Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 435,888 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.

anysearch

673

anysearch-ai/anysearch-skill

Skill Claude CodeCodex

Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.

not rated 6.8k +21 changed 2mo ago A 24 tokens original Apache-2.0

rewardkit

674

harbor-framework/harbor

Skill Claude CodeCodex

Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward score.

not rated 6.8k +146 changed 3d ago A Socket: passSnyk: passSkillSpector: pass 46 tokens original Apache-2.0

darwin-skill

675

alchaincyf/darwin-skill

Skill Claude Code

An automated workflow for evaluating and improving SKILL.md files, which are instruction files for coding-agent add-ons. It scores their structure and tests whether edits improve actual results.

not rated 6.8k +80 changed 1mo ago A 195 tokens original MIT

autoresearch

676

uditgoenka/autoresearch

Plugin Claude Code

Bundles 5 hooks

Autonomous improvement engine. 14 commands: iterate, plan, debug, fix, security, ship, scenario, predict, learn, reason, probe, improve, evals, regression.

not rated 6.8k +25 changed 6d ago A tokens not measured original MIT

workspace-dispatch

677

outsourc-e/hermes-workspace

Skill Claude CodeCodex

Single-agent mission orchestrator. Decomposes a mission into tasks, spawns one worker per task using the default model, verifies exit criteria, and chains tasks with retry. No critic pattern — each worker self-verifies. Simple, fast, works with any model config.

not rated 6.8k +18 yesterday A SkillSpector: warn 59 tokens original MIT

node-crawler

678

bda-research/node-crawler

Skill Claude CodeCodex

Node.js web crawler for production-grade, large-scale tasks — NOT for simple one-off requests. Use only when: bulk scraping, batch downloading, multi-page crawling, long-running spiders, or complex multi-step workflows that need connection pooling, rate limiting, proxy rotation, automatic retries, and Cheerio parsing.…

not rated 6.8k +1 4mo ago A SkillSpector: pass 115 tokens original MIT

lieflat-charts

679

larashero3-dotcom/lieflat-charts

Skill Codex

A template-based tool for making data visualizations and publishable HTML reports. It can use real implementations from included chart galleries and choose from 12 full-page report templates based on the data’s meaning.

not rated 6.7k +208 changed 3d ago A 125 tokens

dev-browser

680

SawyerHood/dev-browser

Skill Claude CodeCodex

Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, log into sites, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot"…

not rated 6.7k +12 changed 2mo ago A Socket: passSnyk: warnSkillSpector: pass 98 tokens original MIT

clawrouter

681

BlockRunAI/ClawRouter

Skill Claude CodeCodex

Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 91 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. Free open-weight models included. Also exposes realtime market data…

not rated 6.7k +4 changed yesterday A SkillSpector: warn 171 tokens original MIT

osmedeus-expert

682

j3ssie/osmedeus

Skill Claude CodeCodex

Expert guide for the Osmedeus security automation workflow engine. Use when: (1) writing or editing YAML workflows (modules and flows), (2) running osmedeus CLI commands (scan, workflow management, installation, server), (3) configuring steps, runners, triggers, or template variables, (4) debugging workflow execution…

not rated 6.6k +10 1mo ago A SkillSpector: warn 113 tokens original MIT

n8n-mcp-skills

683

czlonkowski/n8n-skills

Plugin Claude Code

Bundles 15 skills · 2,472 tokens together

Complete bundle: 14 expert skills for building flawless n8n workflows with the n8n-mcp MCP server — and deploying the self-hosted n8n that runs them (expression syntax, MCP tools usage, workflow patterns, validation, node configuration, JavaScript code, Python code, the AI-agent Custom Code Tool, production error…

not rated 6.6k +37 changed 13d ago A tokens not measured original MIT

create-ex

684

therealXiaomanChu/ex-skill

Skill Claude Code

A tool for turning an ex-partner’s messages, photos, and social posts into an AI skill with stored relationship memories and a conversational persona. It supports English and Chinese and can update the result with new information.

not rated 6.6k +7 7mo ago C 69 tokens original MIT

orval

685

orval-labs/orval

Skill Claude CodeCodex needs its repo

Generate type-safe API clients, TanStack Query/SWR hooks, Zod schemas, MSW mocks, Hono server handlers, MCP servers, and SolidStart actions from OpenAPI specs using Orval. Covers all clients (React/Vue/Svelte/Solid/Angular Query, Fetch, Axios), custom HTTP mutators, authentication patterns, NDJSON streaming…

not rated 6.6k +10 yesterday A Socket: passSnyk: passSkillSpector: warn 83 tokens original MIT

sync

686

wechatsync/Wechatsync

Plugin Claude Code

Bundles 1 skill, 4 commands · 167 tokens together

Sync articles to 20+ content platforms (Zhihu, Juejin, CSDN, Toutiao, Weibo, etc.).

not rated 6.6k +30 14d ago A tokens not measured GPL-3.0

genkit-ai/genkit

Skill Claude CodeCodex needs its repo

Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency guidelines.

not rated 6.6k +7 yesterday A SkillSpector: pass 35 tokens original Apache-2.0

monke-testing-guide

688

airweave-ai/airweave

Cursor rule Cursor

Monke is Airweave's end-to-end testing framework for source connectors. It creates real test data in external systems, triggers syncs, and verifies data appears correctly in the search index.

not rated 6.5k +2 5mo ago A 7,424 tokens original MIT archived

xcodebuildmcp-cli

689

getsentry/XcodeBuildMCP

Skill Claude CodeCodex

Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).

not rated 6.5k 6d ago A Socket: passSnyk: passSkillSpector: pass 48 tokens original MIT

preline-mcp

691

htmlstreamofficial/preline

Skill Codex

Add, integrate, or build Preline UI components and blocks into HTML files via the Preline MCP server. Use when the user mentions "preline", says "/preline", asks to add a UI component, or requests a Preline block (a ready-made page section) using Preline UI.

not rated 6.5k +6 2mo ago A SkillSpector: warn 66 tokens

feishu-create-doc

692

op7418/CodePilot

Skill Claude CodeCodex

A skill for creating Feishu cloud documents from Lark-flavoured Markdown, a Feishu-specific form of plain-text document formatting.

not rated 6.5k +5 1mo ago A SkillSpector: pass 40 tokens

loopx-project

693

huangruiteng/loopx

Skill Codex

Use when connecting a repository or project goal document to LoopX, maintaining project-local goal state, refreshing stale dashboard status, syncing local projects into the shared global registry, or diagnosing LoopX CLI/PATH/status/history issues across multiple repos. For registering durable project materials such…

not rated 6.5k changed 1mo ago A SkillSpector: warn 74 tokens original Apache-2.0

code-migration

694

kucherenko/jscpd

Skill Claude CodeCodex

Move code from one implementation to another function by function, tests first and code second, and check two implementations of one app for parity, with jscpd --compare as the progress measure and a coverage map binding each function to its tests. Use when porting a library or app to another language or framework…

not rated 6.5k +32 changed 1mo ago A 110 tokens original MIT

defense-evasion

695

PurpleAILAB/Decepticon

Skill Claude Code

Endpoint defense bypass — AMSI/ETW patching, ScareCrow framework, custom loaders, direct/indirect syscalls, LOLBAS execution, process injection.

not rated 6.5k 8d ago A SkillSpector: warn 40 tokens original Apache-2.0

swiftui-pro

696

twostraws/SwiftUI-Agent-Skill

Plugin Claude Code

Bundles 1 skill · 36 tokens together

Reviews SwiftUI code for best practices on modern APIs, maintainability, and performance.

not rated 6.5k +53 11d ago A tokens not measured copy · 94% MIT

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: