Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 416,104 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.

100-engine

6025

heyzgj/cursor-project-master

Cursor rule Cursor

The Core Engine. It orchestrates the project's entire lifecycle, from initial planning and scaffolding to the iterative task execution loop. It acts as the central state machine.

not rated 169 1y ago A 1,583 tokens

gpt-isms-stamp-out

6026

makoMakoGo/fish-claude

Skill Claude CodeCodex

Strip GPT-5.4 verbal tics from text. Use when user asks to de-GPT a document, remove AI-isms, stamp out GPT tics, or clean up AI-written text. Also use proactively when creating documents (README, docs, proposals, specs) to avoid GPT-5.4 tic patterns in the output.

not rated 169 2mo ago A SkillSpector: pass 77 tokens original MIT

engraph

6027

devwhodevs/engraph

Skill Claude Code

Index and search document collections using hybrid semantic + graph + full-text search. Use when users need to search knowledge bases, find connections between documents, discover related content via link graphs, or query indexed markdown collections.

not rated 169 3mo ago A 45 tokens original MIT

fast-api

6028

ilanbenb/wa_llm

Cursor rule Cursor

You are an expert in Python, FastAPI, and scalable API development.

not rated 169 +1 yesterday A 762 tokens copy · 94% MIT

Readme.skill

6029

study8677/Readme.skill

Plugin Claude Code

Bundles 1 skill · 250 tokens together

Generate an AI-Native developer profile or monthly/time-window report from local Claude Code + Codex CLI + Kiro (AWS) + Trae (ByteDance) + Gemini Antigravity (Google) + Cursor composer metadata, GitHub contributions, and git log. Local-only, read-only, anonymized by default.

not rated 169 +1 3mo ago A tokens not measured original MIT

kanban

6030

kanban-rs/kanban

MCP server Claude CodeCodexCursor +2

MCP server "kanban" as configured in kanban-rs/kanban. Launched with nix run .#kanban-mcp -- kanban.json.

not rated 169 3d ago A tokens not measured original Apache-2.0

elevenlabs

6031

zapier/connectors

Plugin Claude Code

Bundles 1 skill · 115 tokens together

Agent-callable ElevenLabs tools — generate spoken audio from text, create sound effects and multi-speaker dialogue, re-voice and clean up audio, transcribe audio and video, design synthetic voices, and manage voices, history, and quota. Use when the user mentions ElevenLabs or wants AI audio work — text to speech…

not rated 169 +4 23d ago A tokens not measured

alibabacloud-devops

6032

aliyun/alibabacloud-devops-mcp-server

Skill Claude CodeCodex

A skill that connects an agent to Alibaba Cloud Yunxiao, a platform for managing code, projects, build pipelines, application delivery, and testing.

not rated 169 +1 changed 2d ago A SkillSpector: warn 43 tokens original Apache-2.0

Hector-xue/IvyeaOps

Skill Claude CodeCodex

A Chinese-language guide for auditing an Amazon product listing identified by its ASIN, Amazon’s product identifier. It examines listing visibility, conversion, advertising, and Amazon’s COSMO and Rufus systems, then suggests changes.

not rated 169 +17 8d ago A 166 tokens AGPL-3.0

moi-workspace

6034

molefrog/moi

Skill Claude Code

The moi workspace — the web UI the user chats from, extended with agent-authored applets (widgets, views) plus theme & config. Read this FIRST when a message carries a hidden moi-context envelope or the user uses moi vocab such as workspace, applet, widget, view, scratchpad, dashboard, or a moi command, or asks to…

not rated 169 +8 changed today A 94 tokens

garchmethod

6035

milesdeutscher/garchmethod

Plugin Claude Code

Bundles 1 skill · 94 tokens together

Volatility forecasting + position sizing via walk-forward GARCH(1,1). Answers 'how much' — never 'which way'. Vol forecasts, storm/calm regimes, vol-targeted sizing, and an honest fixed-vs-vol-targeted backtest harness for any strategy.

not rated 169 +38 2mo ago A tokens not measured original MIT

wechat-use

6036

leeguooooo/wechat-use

Skill Claude CodeCodex

Release status: v1.18.7 is published and marked latest. The capabilities below apply to the released build; users on older versions can upgrade with the README install command.

not rated 169 +3 changed 7d ago E ✓ AI review 207 tokens

altic-studio

6037

altic-dev/altic-mcp

Skill Claude CodeCodex

Skill "altic-studio" from altic-dev/altic-mcp, covering altic studio, mode a: applescript (macos apps), applescript capabilities, mode b: reminders, calendar, and notes (mcp) and mode c: chrome browser control (mcp cdp).

not rated 169 +5 2mo ago A SkillSpector: pass 23 tokens original Apache-2.0

Vuk97/forward-implementation-first

Skill Claude CodeCodex

Keeps an agent building and validating real output instead of servicing its own bookkeeping. Use for multi-stage pipelines, capability roadmaps, long-running implementation loops, migrations, staged data or build runs, and any run where administrative hashes, locks, receipts, dashboards, certification markers, or…

not rated 169 +3 changed 14d ago C 94 tokens original MIT

tiered-memory

6040

Azure-Samples/eShopLite

Skill Claude CodeCodex

Three-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawn.

not rated 168 2mo ago A SkillSpector: warn 25 tokens original MIT

onboard

6041

wednesday-solutions/ai-agent-skills

Command Claude Code

Generate a personalized onboarding brief for a new developer joining the project.

not rated 168 3mo ago A 0 tokens original MIT

imagegen

6042

tercumantanumut/selene

Skill Claude CodeCodex

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (${SELENESKILLROOT}/scripts/imagegen.py) and require…

not rated 168 +1 1mo ago A SkillSpector: warn 81 tokens original MIT

aivis

6043

onism1767-creator/potato

Skill Claude CodeCodex

A measurement workflow for checking how often a brand is mentioned or cited in Claude’s web-search answers. Claude is an AI service, and web search lets it use online sources when answering questions.

not rated 168 2mo ago A 81 tokens original MIT

Video Editor (FFmpeg)

6044

tubecreate/tubecli

Skill Claude CodeCodex

AI-powered Video Editor with trimming, merging, effects, overlays, and export.

not rated 168 +1 yesterday A SkillSpector: warn 21 tokens original MIT

spec-injection-index

6045

EXboys/skilllite

Cursor rule Cursor

Auto-select and inject project specs by task type.

not rated 168 +1 4d ago A 374 tokens original MIT

make-no-mistakes-max

6046

thesysdev/make-no-mistakes

Skill Claude CodeCodex

Enterprise collaboration standard for technical enablement. M-stack optimizes for optics, alignment, and downstream socialization of engineering decisions. Precision matters, but the repeatable narrative, stakeholder calm, and velocity story are treated as first-class deliverables alongside the code path.

not rated 168 +1 5mo ago A 0 tokens original Apache-2.0

suryast/indonesia-gov-apis

Skill Claude CodeCodex

Query 57 Indonesian government APIs and data sources — BPJPH halal certification, BPOM food safety, OJK financial legality, BPS statistics, BMKG weather/earthquakes, Bank Indonesia exchange rates, IDX stocks, CKAN open data portals, pasal.id (third-party law MCP). Use when building apps with Indonesian government…

not rated 168 +1 yesterday A 129 tokens original MIT

tilelang-skill

6048

slowlyC/agent-gpu-skills

Skill Claude CodeCodex needs its repo

Write, debug, and optimize TileLang kernels from local upstream language, JIT, autotuning, profiling, compiler, test, and example source. Use when the task explicitly involves tilelang, tilelang.language, @tilelang.jit, @T.primfunc, T.Kernel, T.copy, T.gemm, TileLang Profiler, Carver, TileLang passes, or TileLang…

not rated 168 +1 1mo ago A SkillSpector: warn 148 tokens 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: