Claude Code

81,609 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

vgpu

3001

codeworksh/codework

Skill Claude CodeCodex

Build, debug, test, and optimize WebGPU projects using vgpu, its CLI, or @vgpu packages. Use for vgpu API questions, WGSL workflows, browser or Node rendering, integrations, testing, and performance work.

not rated 26 +1 today A 51 tokens original MIT

cuda-auto-tune

3003

Bruce-Lee-LY/cuda_auto_tune

Skill Claude CodeCodex

NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels. MANDATORY: every optimization MUST start with NCU profiling, followed by multi-dimensional analysis, then targeted code modification, then re-profiling to verify. Supports roofline, memory hierarchy, warp stalls, instruction mix…

not rated 25 7mo ago C 167 tokens original MIT

gauntlet

3004

robertsfeir/atelier-pipeline

Cursor rule Cursor

Run a full-spectrum, multi-agent audit covering every layer of the application: architecture, implementation, testing, security, frontend/UX, product alignment, and blind code review. All rounds run in parallel — contamination is prevented by instruction, not by timing. Phase 2 begins only after all active rounds…

not rated 25 4mo ago A 8,143 tokens original Apache-2.0 archived

mm-web-bridge

3006

mworldorg/markdown-memory

Skill Claude CodeCodex

An idea partner for a developer who discusses plans, checks current information online, and prepares self-contained tasks for Claude Code running in Windows PowerShell. It is designed for Russian-language work and mentions Telegram bots, Python, SQLite, and Railway deployment.

not rated 25 +1 23d ago A SkillSpector: warn 154 tokens original MIT

aegis

3007

myclaude-sh/myclaude-creator-engine

Skill Claude Code

SAST security audit: STRIDE threat model, 300+ vuln patterns, 8 compliance frameworks, auto-fix, hardening. Use when: audit code, find vulnerabilities, compliance check, threat model, secrets scan, CVE review. NOT for: DAST, pentesting.

not rated 25 6d ago A 63 tokens original MIT

arc

3008

howells/arc

Plugin Claude Code

Bundles 13 skills, 11 commands · 986 tokens together

Deprecated and no longer maintained. Arc remains available as an archive; use github.com/howells/skills for focused agent skills.

not rated 25 2mo ago A tokens not measured original MIT archived

create-app-yaml

3009

0xMaxMa/claude-gateway

Skill Claude Code

Scan Dockerfile(s) in the current directory and generate a draft app.yaml for the gateway app store.

not rated 25 +1 changed 25d ago A 26 tokens

context7

3010

krzemienski/claude-code-builder

MCP server Claude CodeCodexCursor +2

One of 5 in .mcp.json

MCP server "context7" as configured in krzemienski/claude-code-builder. Runs locally from the @context/mcp npm package.

not rated 25 11mo ago A tokens not measured original MIT

surf

3011

vibesurf-ai/claude-surf

Plugin Claude Code

Bundles 21 skills, 1 hook · 741 tokens together

VibeSurf integration - Control browsers, automate workflows, execute AI skills (search/crawl/jscode/summary), use Composio integrations (Gmail/GitHub/Slack), and run pre-built workflows.

not rated 25 9mo ago A tokens not measured original MIT

antidote

3012

Avtr99/antidote

Plugin Claude Code

Bundles 1 skill · 47 tokens together

Stop AI agents from patching symptoms. Forces structural root-cause fixes over symptom patching in any language or stack.

not rated 25 6d ago A tokens not measured original MIT

floodsung

3013

floodsung/floodsung-skill

Skill Claude CodeCodex

A writing and decision-making style guide based on Flood Sung’s published Chinese articles, ideas, and answers. It helps an agent respond in his stated viewpoint and tone.

not rated 25 6mo ago A 127 tokens

paoding-skill

3014

longyunfeigu/paoding-skill

Skill Codex

Use when studying, reverse-engineering, comparing, reviewing, or learning from AI skill packages, SKILL.md files, Claude/Codex skills, prompt workflows, or agent playbooks; use when the user wants reusable skill design patterns, a keep/cut review, Markdown report, structured pattern notes, or multi-page web handbook.…

not rated 25 4mo ago A 105 tokens original Apache-2.0

97

3016

oribarilan/97

Plugin Claude Code

Bundles 14 skills, 1 hook · 445 tokens together

Skills distilled from the hard-won lessons of world-renowned programmers, in the spirit of '97 Things Every Programmer Should Know'. Your coding agent invokes them when about to refactor, write a test, design an API, or commit.

not rated 25 changed 16d ago A tokens not measured

aura-frog

3019

nguyenthienthanh/aura-frog

Plugin Claude Code

Bundles 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers · 2,925 tokens together

Planning-first LLM OS for software engineering. Hierarchical planning (T0-T4) survives session reset · forensic reasoning traces · L1+L2 conflict detection · self-healing safety gates · per-agent MCP security · durable project-context snapshots · cross-tool porter (Copilot/Codex/Cursor) · CLI dashboard. 15 agents…

not rated 25 changed 19d ago A tokens not measured original MIT

wechat-styler

3021

zjp1997720/wechat-styler

Skill Codex

A tool that converts Markdown articles into inline-styled HTML for WeChat Official Accounts, China's publishing platform. It offers selectable visual themes and optional structured components and an opening SVG animation.

not rated 25 3mo ago A 81 tokens copy · 88% MIT

zh-ebn-report

3023

htlin222/zh-ebn-report-skill

Skill Claude CodeCodex

A writing coach for Taiwanese nurses preparing evidence-based nursing reports, which use research findings to guide clinical care. It covers literature reports and case analyses for nursing advancement levels N1–N4.

not rated 25 +1 3d ago A 343 tokens original MIT

slopsec

3024

lachydotmcg/slopsec

Plugin Claude Code

Bundles 1 skill · 128 tokens together

Security audit and hardening for vibe-coded SaaS apps. Walks the 50 most common ways AI-generated apps get owned and produces a prioritized fix list.

not rated 25 3mo 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: