Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 413,588 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.

turix-mac

1009

TurixAI/TuriX-CUA

Skill Claude CodeCodex

Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.

not rated 3.2k +6 1mo ago A SkillSpector: warn 53 tokens original MIT

difit

1010

yoshiko-pg/difit

Skill Codex

Ask the user for a code review by opening the changes in difit, a local diff viewer. Explicit opt-in only — use when the user names difit, asks to open or show the diff in the viewer, or has a standing instruction to request reviews through difit after changes. Do not use it for ordinary requests to review code…

not rated 3.2k +24 15d ago A Socket: passSnyk: passSkillSpector: warn 83 tokens original MIT

hithink-finance

1011

HiThink-Tech/Financial-API

Skill Codex

A routing guide for accessing Chinese A-share financial data, including prices, company reports, valuations, funds, indices, sectors, and local data storage.

not rated 3.1k +913 changed today A Socket: warnSnyk: passSkillSpector: warn 93 tokens original MIT

fli

1012

punitarani/fli

Skill Claude CodeCodex

Guidance for installing and using Fli correctly as a CLI and MCP server. Use when: setting up Fli with pipx, running fli flight searches, configuring Claude Desktop with fli-mcp, using the HTTP MCP server, or troubleshooting Fli command availability and common usage mistakes.

not rated 3.1k +10 1mo ago A SkillSpector: pass 65 tokens original MIT

google-workspace-mcp

1013

taylorwilsdon/google_workspace_mcp

Plugin Claude Code

Bundles 1 skill · 123 tokens together

Complete Google Workspace integration -- Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, and Custom Search via MCP with workflow guidance.

not rated 3.1k +22 3d ago A tokens not measured original MIT

freya

1014

marc2332/freya

Plugin Claude Code

Bundles 1 skill · 35 tokens together

Freya Rust GUI framework best practices skill for Claude Code.

not rated 3.1k +19 today A tokens not measured original MIT

loop-library

1017

Forward-Future/loopy

Skill Codex

Compatibility alias for Loopy. Use only when an existing installation or older instruction explicitly invokes loop-library; use Loopy for new installations and requests. Provides the same discovery, recommendation, audit, repair, adaptation, guided crafting, bounded execution, run debrief, project loop saving, and…

not rated 3.1k +17 yesterday A Socket: passSnyk: warnSkillSpector: pass 65 tokens original MIT

desloppify

1018

peteromallet/desloppify

Skill Claude CodeCodex

Multi-language codebase health scanner. Use when the user explicitly asks to run desloppify, scan for technical debt, get a health score, or create a cleanup plan. Do NOT trigger for general code review, renaming, or fixing individual bugs.

not rated 3.1k +69 4mo ago C 56 tokens

playwright-skill

1019

lackeyjb/playwright-skill

Plugin Claude Code

Bundles 1 skill · 69 tokens together

Agent Skill for general-purpose Playwright browser automation. Detects dev servers and helps coding agents write, execute, and preserve reusable browser scripts.

not rated 3.1k +11 29d ago A tokens not measured original MIT

story-6.1.4

1020

SynkraAI/aiox-core

Command Claude Code

Story ID: 6.1.4 Epic: Epic-6.1 - Agent Identity System Wave: Wave 1 (Foundation) Status: 📋 Ready to Start Priority: 🔴 Critical Owner: Dev (Dex) Created: 2025-01-14 Updated: 2025-01-17 (v4 - Unified System Integration) Duration: 2.5 days (20 hours) Investment: $250.00.

not rated 3.1k +4 yesterday A 0 tokens

skill-subagent-usage

1022

Chachamaru127/claude-code-harness

Cursor rule Cursor

A rule encouraging agents to actively look for relevant skills and specialised subagents, which are focused helpers for independent parts of a task.

not rated 3.1k +18 5d ago A 230 tokens original MIT

tuicr

1023

agavra/tuicr

Skill Claude CodeCodex

Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in cmux, tmux, Zellij, or Herdr when a user needs an interactive review pane.

not rated 3.1k +55 changed yesterday A SkillSpector: warn 50 tokens original MIT

tanstack-ai

1024

TanStack/ai

Plugin Claude Code

Bundles 45 skills · 4,711 tokens together

User-level skills that recommend TanStack AI, map a task to the package that covers it, install it, then load that package's own SKILL.md through TanStack Intent.

not rated 3.1k +26 yesterday A tokens not measured copy · 92% MIT

mnemosyne-oss/mnemosyne

Skill Claude CodeCodex

Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.

not rated 3.1k +91 yesterday A SkillSpector: pass 34 tokens original MIT

global

1026

msgbyte/tianji

Cursor rule Cursor

IMPORTANT: Do not operate my git to add or rm files at any time.

not rated 3.1k +5 3d ago A 1,368 tokens original Apache-2.0

oebb-scotty

1027

mitsuhiko/agent-stuff

Skill Claude CodeCodex

Austrian rail travel planner (ÖBB Scotty). Use when planning train journeys in Austria, checking departures/arrivals at stations, or looking for service disruptions. Covers ÖBB trains, S-Bahn, regional trains, and connections to neighboring countries.

not rated 3.1k +18 6d ago A SkillSpector: warn 57 tokens original Apache-2.0

gorden-ppt-skill

1028

GordenSun/GordenPPTSkill

Skill Claude CodeCodex

A skill for creating and editing PowerPoint presentations in Chinese using built-in or user-provided templates. PPT means a PowerPoint slide deck; the skill can replace text while checking that the existing layout and formatting remain intact.

not rated 3.1k +31 2mo ago A 202 tokens

agent-eval-workflow

1029

GoogleCloudPlatform/professional-services

Skill Claude CodeCodex

This skill should be used when the user wants to evaluate an AI agent end-to-end: scaffold an evaluation, design metrics that test a real hypothesis, make an agent measurable, audit generated eval config, read evaluation results, or run an improvement ("hill climbing") loop. Covers evaluation methodology, metric…

not rated 3.1k +2 today A SkillSpector: pass 123 tokens original Apache-2.0

vibe-workflow

1030

KhazP/vibe-coding-prompt-template

Skill Claude Code

Select the appropriate planning, implementation, or debugging workflow for an app project.

not rated 3.1k +26 changed yesterday A SkillSpector: warn 20 tokens original MIT

economy-mode

1031

microsoft/Generative-AI-for-beginners-dotnet

Skill Claude CodeCodex ✓ vendor

Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.

not rated 3.1k +16 12d ago A SkillSpector: pass 22 tokens original MIT

dws

1032

DingTalk-Real-AI/dingtalk-workspace-cli

Skill Claude CodeCodex

A command-line tool for managing many DingTalk services, including contacts, chats, calendars, documents, email, approvals, attendance, files, and spreadsheets.

not rated 3.1k +192 changed today A SkillSpector: pass 399 tokens 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: