Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 438,256 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.

file-naming

10033

ngtiendong/Academic-Research-Agent-Skill

Command Claude Code

Command "file-naming" from ngtiendong/Academic-Research-Agent-Skill, covering /file-naming, language, task, convention and output.

not rated 73 +3 1mo ago A 0 tokens original MIT

cues

10034

opencues/opencues

Skill Claude CodeCodex

AMBIENT BACKGROUND TASK — FIRE ON EVERY SUBSTANTIVE TURN. The user does NOT need to ask. When the user mentions ANY domain (drafting, building, writing, composing, researching, planning, comparing options, exploring, deciding, learning, debugging, designing, refactoring, configuring — ANY domain engagement), you MUST…

not rated 73 +2 23d ago A SkillSpector: pass 239 tokens original Apache-2.0

dcc-cua

10035

dcc-mcp/dcc-mcp-core

Skill Claude CodeCodex

A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.

not rated 73 changed 9d ago A SkillSpector: pass 131 tokens original MIT

molmoact-libero

10036

graph-robots/open-robot-skills

Skill Claude CodeCodex

Run the MolmoAct LIBERO checkpoint (allenai/MolmoAct-7B-D-LIBERO-0812) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSCPOSE action space from agentview + wrist cameras, served behind a vLLM-style script speaking the openpi websocket…

not rated 73 +9 1mo ago A SkillSpector: warn 226 tokens original Apache-2.0

slide-wright

10038

arifszn/slide-wright

Skill Claude CodeCodex

Create beautiful web presentations from a topic, rough notes, or an outline, and edit decks afterward — adding, removing, or revising slides. Asks how many design directions to preview and whether to animate, shows a two-slide preview of each custom theme, then builds the full deck only once the user picks a…

not rated 73 changed 5d ago A 115 tokens original MIT

hive-memory

10039

projectmentor/hive-mind

Skill Claude Code

Read from and write to the shared Hive Mind corpus (the hv CLI) — append-only institutional memory shared across agents (Hermes, Claude Code, …) and machines. Use to record decisions/outcomes/constraints and to check what the hive already knows before acting — especially on errors, uncertainty, or a named…

not rated 73 changed 1mo ago A 73 tokens AGPL-3.0

ai-tips-tricks

10040

0xMulight/human-social-copy

Skill Claude CodeCodex

An automated workflow for searching the web for practical AI tips, techniques, and workflows, then writing tutorial-style Chinese posts and sending them to Telegram.

not rated 73 3mo ago C 53 tokens original MIT

researcher

10041

howdeploy/kisa-stack

Skill Codex

A research workflow for searching the live web and extracting information from pages. It supports quick scans for short overviews and deep research for comparing several sources.

not rated 73 +4 changed 2mo ago A 114 tokens original MIT

spec

10042

zenbase-ai/llml

Cursor rule Cursor

Cursor rule "spec" from zenbase-ai/llml, covering llml technical specification, core transformation rules, 1. empty value handling, 2. primitive value formatting and 3. key preservation.

not rated 73 1y ago A 3,540 tokens original MIT

levy

10043

seaworld008/Commonly-used-high-value-skills

Skill Claude CodeCodex

Domain knowledge agent for Japanese income tax filing (kakutei shinkoku). Guides income classification, deduction optimization, tax calculation, and filing for freelancers, sole proprietors, and side-business earners. Does not write code.

not rated 73 +1 changed today A SkillSpector: warn 50 tokens original MIT

flightclaw

10044

jackculpan/flightclaw

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 114 tokens together

Search Google Flights, price-track routes and get alerts when fares drop, then book and pay through Duffel. Remembers travellers, companions, loyalty programmes, cards and cabin preferences so options come back ranked for the person asking.

not rated 73 2mo ago A tokens not measured original MIT

swallowtail

10045

regiellis/godot-mcp-go

Skill Claude CodeCodex

Use the complete Godot development loop from the swallowtail CLI: discover the live engine API, build and edit in the open editor, run and play the game, observe state, debug failures, fix them in place, and verify the result. Use when the task involves creating or modifying a Godot project, testing game behavior…

not rated 73 +1 changed 1mo ago A 0 tokens original MIT

awesome-agents-md

10047

khasky/awesome-agents-md

Plugin Gemini CLI

awesome-agents-md. One self-contained AGENTS.md with shared rules for AI coding agents: Claude Code, OpenAI Codex, Gemini, Cursor Agent, and more.

not rated 73 +1 14d ago A tokens not measured original MIT

mobbin

10048

mobbin/skills

Plugin Claude Code

Bundles 4 skills · 381 tokens together

Give your AI agent 600,000+ real app screens, and the skills to use them. Includes the Mobbin MCP and a skill that redesigns your screen from patterns real apps ship, in your own design system, with the references behind every change.

not rated 73 +6 changed 15d ago A tokens not measured original MIT

longbridge

10049

longbridge/skills

Plugin Claude Code

Bundles 13 skills, 1 command · 3,403 tokens together

Longbridge securities skill family: market data, technical analysis, derivatives, fundamentals, research, portfolio & account, quant strategies, watchlist, content, market intelligence, earnings, and value investing. HK / US / A-share (SH/SZ) / Singapore markets. Trilingual (Simplified Chinese, Traditional Chinese…

not rated 73 +2 10d ago A tokens not measured original MIT

grounded-ai

10050

grounded-ai/grounded_ai

Plugin Claude Code

Bundles 1 hook

Stop hook that checks Claude's final answer against the turn's tool output with TypeSafe's Jev, and sends Claude back to re-check unsupported claims.

not rated 73 +1 changed 1mo ago A tokens not measured original MIT

lacuna-code-to-paper

10051

tiptreesystems/lacuna-research-mcp

Skill Claude CodeCodex

Trace an ML code repository, dataset, or model to its linked research papers with Lacuna. Use when a user asks which papers an implementation comes from, how code relates to a paper, or what research to read before changing it.

not rated 73 +7 today A 53 tokens original MIT

custom-brand-design

10052

KbWen/agent-virtual-office

Skill Claude CodeCodex

Apply approved project brand guidance and the selected screen design reference during planning, implementation, and review.

not rated 73 +3 3d ago A 23 tokens copy · 100% MIT

agenticforge-agents

10054

LittleBlacky/AgenticFORGE

Skill Claude CodeCodex

Expert at selecting and configuring AgenticFORGE agents. Generates correct FunctionCallAgent, ReActAgent, PlanSolveAgent, ReflectionAgent, SimpleAgent, SkillAgent, and WorkflowAgent code with proper configuration. Use when the user wants to build an agent, choose between agent types, configure agent options, or…

not rated 72 4mo ago A 72 tokens

trend-pulse

10055

claude-world/claude-world-studio

MCP server Claude CodeCodexCursor +2

One of 4 in .mcp.json

MCP server "trend-pulse" as configured in claude-world/claude-world-studio. Runs locally from the trend-pulse[mcp] Python package.

not rated 72 +1 16d 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: