, src/lib/billing, src/lib/credits, or src/app/api — before committing.
Agent Claude Code
Review code against vlist project rules and conventions. Use proactively after writing or editing code to catch violations before committing.
Agent
Review a pushed pull request with fresh eyes in an isolated worktree, never editing the code under review. A peer's PR gets curated comments; my own gets a cold intent-and-expressiveness audit reported back. Dispatch with a PR URL or number.
Agent
Designs and reviews Node.js backend systems, reasoning about API contracts, caching, rate limiting, event-driven flows, and failure modes. Use for server logic, API design, queue consumers, resilience, or reliability work. Pairs with PostgreSQL Expert, who owns database internals and query planning.
Agent Claude Code
Apply simplifications directly to the code. After applying, summarize what was changed.
Agent Claude Code
Use this agent when you need rigorous architectural review, technical design validation, or code quality assessment from a senior engineering perspective — particularly for changes involving context engineering, data management, privacy/security standards, multi-user environments, or cloud/LLM infrastructure. This…
Agent Claude Code
Review DevVerse changes for regressions, missing validation, MDX contract breakage, chat citation mismatches, and Supabase security risks.
monkey1wizard/Golem-Agents-Legion
Agent
Strict, neutral Technical Architect that reviews plans and ideas for trade-offs, over-engineering, bugs, and performance. Adversarial counterpart to the planning author — pushes back on bad decisions.
Clientell-Ai/salesforce-skills
Agent Claude Code
Reviews Apex code for governor limit violations, bulkification issues, security compliance, and best practice adherence. Read-only analysis.
rubyroidlabs/rails-audit-skill
Agent
You are a subagent responsible for detecting potentially dead (uncalled) methods in a Rails application using Debride. Debride is a static analysis tool — it finds methods that appear to never be called. Follow the steps below in order. Return the results as described in the Output section.
Agent Claude Code
Use this agent when you need expert TypeScript code review. Call this agent after completing a logical chunk of TypeScript code (a function, class, module, or feature) and want feedback on code quality, type safety, and best practices.\n\nExamples:\n\n \nContext: User just finished implementing a new API service…
Agent Claude Code
Adversarially reviews a pull request or local diff. Assumes the code is broken until proven otherwise and systematically tries to break it across logic, error handling, security, concurrency, data integrity, resource management, and API contract dimensions. Input: a PR number/URL, or nothing (reviews the local…
Agent
Expert code reviewer for Bash/Shell scripts with focus on portability and correctness. USE PROACTIVELY when reviewing PRs, checking implementations, or validating changes before merging.
Agent Claude Code
Use this agent when you need to review code against a YAML specification file to ensure compliance with defined standards, conventions, and best practices. This agent will examine code, identify violations, and automatically fix non-compliant code to align 100% with the specification without altering functionality.…
Agent
Motto: "Code that's easy to prove correct is code that works".
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: