Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 414,493 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.

higgsfield

2185

higgsfield-ai/skills

Plugin Claude Code

Bundles 8 skills · 1,636 tokens together

Higgsfield AI skills for images, videos, complete brand systems, narrated explainers, YouTube thumbnails, browser games, Marketing Studio, engagement analysis, and Soul Character training.

not rated 935 +49 2d ago A tokens not measured original MIT

cavekit-design-system

2187

JuliusBrussee/caveman-code

Skill Claude Code

How to write and maintain DESIGN.md as the visual specification layer for Cavekit projects. Nine-section format, design tokens, accessibility, integration with kits/plans. Use when defining or revising visual identity, importing a third-party design system, or auditing UI code against design tokens.

not rated 934 +2 29d ago A SkillSpector: pass 62 tokens original MIT

clawhip

2188

Yeachan-Heo/clawhip

Skill Claude CodeCodex

Attach/install/use clawhip as a daemon-first notification gateway runtime for OpenClaw / Clawdbot.

not rated 933 +1 9d ago A 25 tokens original MIT

octocode-benchmark

2189

bgauryy/octocode

Skill Claude CodeCodex needs its repo

Use when planning, running, grading, or reporting the by-hand Octocode research benchmark — pairwise matchups (Octocode anchor vs one baseline: gh+RTK, gh+Headroom, or plain gh) over markdown questions, with a fresh isolated runner agent per (question, arm, pass), one blind judge per question grading two answers X/Y…

not rated 933 +7 yesterday A SkillSpector: warn 117 tokens original MIT

repo-audit

2190

adolfousier/opencrabs

Skill Claude CodeCodex

Run a comprehensive language-agnostic repository health audit, scored 0-100. Detects language, runs native tooling, never assumes JS/Python.

not rated 933 +3 today A SkillSpector: warn 35 tokens original MIT

forgecad-build-model

2191

ForgeCAD/forgecad-public-kit

Skill Claude CodeCodex

Build or edit a manufacture-realistic .forge.js model in a project, then validate it with run, render, inspect, and export evidence.

not rated 932 +1 3mo ago A SkillSpector: pass 35 tokens original MIT

slides

2192

stackblitz/bolt-slides

Skill Claude CodeCodex

Build a premium PRESENTED slide deck — classic one-slide-at-a-time slides you advance with a clicker — as a Vite + React app. It keeps the Slidev navigation UI (floating glass dock + thumbnail rail + click-builds + presenter) but slides are RESPONSIVE React (reflow to any screen, no fixed canvas) and fully…

not rated 931 +6 1mo ago A SkillSpector: pass 140 tokens original MIT

mcp-framework

2193

QuantGeekDev/mcp-framework

Cursor rule Cursor

We are in the mcp-framework , a typescript framework that allows construction of model context protocol (mcp) servers. We are implementing the new specification: Overview MCP provides a standardized way for applications to.

not rated 930 +1 5mo ago A 0 tokens original MIT

video-translator

2194

InsiderX-Pro/video-translator

Skill Claude CodeCodex

A service workflow for translating or dubbing a user-provided video and returning a preview link for the result.

not rated 929 +75 2mo ago A 49 tokens original MIT

chatgpt-web-research

2195

bear2u/my-skills

Skill Codex

Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research, competitor research, second-opinion research, or any browser-only work. Load chrome:control-chrome first, then computer-use:computer-use for fallback. Save verified…

not rated 929 +7 2mo ago A 104 tokens

skill-creator

2196

luongnv89/asm

Skill Claude Code

Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.

not rated 928 +13 changed 4d ago A SkillSpector: warn 54 tokens original MIT

Adkid-Zephyr/anti-defensive-writing-Skill

Skill Claude CodeCodex

Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…

not rated 928 +434 today A SkillSpector: pass 138 tokens original MIT

H-mmer/pentest-agents

Cursor rule Cursor

Cursor rule "pentest-agents-payloads" from H-mmer/pentest-agents, covering payload reference, xss payloads, basic, waf bypass and context-specific.

not rated 927 +110 3mo ago A ✓ AI review 8 tokens

cursorrules

2199

qinshihu/itops-agent-platform

Cursor rule Cursor

ITops Agent is a one-stop intelligent ops platform. Stack: Node.js + Express + TypeScript + SQLite (backend) / React + Vite + Ant Design + Tailwind (frontend). DDD modules: 24 backend modules + 23 frontend modules. See .trae/rules/architecture.md §1.2.

not rated 926 +7 6d ago A 1,432 tokens

claude-code-dmwork

2200

Mininglamp-OSS/octo-server

Skill Claude CodeCodex

Connect to DMWork messaging platform as an AI bot via the OpenClaw DMWork adapter plugin.

not rated 926 +103 yesterday A SkillSpector: pass 0 tokens original Apache-2.0

short-drama

2201

ZJU-REAL/Easel

Skill Claude CodeCodex needs its repo

A production workflow for making multi-episode AI short dramas, covering story planning, character consistency, scripts, generated video shots, voices, sound, subtitles, and final assembly.

not rated 926 +515 yesterday A SkillSpector: pass 124 tokens original Apache-2.0

skill-creator

2202

usewhale/Whale

Skill Codex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

not rated 925 +1 1mo ago A 46 tokens copy · 70% MIT

etrules

2203

FlameskyDexive/Legends-Of-Heroes

Cursor rule Cursor

A Chinese-language coding rule set for the ET framework, a game-development framework using an entity-component-system structure. It defines how data, logic, packages, and assemblies should be organized.

not rated 925 +2 1mo ago A 0 tokens original MIT

sessy

2204

marckohlbrugge/sessy

Plugin Claude Code

Bundles 1 MCP server

Track AWS SES bounces, complaints, and delivery stats from Claude Code. Requires a Sessy API key. Does not send email or change SES settings.

not rated 924 +2 4d ago A tokens not measured

hatch-pet-v2

2205

legeling/awesome-codex-pet

Skill Codex

Create, repair, validate, visually QA, and package Codex-compatible v2 animated pets from character art, generated images, company or prospect brand cues, or visual references. Use for any new Codex pet, custom mascot, non-pixel pet style, brand-inspired pet, existing-pet repair, or 8x11 spritesheet workflow requiring…

not rated 924 +66 changed yesterday A SkillSpector: pass 103 tokens original MIT

citra

2207

SylphxAI/pdf-reader-mcp

Skill Claude CodeCodex

Skill "citra" from SylphxAI/pdf-reader-mcp, covering citra — pdf evidence for agents, install, or, tools and sdk.

not rated 923 +6 3d ago A SkillSpector: warn 0 tokens original MIT

debugger

2208

Auties00/Cobalt

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "debugger", hosted remotely at 127.0.0.1, as configured in Auties00/Cobalt.

not rated 921 +3 1mo ago A tokens not measured original 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: