Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 434,082 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.

npcpy-prompting

3577

NPC-Worldwide/npcsh

Skill Claude CodeCodex

Skill "npcpy-prompting" from NPC-Worldwide/npcsh, covering npcpy-prompting, imports, basic-call, json-mode and npc-object.

not rated 502 +2 5d ago A SkillSpector: pass 16 tokens original MIT

earn-hunter

3578

okx/agent-trade-kit

Skill Claude CodeCodex

A monitoring skill for OKX Earn products, which let users put supported cryptocurrency assets into flexible, fixed-term, or short-term earning programmes.

not rated 504 +4 changed 10d ago A SkillSpector: warn 114 tokens original MIT

ai-dial-ui-kit

3580

epam/ai-dial-chat

MCP server Claude CodeCodexCursor +2

One of 4 in .mcp.json

MCP server "ai-dial-ui-kit" as configured in epam/ai-dial-chat. Runs ./node_modules/@epam/ai-dial-ui-kit/dist/mcp-server.cjs with node.

not rated 501 +1 today A tokens not measured original Apache-2.0

seo-audit

3581

shadcn-labs/agentcn

Skill Claude CodeCodex

How to present the deterministic AI-SEO audit returned by auditpage. Use when reporting a page's readability and citation-readiness for AI answer engines (ChatGPT, Claude, Perplexity).

not rated 502 +4 1mo ago A SkillSpector: pass 43 tokens original MIT

ai-vibe-writing

3582

donghuixin/AI-Vibe-Writing-Skills

Skill Claude CodeCodex

Draft and revise academic prose in the author's voice, repair sentence-level reasoning, trace systems-paper claims to evidence, prepare reviewer responses, and critically appreciate papers for transferable lessons. Use for manuscript writing, scoped editing, logic checks, response letters, and paper appreciation…

not rated 501 +1 changed 23d ago A 66 tokens original MIT

seomonster

3583

avansaber/seo-monster

Plugin Cursor

Bundles 1 skill, 2 MCP servers · 49 tokens together

User-credential-driven MCP server for SEO workflows over Google Search Console, GA4, PageSpeed Insights, Cloudflare, IndexNow, Chrome UX Report, and a stdlib HTTP client for technical-SEO checks.

not rated 501 +59 changed yesterday A tokens not measured original MIT

scribe

3584

ooiyeefei/ccc

Skill Claude CodeCodex

Turn meeting recordings into notes with an unbroken chain of custody from audio to claim. Use when the user has recordings or audio to transcribe or summarize, or when an existing transcript or auto-summary reads as garbled or untrustworthy.

not rated 500 +2 changed 24d ago A SkillSpector: pass 50 tokens original MIT

yinyuan

3585

Ming-H/yinyuan-skills

Skill Claude Code

A Chinese-language relationship and marriage-fortune skill using methods such as birth-date matching, zodiac matching, and fortune slips.

not rated 505 +7 7mo ago A 127 tokens

leancodepl/marionette_mcp

Skill Claude CodeCodex

Drive a running Flutter app (debug or profile) with Marionette — an AI agent's hands and eyes for the app — tapping/typing/scrolling, screenshots, logs, hot reload/restart, device sweeps, custom extensions, and the session report, via marionettemcp or the marionette CLI. Use whenever asked to test, click through…

not rated 500 +2 changed 11d ago A 225 tokens original Apache-2.0

arcmark

3587

Geek-1001/arcmark

Skill Claude Code

Organize bookmarks, folders, and markdown notes in the Arcmark macOS app. ALWAYS use this skill when the user asks to save a link, create a folder, move bookmarks between workspaces, take notes, or otherwise tidy their Arcmark sidebar.

not rated 499 4mo ago A SkillSpector: pass 54 tokens original MIT

repo-analyzer

3588

yzddmr6/repo-analyzer

Plugin Claude Code

Bundles 1 skill · 88 tokens together

Deep architectural analysis of open-source projects with professional reports.

not rated 500 6mo ago A tokens not measured original MIT

horosa

3589

Horace-Maxwell/horosa-skill

Plugin Claude Code

Bundles 1 skill, 2 MCP servers · 191 tokens together

A local-first metaphysics toolkit for Claude Code, covering astrology, Chinese divination systems, tarot, geomancy, and related techniques.

not rated 501 +13 changed yesterday A tokens not measured AGPL-3.0

cdp

3591

browser-use/browser-harness-js

Skill Claude CodeCodex

Drive Chrome via the DevTools Protocol from JavaScript. Run JS snippets through the browser-harness-js CLI — it auto-spawns a long-lived bun HTTP server holding a fully-typed CDP Session, and every call (browser-harness-js 'await session.Page.navigate(...)') executes against the same persistent connection. Session…

not rated 498 +2 2mo ago B 123 tokens original MIT

vet

3593

imbue-ai/vet

Skill Claude CodeCodex

Run vet immediately after ANY logical unit of code changes. Do not batch your changes, do not wait to be asked to run vet, make sure you are proactive.

not rated 497 +18 1mo ago B Socket: passSnyk: pass 35 tokens AGPL-3.0

pi-ralph-wiggum

3594

tmustier/pi-extensions

Skill Claude CodeCodex

Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.

not rated 497 5d ago A SkillSpector: pass 49 tokens original MIT

sdl-mcp-agent-workflow

3595

GlitterKill/sdl-mcp

Skill Claude CodeCodex

Use when working in an SDL-MCP-enabled repository, including repository exploration, task context, code inspection, runtime execution, edits, or SDL-MCP tool calls.

not rated 498 changed 2mo ago A 41 tokens

jackson-video-resources/markov-hedge-fund-method

Plugin Claude Code

Bundles 1 skill · 126 tokens together

Markov regime detection for any asset. Labels each day Bull/Bear/Sideways from a rolling-return rule, builds the maximum-likelihood transition matrix, forecasts n-step ahead via Chapman-Kolmogorov, solves the stationary distribution, and runs a no-lookahead walk-forward backtest reporting Sharpe and max drawdown.…

not rated 498 +2 5mo ago A tokens not measured

ak-maintainer

3597

saltbo/agent-kanban

Skill Codex

Manage authorized project work through Agent Kanban and Realmroot Toolbox, typically in scheduled-task or heartbeat-triggered Sessions. Proactively inspect what needs doing, delegate execution to other Agents, and coordinate and review their Tasks as a manager.

not rated 496 +1 changed 1mo ago A 50 tokens

academic-rebuttal

3598

TobiasLee/Rebuttal-Skill

Skill Claude CodeCodex

Use when an author has received peer-review comments and scores for an academic paper and needs to diagnose underlying reviewer concerns, decide whether a rebuttal is worthwhile, plan rebuttal experiments, or prepare evidence-grounded response material and revision plans for the author to review and finalize. Produces…

not rated 498 +1 2d ago A 97 tokens

reviewer

3599

duckbugio/flock

Agent Claude Code

Read-only adversarial reviewer. Pre-PR it returns a verdict for the arbiter; on an open PR it posts true line-anchored INLINE comments via the git-host API, written in the PR's own language. Scores risk and checks cross-service compatibility. Never edits code.

not rated 495 +6 13d ago A 60 tokens original MIT

canary-workflows

3600

0xnyn/canary

Cursor rule Cursor

Canary browser automation — when and how to use the canary skills and workflows.

not rated 496 +1 15d ago A 17 tokens

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: