ClaudeCodeMod

All shelves / Marketplaces

milad-afkhami/sissy-code-review-squad

milad-afkhami/sissy-code-review-squad ยท 0 stars ยท 1 plugin

Marketplace

Install

In Claude Code
/plugin marketplace add milad-afkhami/sissy-code-review-squad

Run inside Claude Code, then install plugins from it. Check the repo's README before you run it.

Open the repo

Plugins 1

After adding the marketplace, install one with /plugin install <name>@sissy-code-review-squad.

  1. 1sissy-code-review-squad10 specialized AI agents review accessibility, security, performance, SEO, styling, code quality, React, TypeScript, Git hygiene, and QA./plugin install sissy-code-review-squad@sissy-code-review-squadproductivity

Files

README.md

Sissy Code Review Squad

A multi-agent code review plugin for Claude Code and Codex CLI that reviews GitLab merge requests across 10 specialized domains.

The Squad

Agent Focus Area Blocking Criteria
๐Ÿฆฏ Colorblind Sissy Accessibility WCAG A/AA violations
๐Ÿ”’ SecuSissy Security XSS, exposed secrets, auth bypass
โšก TurboSissy Performance Memory leaks, N+1 queries
๐ŸŒ Canonical Sissy SEO Hidden content, missing meta tags
๐ŸŽจ ChicSissy Styling Design system violations, broken layouts
๐Ÿงน KISS Sissy Code Quality Massive functions, unmaintainable code
โš›๏ธ Hooked Sissy React Missing cleanup, missing keys
๐Ÿ“ Unknown Sissy TypeScript any types, unsafe assertions
๐Ÿ“š Detached-HEAD Sissy Git Secrets in commits
โœ… BugSlayer Sissy QA Missing requirements, critical bugs

Installation

Claude Code

claude plugins install sissy-code-review-squad

Codex CLI

codex plugin marketplace add milad-afkhami/sissy-code-review-squad --ref v2.5.1
codex plugin add sissy-code-review-squad@sissy-code-review-squad

Restart Codex after installation so it discovers the new skills.

Quick Start

  1. Install the plugin (see above)

  2. Run a review on any GitLab MR from either runtime:

    Claude Code:

    /sissy-code-review-squad:sissy-squad https://gitlab.com/your-org/your-project/-/merge_requests/123
    

    Codex CLI:

    $sissy-squad https://gitlab.com/your-org/your-project/-/merge_requests/123
    

On each run, a zenity dialog asks which agents to enable (saved to .sissy/review-config.yml). The squad then reviews the MR in an isolated git worktree โ€” your working tree, including uncommitted changes, is never touched โ€” and posts comments directly to GitLab.

When the developer replies to the threads, run the follow-up to verify the fixes:

/sissy-code-review-squad:follow-up-review https://gitlab.com/your-org/your-project/-/merge_requests/123
$follow-up-review https://gitlab.com/your-org/your-project/-/merge_requests/123

Both commands are self-contained: they provision the worktree from the MR's own source branch and remove it when done. There is no separate setup step.

Configuration

sissy-squad shows a zenity picker each run and writes your selection to .sissy/review-config.yml. You can also edit that file directly 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

When upgrading, if the neutral file is absent and .claude/review-config.yml exists, the next sissy-squad run copies the legacy file unchanged to .sissy/. The legacy file is left untouched; future picker saves use only .sissy/.

Comment Format

All review comments use consistent severity prefixes:

Prefix Meaning Blocking?
โ— [blocking] Must fix before merge Yes
๐Ÿ’ก [suggestion] Recommended improvement No
๐Ÿ’… [nit] Style preference No
โ“ [question] Needs clarification No

Recommended Project Files

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.

How It Works

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚                    CODE REVIEW PIPELINE                     โ”‚
โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
โ”‚                                                             โ”‚
โ”‚  1. PARSE MR METADATA                                       โ”‚
โ”‚     โ””โ”€โ”€ Extract project ID and MR IID from URL              โ”‚
โ”‚                                                             โ”‚
โ”‚  2. CONFIGURE AGENTS                                        โ”‚
โ”‚     โ””โ”€โ”€ zenity picker โ†’ write .sissy/review-config.yml      โ”‚
โ”‚                                                             โ”‚
โ”‚  3. FETCH MR DATA                                           โ”‚
โ”‚     โ””โ”€โ”€ Get MR details + diffs (incl. source branch)        โ”‚
โ”‚                                                             โ”‚
โ”‚  4. PROVISION WORKTREE                                      โ”‚
โ”‚     โ””โ”€โ”€ Detached mirror of origin/<source_branch> in /tmp   โ”‚
โ”‚         (your working tree is never touched)                โ”‚
โ”‚                                                             โ”‚
โ”‚  5. ARCHITECTURE DISCOVERY                                  โ”‚
โ”‚     โ””โ”€โ”€ Gather project context from the worktree            โ”‚
โ”‚                                                             โ”‚
โ”‚  6. PARALLEL REVIEW                                         โ”‚
โ”‚     โ””โ”€โ”€ All enabled agents review simultaneously            โ”‚
โ”‚                                                             โ”‚
โ”‚  7. SUMMARY + CLEANUP                                       โ”‚
โ”‚     โ””โ”€โ”€ Post summary to MR, then remove the worktree        โ”‚
โ”‚                                                             โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

Prerequisites

  • Claude Code CLI (v1.0.0 or later) or Codex CLI with plugin support
  • Git (any version with worktree support โ€” 2.5+)
  • GitLab MCP Server configured with access token
  • GitLab Project with merge requests
  • zenity โ€” for the agent-selection dialog (sudo apt install zenity; if absent, the review falls back to your existing .sissy/review-config.yml)
  • notify-send (libnotify) โ€” for the completion desktop notification (optional)

GitLab MCP Setup

The plugin uses the GitLab MCP server already configured in the runtime; it does not install or own the server or its credentials. For Codex, verify the existing configuration with codex mcp list. For Claude Code, a configuration has this shape:

{
  "mcpServers": {
    "gitlab-mcp": {
      "command": "npx",
      "args": ["-y", "@anthropic/gitlab-mcp"],
      "env": {
        "GITLAB_TOKEN": "your-gitlab-token",
        "GITLAB_URL": "https://gitlab.com"
      }
    }
  }
}

Commands

Runtime Command Description
Claude Code /sissy-code-review-squad:sissy-squad <MR_URL> Pick agents, provision a worktree, run the full review, clean up
Codex CLI $sissy-squad <MR_URL> Run the same canonical initial-review workflow
Claude Code /sissy-code-review-squad:follow-up-review <MR_URL> Verify developer fixes on addressed threads and resolve/reply
Codex CLI $follow-up-review <MR_URL> Run the same canonical follow-up workflow
Claude Code only /sissy-code-review-squad:clear-mr-comments <MR_URL> Remove all Sissy discussions and notes from an MR

Example Output

After running the command, you'll see:

  1. Individual comments posted to specific lines in the MR
  2. Agent summary notes from each agent with their findings
  3. Final summary with aggregated results:
## Comprehensive Code Review Summary

### Review Results by Agent

| Agent | โ— Blocking | ๐Ÿ’ก Suggestions | ๐Ÿ’… Nits |
|-------|------------|----------------|---------|
| ๐Ÿฆฏ Colorblind Sissy | 1 | 3 | 2 |
| ๐Ÿ”’ SecuSissy | 0 | 1 | 0 |
| โšก TurboSissy | 0 | 2 | 1 |
| ... | ... | ... | ... |
| **Total** | **1** | **12** | **8** |

### Verdict
โš ๏ธ **CHANGES REQUESTED** - Blocking issues must be resolved

Troubleshooting

"Project not found" error

  • Verify the MR URL is correct and accessible
  • Check your GitLab token has read_api scope
  • Ensure the project path matches exactly

"No MR found for branch" error

  • The MR might not exist yet - create it first
  • Check if the MR is in a different state (closed, merged)

Agents not posting comments

  • Verify GitLab token has api scope (not just read_api)
  • Check if the MR allows comments from your account

Configuration not loading

  • Ensure .sissy/review-config.yml is valid YAML
  • Check the file path is exactly .sissy/review-config.yml

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for guidelines.

License

MIT License - see LICENSE for details.


Built with ๐Ÿ’œ for better code reviews

Facts

Kind
Marketplace
Repo
milad-afkhami/sissy-code-review-squad
Group
Uncategorized
Stars
0
Marketplace name
sissy-code-review-squad
Owner
Milad Afkhami
License
MIT
Language
Python
Created
2026-01-05
Last push
2026-10-11
Plugins
1

More on this shelf

  1. 1obra/superpowersobra/superpowersAn agentic skills framework & software development methodology that works.297.9k
  2. 2affaan-m/everything-claude-codeaffaan-m/ECCThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.277.5k
  3. 3anthropics/skillsanthropics/skillsPublic repository for Agent Skills180.6k
  4. 4f/prompts.chatf/prompts.chatf.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source โ€” self-host for your organization with complete privacy.172.7k
  5. 5anthropics/claude-codeanthropics/claude-codeClaude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.150.3k
  6. 6nextlevelbuilder/ui-ux-pro-max-skillnextlevelbuilder/ui-ux-pro-max-skillAn AI skill that provides design intelligence for building professional UI/UX across multiple platforms.135k