Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 435,011 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.

llm-wiki

1657

androoAGI/starnet

Skill Claude CodeCodex

Build and maintain a persistent, interlinked Markdown knowledge base: ingest sources once, cross-reference and flag contradictions, answer questions from it, and check it for broken links and gaps.

not rated 1.7k +69 6d ago A 41 tokens original MIT

sublinkpro

1658

ZeroDeng01/sublinkPro

Skill Claude CodeCodex

Manage SublinkPro proxy subscriptions via its REST API — add/query nodes, build and share subscriptions, manage airports, templates (incl. AI template editing), tags, and view dashboard stats. Use when the user wants to operate their SublinkPro instance.

not rated 1.7k +5 yesterday C SkillSpector: warn 56 tokens original MIT

quark

1659

ev-flow/quark-engine

Plugin Claude Code

Bundles 2 skills · 63 tokens together

Quark Engine skills for Claude Code: run APK malware analysis and generate detection rules.

not rated 1.7k +1 today A tokens not measured GPL-3.0

emil-design-eng

1660

classroomio/classroomio

Skill Claude CodeCodex

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

not rated 1.7k +1 today A SkillSpector: pass 35 tokens AGPL-3.0

clawd-media-track

1661

fancydirty/mediary-scout

Skill Claude CodeCodex

Resource tracking and acquisition workflow for media resources. MUST use when the user asks to get, add, track, monitor, search, acquire, transfer, or initialize movies, TV shows, anime, Pansou resources, or 115 cloud storage items with the clawd-media-track system. For every clawd-media-track task: first read…

not rated 1.7k +106 yesterday A 115 tokens original 0BSD

agent-kit

1663

sendaifun/solana-agent-kit

MCP server Claude CodeCodexCursor +2

MCP server "agent-kit" as configured in sendaifun/solana-agent-kit. Runs /absolute/path/to/build/index.js with node. Needs 3 environment variables to run.

not rated 1.7k +1 5mo ago A tokens not measured original Apache-2.0

dbs-xhs-title

1664

Pluviobyte/rnskill

Skill Claude CodeCodex

A title-writing tool for Xiaohongshu, a Chinese social platform for lifestyle and general content, based on 75 tested title patterns.

not rated 1.7k +27 1mo ago A SkillSpector: pass 172 tokens

dynamic-archify

1665

Unclecheng-li/AI_Animation

Skill Claude CodeCodex

Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone animated HTML files with SVG graphics, flowing animation effects, a built-in dark/light theme toggle, and one-click export to PNG / JPEG / WebP / SVG / GIF / WebM. Accepts plain-language descriptions or pasted…

not rated 1.7k +48 11d ago A SkillSpector: pass 163 tokens original MIT

bv

1666

Dicklesworthstone/beads_viewer

Skill Claude CodeCodex

Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use --robot- flags for AI agents.

not rated 1.7k +2 changed today A 39 tokens

anti-defensive-writing

1667

Kiterlin/anti-defensive-writing

Skill Claude CodeCodex

Reduce defensive writing in drafts and revisions by removing unnecessary caveats, disclaimers, hedges, apology-like framing, negative self-limiting statements, and over-explanations while preserving necessary scope, accuracy, safety, legal, ethical, and methodological limits. Use when drafting or revising academic…

not rated 1.7k +161 changed 20d ago A 132 tokens original MIT

newsletter

1668

masamasa59/ai-agent-papers

Skill Claude Code

Write a monthly trend newsletter for this ai-agent-papers repo. Use when asked to create/update a monthly trend report, summarize a category's recent papers, or "make a newsletter". Encodes the house procedure: cover every coherent category with enough papers that month (no fixed number of issues; overlap between…

not rated 1.7k +5 21d ago A SkillSpector: pass 120 tokens

planby

1669

karolkozer/planby

Skill Claude CodeCodex

Build and edit schedule / timeline / agenda / planner / booking-grid / program-guide UIs with planby (open source) in React — any "rows x time" layout: conference and event agendas, festival line-ups, class and shift schedules, room and resource booking grids, project timelines, streaming line-ups, and TV guides /…

not rated 1.7k 2mo ago A SkillSpector: pass 180 tokens

build

1670

TeamHypersomnia/Hypersomnia

MCP server Claude CodeCodexCursor +2

MCP server "build" as configured in TeamHypersomnia/Hypersomnia. Runs cmake/mcp_build_server.py with python3.

not rated 1.7k +7 5d ago A tokens not measured AGPL-3.0

openlore

1671

aakarim/OpenLore

Skill Claude CodeCodex

Query and publish to an OpenLore knowledge repository over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.

not rated 1.7k +5 changed 14d ago A SkillSpector: warn 42 tokens original Apache-2.0

boss-zhipin-scraper

1672

eatmoreduck/boss-zhipin-scraper

Skill Claude CodeCodex

Scrape BOSS直聘 (job listing site) via Chrome CDP. Searches jobs by keyword/city/filters, fetches JD details, outputs structured JSON/CSV with plaintext salary, and can summarize scraped results into a job-market prompt. Optional --company locally filters results by company name (bossname substring) with no extra…

not rated 1.7k +33 changed 3d ago A 97 tokens original MIT

obsidian

1673

bitbonsai/mcpvault

Skill Claude CodeCodex

Activate when the user mentions their Obsidian vault, notes, tags, frontmatter, daily notes, backup, or sync. Route operations across MCP, Obsidian CLI/app actions, and git sync with safe defaults.

not rated 1.7k +9 changed 5d ago A Socket: passSnyk: passSkillSpector: warn 48 tokens original MIT

video-podcast-maker

1674

Agents365-ai/video-podcast-maker

Skill Claude Code

Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…

not rated 1.7k +10 changed 1mo ago A SkillSpector: warn 214 tokens original MIT

evals

1675

ai-evals-course/evals-skills

Plugin Claude Code

Bundles 9 skills · 547 tokens together

Skills for building LLM evals. Starts with interactive error discovery: build a review app, sample diverse traces, and organize human annotations into failure modes.

not rated 1.7k +18 changed 2mo ago A tokens not measured original Apache-2.0

cc-thinking-skills

1676

tjboudreaux/cc-thinking-skills

Plugin Claude Code

Bundles 28 skills · 1,028 tokens together

28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools.

not rated 1.7k +24 3mo ago A tokens not measured original MIT

agent-organizer

1677

lst97/claude-code-sub-agents

Agent Claude Code

A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collaborative workflow to achieve project goals. Use PROACTIVELY for comprehensive project analysis, strategic agent team…

not rated 1.7k +1 1y ago A 66 tokens original MIT

llm-review

1678

skyllwt/AutoSci

MCP server Claude CodeCodexCursor +2

MCP server "llm-review" as configured in skyllwt/AutoSci. Runs mcp-servers/llm-review/server.py with python3.

not rated 1.7k 1mo ago A tokens not measured original MIT

burrow-system-tools

1679

caezium/burrow

Skill Claude CodeCodex

Diagnose and fix the user's Mac with Burrow's local MCP tools (burrowdoctor, burrowsnapshot, burrowtopprocesses, burrowprocessusage, burrowports, burrowanalyze, burrowdiskforecast, burrowdupes, burrowanomalies, burrowagentaudit, burrowclean, …). Use whenever the Mac is slow, hot, loud, low on disk, draining battery…

not rated 1.7k +87 today A SkillSpector: pass 194 tokens original MIT

cursor-rules

1680

nextify-limited/libra

Cursor rule Cursor

Intelligent programming assistant protocol - automatically selects simple direct response or complex RIPER-5 mode based on task complexity.

not rated 1.7k +3 1y ago A 22 tokens AGPL-3.0

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: