Multi-agent code review plugin for GitLab merge requests. 10 specialized AI agents review accessibility, security, performance, SEO, styling, code quality, React, TypeScript, Git hygiene, and QA.
Remove all discussions and notes from a GitLab merge request
Follow-up review for a GitLab MR — evaluates addressed threads and resolves or replies
Prepare a branch for review — fetch, checkout, hard-reset to origin, and configure review agents
Run comprehensive code review on a GitLab merge request using 10 specialized agents
Review the merge request for accessibility (a11y) issues.
You are a discussion classifier agent. Your job is to fetch all unresolved discussion threads on a GitLab MR, classify each by developer intent, and extract structured data for addressed threads.
Review the merge request for code quality, readability, and maintainability.
Discover project architecture, conventions, and patterns to provide context for code review agents.
You are an MR data fetcher agent. Your job is to fetch MR metadata and diffs and return structured data.
Uses power tools
Uses Bash, Write, or Edit tools
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.
A multi-agent code review plugin for Claude Code that reviews GitLab merge requests across 10 specialized domains.
| Agent | Focus Area | Blocking Criteria |
|---|---|---|
| 🦯 Colorblind Sissy | Accessibility | WCAG A/AA violations |
| 🔒 SecuSissy | Security | XSS, exposed secrets, auth bypass |
| ⚡ TurboSissy | Performance | Memory leaks, N+1 queries |
| 🌐 Canonical Sissy | SEO | Hidden content, missing meta tags |
| 🎨 ChicSissy | Styling | Design system violations, broken layouts |
| 🧹 KISS Sissy | Code Quality | Massive functions, unmaintainable code |
| ⚛️ Hooked Sissy | React | Missing cleanup, missing keys |
| 📝 Unknown Sissy | TypeScript | any types, unsafe assertions |
| 📚 Detached-HEAD Sissy | Git | Secrets in commits |
| ✅ BugSlayer Sissy | QA | Missing requirements, critical bugs |
claude plugins install sissy-code-review-squad
Install the plugin (see above)
Copy the configuration template to your project:
cp node_modules/sissy-code-review-squad/templates/review-config.yml .claude/review-config.yml
Run a review on any GitLab MR:
/sissy-code-review-squad:sissy-squad https://gitlab.com/your-org/your-project/-/merge_requests/123
That's it! The squad will review your MR and post comments directly to GitLab.
Edit .claude/review-config.yml to enable/disable agents:
agents:
accessibility:
enabled: true
security:
enabled: true
performance:
enabled: true
seo:
enabled: false # Disable for non-web projects
styling:
enabled: true
code-quality:
enabled: true
react:
enabled: true
typescript:
enabled: true
git:
enabled: true
qa:
enabled: true
All review comments use consistent severity prefixes:
| Prefix | Meaning | Blocking? |
|---|---|---|
❗ [blocking] | Must fix before merge | Yes |
💡 [suggestion] | Recommended improvement | No |
💅 [nit] | Style preference | No |
❓ [question] | Needs clarification | No |
For best results, create these files in your project's .claude/rules/ directory:
| File | Purpose |
|---|---|
tech-stack.md | Your project's technology stack (React, Next.js, TypeScript, etc.) |
component-boilerplate.md | Component patterns and conventions |
services-guideline.md | Service layer patterns |
data-flow.md | Data architecture and state management |
These files help the Discovery agent provide project-specific context to reviewers.
Note: Some agents (React, TypeScript, Code Quality, Styling) will check for these files and provide more targeted feedback when they exist. If files are missing, agents gracefully continue with generic best practices.
┌─────────────────────────────────────────────────────────────┐
│ CODE REVIEW PIPELINE │
├─────────────────────────────────────────────────────────────┤
│ │
│ 1. PARSE MR METADATA │
│ └── Extract project ID and MR IID from URL │
│ │
│ 2. LOAD CONFIGURATION │
│ └── Read .claude/review-config.yml │
│ │
│ 3. FETCH MR DATA │
│ └── Get MR details + diffs from GitLab │
│ │
│ 4. ARCHITECTURE DISCOVERY │
│ └── Gather project context from .claude/rules/ │
│ │
│ 5. PARALLEL REVIEW │
│ └── All enabled agents review simultaneously │
│ │
│ 6. SUMMARY │
│ └── Post aggregated summary to MR │
│ │
└─────────────────────────────────────────────────────────────┘
Make sure you have the GitLab MCP server configured in your Claude Code settings:
{
"mcpServers": {
"gitlab-mcp": {
"command": "npx",
"args": ["-y", "@anthropic/gitlab-mcp"],
"env": {
"GITLAB_TOKEN": "your-gitlab-token",
"GITLAB_URL": "https://gitlab.com"
}
}
}
}
npx claudepluginhub milad-afkhami/sissy-code-review-squad --plugin sissy-code-review-squadComprehensive 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.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.