Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 438,333 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.

deck-factory

9481

gongnyang/deck-factory

Plugin Claude Code

Bundles 1 skill · 456 tokens together

Presentation-grade dark-editorial HTML deck design system, packaged as a Claude Code skill. One line of intent → a deck that looks like it came out of a real keynote.

not rated 83 +3 4mo ago A tokens not measured original MIT

gearlynx-debugging

9482

drhelius/Gearlynx

Skill Claude CodeCodex

Debug and trace Atari Lynx games using the Gearlynx emulator MCP server. Provides workflows for 6502 CPU debugging, breakpoint management, hardware inspection, disassembly analysis, and execution tracing. Use when the user wants to debug a Lynx game, trace code execution, inspect CPU registers or hardware state, set…

not rated 83 +2 changed 24d ago A 137 tokens GPL-3.0

dotfiles-bootstrap

9483

sebastienrousseau/dotfiles

Skill Claude CodeCodex

Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot config init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.

not rated 83 +1 changed 19d ago A SkillSpector: pass 89 tokens original Apache-2.0

reduce

9484

escoffier-labs/brigade

Skill Claude CodeCodex

Use when asked to simplify, clean up, tidy, or refactor code for clarity without changing what it does, or when the user says "simplify this", "clean this up", "make it readable", "reduce the complexity", or "tidy this". Behavior-preserving only; not a bug or security audit (use bug-hunt or security-sweep for those).

not rated 83 +1 changed 13d ago A SkillSpector: pass 79 tokens original MIT

efremidze/swift-architecture-skill

Plugin Claude Code

Bundles 1 skill, 1 hook · 65 tokens together

Swift iOS architecture guidance and playbooks for MVVM, MVI, TCA, Clean Architecture, VIPER, MVP, Coordinator, and Reactive patterns. Use when designing, implementing, refactoring, or reviewing the architecture of a SwiftUI or UIKit feature, module, or codebase.

not rated 83 +2 1mo ago A tokens not measured original MIT

cursor

9486

brendanciccone/storysync

Cursor rule Cursor

Sync Storybook components and design tokens from code to Figma with storysync, measuring each variant's rendered styles rather than inferring them. Use when pushing a component library to Figma, scoring what landed against what rendered, or auditing drift between code and a Figma file.

not rated 83 +8 changed 1mo ago A 56 tokens original MIT

fleetq-connect

9487

escapeboy/agent-fleet-o

Skill Claude CodeCodex

Connect an agent to FleetQ over MCP or the REST API, including obtaining credentials via dynamic client registration.

not rated 83 +2 today A 25 tokens AGPL-3.0

lili_persona

9491

mcxxiu/lily

Skill Claude CodeCodex

A Chinese-language chat role-play persona with a specified teenage, homebound character and deliberately provocative personality.

not rated 83 +1 6mo ago A 64 tokens AGPL-3.0

pagespeed-insights-mcp

9492

ruslanlap/pagespeed-insights-mcp

MCP server Claude CodeCodexCursor +2

Google PageSpeed Insights and CrUX: six workflow tools for web performance. Runs locally from the pagespeed-insights-mcp npm package. Needs 1 environment variable to run.

not rated 83 +3 yesterday A tokens not measured original Apache-2.0

deepline-ads-audiences

9493

getaero-io/gtm-eng-skills

Skill Claude CodeCodex

Use this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Match, Meta/Facebook Custom Audiences, or LinkedIn Matched Audiences. Triggers on phrases like '/deepline-ads-audience', '/deepline-ads-audiences', 'upload this audience', 'create custom audiences', 'personal…

not rated 83 +8 changed yesterday A SkillSpector: warn 133 tokens original MIT

execbro

9495

igorzheludkov/execbro

MCP server Claude CodeCodexCursor +2

Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots. Runs locally from the execbro npm package. Needs 1 environment variable to run.

not rated 83 +2 yesterday A tokens not measured

using-open-artifacts

9496

coda0HQ/open-artifacts

Skill Claude CodeCodex

Publish and maintain self-contained HTML, Markdown, or React artifacts as shareable URLs. Use when a user asks to publish a report, writeup, dashboard, prototype, visualization, or document; update an existing artifact; inspect a published artifact; or review watched-source drift in .artifacts/manifest.json or…

not rated 83 +5 changed 27d ago A SkillSpector: warn 147 tokens original MIT

speech-mcp

9497

Kvadratni/speech-mcp

MCP server Claude CodeCodexCursor +2

Speech MCP Server with command-line interface and Kokoro TTS support. Runs locally from the speech-mcp Python package.

not rated 83 1y ago A tokens not measured original MIT

crud-checklist

9498

nylas/cli

Command Claude Code needs its repo

Complete checklist for generating a full CRUD command package.

not rated 83 +1 14d ago A 0 tokens original MIT

icloud-mcp

9499

MrGo2/icloud-mcp

MCP server Claude CodeCodexCursor +2

Apple Mail, Calendar, Contacts, Reminders, Notes, Messages and Safari via AppleScript or iCloud. Runs locally from the mcp-icloud npm package. Needs 3 environment variables to run.

not rated 83 +3 2d ago A tokens not measured original MIT

laravel-audit

9500

MrPunyapal/laravel-auditor

Skill Claude CodeCodex

Perform a deep, structured, evidence-based audit of a Laravel application and produce actionable findings backed by concrete project evidence. Use when asked to audit, review, assess, or evaluate an existing Laravel codebase.

not rated 83 +21 changed 1mo ago A SkillSpector: pass 46 tokens original MIT

illusion-usage

9501

YunTaiHua/illusion-agent

Skill Claude CodeCodex

Dual-purpose guide for agents. Scenario A — agent autonomously drives IllusionAgent via non-interactive print mode (-p). Scenario B — agent helps its human master install and use IllusionAgent's interactive TUI/Web modes. Invoke when an agent needs to operate IllusionAgent, install it for a user, or teach a user how…

not rated 83 changed 19d ago A SkillSpector: warn 76 tokens original MIT

timeboxed-execution

9502

wenjimods/timeboxed-execution

Skill Claude CodeCodex

Run deadline-bound or scope-sensitive agent tasks with explicit done conditions, protected verification time, evidence gates, and safe-stop rules. Use for rapid implementation, debugging, integration, delegated work, feasibility gates, or tasks where scope drift, false completion, repeated failure, or deadline…

not rated 83 2mo ago A 65 tokens original MIT

wave-executor

9503

9thLevelSoftware/legion

Skill Claude CodeCodex

Executes wave-structured plans with personality-injected agents — parallel or sequential per CLI adapter.

not rated 83 +1 2mo ago A 22 tokens

orbit

9504

Noveum/orbit

MCP server Claude CodeCodexCursor +2

Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs. Remote server at orbit.noveum.ai.

not rated 83 +3 today A tokens not measured original Apache-2.0

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: