19,479 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
systemfsoftware/comment-checker
Plugin Claude Code
Bundles 17 skills, 1 hook · 608 tokens together
PostToolUse hook that flags unnecessary comments. Runs comment-checker, then direnv exec if it is missing. Names flake.nix when that is why it is missing.
paritytech/polkadot-ios-community
Plugin Claude Code
Bundles 4 skills · 94 tokens together
Architect / Implementer / Reviewer / Commit-message skills for the PolkadotApp codebase.
avariza/solo-agent-vs-hive-mind
Skill Claude Code
Comprehensive GitHub code review with AI-powered swarm coordination.
hekmon8/awesome-claude-code-plugins
Plugin Claude Code
Bundles 2 skills, 10 commands, 1 agent · 301 tokens together
A bridge that lets Claude Code send coding tasks to DeepSeek Harness for review, criticism, or delegation.
Plugin Cursor
Tiered AI code-review: triage -> relevant specialist reviewers -> synthesis. Reviews AI-written code using AI agents.
Plugin Claude Code
Bundles 11 skills · 1,135 tokens together
General-purpose agent skills from TypeFox. They capture engineering practices, development workflows, and writing guidance that apply across codebases.
Skill Claude Code
Review a PR with JIRA validation, architecture checks, impact analysis, and interactive recommendations.
MCP server Cursor
One of 10 in mcp.json
Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package.
Skill Claude CodeCodex
Apply Agent Decision Comments when changing or reviewing code in repositories that use ADCs.
Plugin Claude Code
Bundles 5 skills · 462 tokens together
Apply Clean Code principles, refactoring patterns, and code smell detection.
Plugin Cursor
Bundles 1 skill, 1 MCP server · 61 tokens together
Checks AI-written code against your rules as it is written, and keeps a record of what it found.
Skill Claude Code
Use when you want one place to answer every question your agent threads ask — the human queue's control session. Registers this session as the desk, ticks the queue on a persistent Monitor, shows waiting Decisions as menus or long-form prompts, lets you discuss one, writes the answers, and wakes each asking thread.
Skill Claude Code needs its repo
Add a new user-facing slash command or discipline skill to the kit — use when creating a new /slashforge- entry point or workflow discipline, wiring it into the installer and snapshot.
vignesh2027/claude-best-practice
Agent Claude Code
Use for code review, PR review, security review. Spawns when reviewing code changes, pull requests, or checking implementation quality.
Skill Claude Code
Review code changes for security, performance, and style issues.
Agent Claude Code
Reviews Swift/SwiftUI code for quality, security, and performance. Use after any code changes.
DaviBonetto/multi-agent-skill-factory
Skill Claude CodeCodex
Goal: Add spec and plan document review loops to the brainstorming and writing-plans skills.
MCP server Claude CodeCodexCursor +2
Agent-first MCP. 11 AST adapters, 12 named languages, 51 tools, mission outcomes. Local. Runs locally from the projscan npm package.
Plugin Claude Code
Bundles 1 skill · 138 tokens together
Multi-agent codebase audit skill for Claude Code — spawns parallel subagents (security, performance, tests, architecture, dead-code) and synthesizes their findings into a prioritized action plan.
Skill Claude CodeCodex
Use when a leading diagnosis or nontrivial fix has initial support and needs one adversarial counterexample before acceptance.
Plugin Claude Code
Bundles 7 commands, 1 hook · 123 tokens together
Umbrella plugin: dispatch /ai:review|rescue|gater across configured providers, plus /ai:compare for fan-out.
Skill Claude Code
Backend security auditor for Django and DRF on an OWASP Top 10 (2025), API Security Top 10 (2023), and ASVS 5.0 foundation. Use when backend code is written or reviewed and touches authentication, sessions, cookies, JWT, OAuth2/OIDC, API keys, password hashing, permissions, access control, IDOR, SSRF, path traversal…
Skill Claude Code
Use when a full GitHub repository URL (github.com/owner/repo) appears in conversation, when the user asks to check, review, or analyze a GitHub repo, or when the user runs /gitgauge. Does not trigger on npm packages, file paths, org pages, or issue/PR links.
MCP server Claude CodeCodexCursor +2
Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package.
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: