Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By avovello
Code review with focused investigation and parallel specialized reviewers for security, architecture, performance, and bug detection
npx claudepluginhub avovello/cc-plugins --plugin reviewReviews code changes for architecture violations. Receives an investigation report and analyzes dependency flow, layer violations, coupling, and service boundaries. Use after an investigator has produced a report.
Reviews code changes for logic errors, bugs, and incorrect behavior. Receives an investigation report and analyzes for definite bugs, type errors, missing error handling, and incorrect logic. Use after an investigator has produced a report.
Investigates a specific git commit to produce a structured investigation report for review agents. Use as Phase 1 when reviewing an existing commit.
Investigates uncommitted code changes (staged and unstaged) to produce a structured investigation report for review agents. Use as Phase 1 when reviewing local changes before commit.
Reviews code changes for performance issues. Receives an investigation report and analyzes for N+1 queries, missing indexes, algorithmic complexity, resource leaks, and unbounded operations. Use after an investigator has produced a report.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Reflective code review toolkit with structured analysis, blast radius analysis, domain expertise, and intelligent review orchestration
Comprehensive code review with architecture, security, and PR enhancement
Automated code review with severity levels and actionable feedback
Verify code, architecture, and bug fixes through factored multi-agent verification
Configurable code review with radical candor - choose between harsh direct feedback or constructive caring criticism. Features Technical.md for project standards, architectural context analysis, actionable fixes, decision register for tracking review decisions, seamless todo integration, and live browser QA via Chrome.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Quality assurance orchestrator with dynamic skill discovery, prompt-based routing, and do-loop agent teams for test writing, execution, and browser testing
Claude Certified Architect – Foundations exam preparation with interactive training, mock exam simulation, and performance analysis
Systematic bug fixing with reproduction, root cause analysis, and team-based fix+review loops
Systematic feature development with codebase exploration, architecture design, and team-based implementation loops (SOLID, Clean Architecture, Design Patterns, DDD)
Core development workflow plugins for Claude Code with specialized agents, Task tool orchestration, and architecture skills.
CC Plugins provides 6 plugins with 10 specialized agents, 7 commands, and 19 skills covering software development workflows and certification exam preparation.
Bugfix and feature-development plugins use Claude Code Agent Teams for iterative do-loops (doer+critic pairs). Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.
All agents use YAML frontmatter for proper Claude Code registration and are callable via Task(subagent_type="plugin:agent").
Reusable agent team infrastructure. Dependency for bugfix and feature-development.
| Component | Type | Purpose |
|---|---|---|
do-loop | Skill | Iteration protocol for doer+critic agent team loops |
Command: /feature "Add OAuth2 authentication"
Discovery → Exploration → Questions → Architecture Loop → Implementation Loop → Test Loop → Summary
| Component | Type | Purpose |
|---|---|---|
code-architect | Agent | Architecture design reference (SOLID, Clean Arch, Patterns, DDD) |
solid-principles | Skill | SOLID design principles |
clean-architecture | Skill | Layered architecture independent of frameworks |
design-patterns | Skill | Common design patterns |
domain-driven-design | Skill | DDD strategic and tactical patterns |
clarifying-questions | Skill | Structured ambiguity resolution |
review-loop | Skill | Code review guidelines for reviewer teammate |
testing-loop | Skill | Test writing guidelines for test-writer teammate |
Command: /review, /review --commit <sha>, /review --pr <number>
Two-phase review: investigate first (broad tools), then 4 specialized reviewers analyze in parallel (narrow tools). Reports only issues with confidence >= 80.
| Component | Type | Purpose |
|---|---|---|
diff-investigator | Agent | Investigate uncommitted changes |
commit-investigator | Agent | Investigate a specific commit |
pr-investigator | Agent | Investigate a pull request |
security-reviewer | Agent | Injection, auth, secrets, input validation, crypto |
architecture-reviewer | Agent | Dependencies, layers, coupling, boundaries |
performance-reviewer | Agent | N+1 queries, indexes, O(n²), resource leaks |
bug-reviewer | Agent | Logic errors, type issues, error handling, data integrity |
Command: /bugfix "Login fails with special characters"
Investigate (subagents) → Fix+Review (team loop) → Test+Review (team loop) → Verify
| Component | Type | Purpose |
|---|---|---|
reproducer | Agent | Reproduce bugs, create failing tests |
root-cause-analyst | Agent | Trace execution, identify root cause, propose fix |
regression-test | Skill | Writing effective regression tests |
Command: /qa <prompt>
Single orchestrator with dynamic skill discovery, prompt-based routing, and do-loop agent teams. Routes to run, write, explore, or convert workflows based on your prompt. Bare /qa runs all tests.
| Component | Type | Purpose |
|---|---|---|
unit-testing | Skill | Unit testing patterns and framework detection |
integration-testing | Skill | Integration testing patterns |
e2e-testing | Skill | E2E and browser testing with Playwright |
Commands: /training, /quiz, /analysis, /update
Claude Certified Architect – Foundations exam preparation. Interactive training by domain, mock exam simulation with weighted scoring, performance analysis with adaptive study recommendations, and content freshness checks.
| Component | Type | Purpose |
|---|---|---|
domain-1-agentic-architecture | Skill | Training curriculum for Domain 1 (27%) |
domain-2-tool-design-mcp | Skill | Training curriculum for Domain 2 (18%) |
domain-3-claude-code-config | Skill | Training curriculum for Domain 3 (20%) |
domain-4-prompt-engineering | Skill | Training curriculum for Domain 4 (20%) |
domain-5-context-management | Skill | Training curriculum for Domain 5 (15%) |
scoring | Skill | Scoring formula and question selection algorithm |
study-path | Skill | Adaptive study recommendation engine |
cd your-project
claude
# Install a specific plugin
/plugin install https://github.com/avovello/cc-plugins.git#plugins/review
git clone https://github.com/avovello/cc-plugins.git
cp -r cc-plugins/plugins/review .claude/plugins/