Use when editing a long file (100+ lines of changes) or when an Edit call freezes, times out, or silently fails - requires splitting large edits into multiple smaller sequential Edit calls
Use when a feature branch is ready for merge — orchestrates PR creation, spec/quality check, review-loop, test-completeness, Copilot review, Codex review, doc consistency, conflict check, and CI verification in a strict sequential pipeline
Use when code changes need iterative multi-round review until no Critical or Important issues remain, with isolated independent reviewers, verification of findings, and parallel review after fixes
Use when you need to audit whether tests are complete for a project or PR — checks good case, bad case, boundary cases, 100% coverage, unit/integration/e2e test layers, then proposes and generates missing tests
Winrey's personal Claude Code plugin — a collection of custom skills.
Iterative multi-round code review with isolated subagents.
Dispatches independent reviewer subagents → screens and verifies findings → fixes confirmed issues → parallel dual-path re-review (fix diff + full review) → repeats until no Critical or Important issues remain.
Add the marketplace and install:
claude plugin marketplace add winrey/claude-code-toolkit
claude plugin install winrey-toolkit
To update later:
claude plugin update winrey-toolkit
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub winrey/claude-code-toolkit --plugin winrey-toolkitCode review plugin with a standalone reviewer agent and two skill strategies: disposable subagents for one-shot reviews and persistent team members for iterative reviews
Code review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in pull requests.
Codex-powered code review gate. Creates a review checkpoint that triggers Codex CLI review when Claude exits.
Command-driven Claude/Codex review workflows for multi-round plan and implementation review.
Multi-lens code review pipeline: deep review (Claude or Codex), automated fix loop, interactive walkthrough, manual promote, external-finding injection.
Automated code review loop: Claude implements, Codex reviews independently, Claude addresses feedback