Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 414,171 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.

codex-guard

6649

Akimiya-z/codex-guard

Skill Claude CodeCodex

Pre-submit hygiene check for AI-agent-authored pull requests. Use this skill whenever you are about to open or update a pull request: it runs the codex-guard CLI locally, verifies the diff contains no leftover TODO/FIXME/XXX markers and no hardcoded secrets, checks that commit subjects follow conventional commits, and…

not rated 139 +2 yesterday A SkillSpector: warn 85 tokens original MIT

encephalon

6650

isaachinman/encephalon

Skill Claude CodeCodex

Use when working in a Git repository that has Encephalon installed, especially before making repository assumptions or when a durable decision, architecture change, convention, incident, workflow, pull request, or material technical change may need long-term agent knowledge.

not rated 140 +1 changed 2d ago A SkillSpector: pass 53 tokens original MIT

nfeio-node-sdk

6652

nfe/client-nodejs

Skill Claude CodeCodex

NFE.io Node.js SDK integration expert (package: nfe-io). MUST trigger when: code imports 'nfe-io' or references NfeClient; user mentions NFE.io, NFS-e, NF-e, CT-e, CF-e, CFe-SAT, nota fiscal, nota fiscal eletronica, Brazilian invoice, fiscal document, electronic invoice Brazil, CNPJ lookup, CPF lookup, service…

not rated 139 changed 13d ago A 264 tokens

pathfinder

6653

shivasurya/code-pathfinder

MCP server Claude CodeCodexCursor +2

Python SDK for code-pathfinder static analysis for modern security teams. Runs locally from the codepathfinder Python package.

not rated 139 +1 2mo ago A tokens not measured original Apache-2.0

loop-engineering

6654

Mark393295827/third-brain-v7-skills

Skill Codex

Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal agent, or metric-driven research cycle.

not rated 139 +1 28d ago A SkillSpector: pass 35 tokens original MIT

cursorrules

6655

alchaincyf/cursor-rules-huasheng

Cursor rule Cursor

A set of instructions for an AI assistant helping build Android apps for a beginner. It specifies Kotlin, Jetpack Compose, common app structure, and a step-by-step working process.

not rated 139 1y ago A 828 tokens original MIT

agent-council

6656

team-attention/agent-council

Skill Claude CodeCodex

Collect and synthesize opinions from multiple AI agents. Use when users say "summon the council", "ask other AIs", or want multiple AI perspectives on a question.

not rated 139 8mo ago A 40 tokens copy · 100% MIT

tickertick

6657

hczhu/TickerTick-API

Skill Claude CodeCodex

Query the TickerTick API for stock news stories and ticker search. Base URL: https://api.tickertick.com. Rate limit: 10 req/min per IP (>5 in any 30s window → 30s block).

not rated 140 3mo ago A 3 tokens original MIT

cursorrules

6658

Claudate/project-multilevel-index

Cursor rule Cursor

A set of Cursor editor rules for automatically maintaining a project's multi-level documentation indexes. Cursor is an AI-assisted code editor that can load these rules when a conversation starts.

not rated 139 8mo ago A 745 tokens original MIT

git

6660

Dave-London/Pare

MCP server Claude CodeCodexCursor +2

One of 26 in server.json

Structured git operations (status, log, diff, branch, show) as typed JSON. Runs locally from the @paretools/git npm package.

not rated 139 +1 3d ago A tokens not measured original MIT

owlex

6663

agentic-box/owlex

Plugin Claude Code

Bundles 4 skills, 4 agents · 219 tokens together

Delegate tasks to Codex, Gemini, and OpenCode AI agents via Owlex MCP.

not rated 139 +1 6mo ago A tokens not measured original MIT

portfolio-audit

6664

hey-stefan/portfolio-audit

Skill Claude Code

Audit a design portfolio website against what top design leaders actually look for when hiring. Use with /portfolio-audit .

not rated 139 5mo ago A 29 tokens

xs-arxiv

6665

karaage0703/ai-assistant-workspace

Skill Claude CodeCodex

A research workflow for finding and summarizing papers on arXiv, an online repository for research preprints, using their abstracts by default.

not rated 139 +2 1mo ago A SkillSpector: pass 79 tokens original MIT

anchormind

6666

JinHo-von-Choi/anchormind

Skill Claude Code

Reference guidance for AnchorMind, a memory server that stores, searches, connects, and updates long-term fragments for AI agents.

not rated 139 +1 changed 8d ago A 0 tokens original Apache-2.0

android-skills

6667

rcosteira79/android-skills

Plugin Claude Code

Bundles 21 skills · 1,751 tokens together

Android and KMP development skills for Claude Code — architecture, Compose, coroutines, flows, networking (Retrofit, Ktor), persistent storage (Room, DataStore), pagination, dependency injection (Hilt, Koin), testing, debugging, Gradle, and Material Design 3.

not rated 139 +2 24d ago A tokens not measured original MIT

adspower-browser

6668

AdsPower/adspower-browser

Skill Claude CodeCodex

AdsPower profile operation via adspower-browser CLI. open/launch/start browser or profile, environment, config profile, AdsPower; create/update/delete/list profiles; groups, tags, proxies; kernel download/list; client patch; API check-status. User phrases like open environment or map to commands such as open-browser.

not rated 139 +2 2mo ago A Socket: warnSnyk: failSkillSpector: warn 69 tokens original MIT

skillward-audit

6669

Fangcun-AI/SkillWard

Skill Claude CodeCodex

Security-audit a third-party skill bundle (folder with SKILL.md, or .zip / .tar.gz archive) before installing it, using the SkillWard cloud scanner. Trigger on any natural safety question about an external skill — "is this skill safe?", "audit / scan / review this skill", "should I install this?", "trustworthy?", "any…

not rated 139 +1 2mo ago A 131 tokens

bun-docs

6670

stefanprodan/cctop

MCP server Claude CodeCodexCursor +2

MCP server "bun-docs", hosted remotely at bun.com, as configured in stefanprodan/cctop.

not rated 139 17d ago A tokens not measured original Apache-2.0

ai-agent-daily-mentor

6672

Marcos-wu/ai-agent-daily-mentor

Skill Codex

A Chinese-language study mentor for learning how to build AI agents over an eight-week plan. It structures daily six-hour lessons around an AI interview project and keeps linked notes in Obsidian, a note-taking app.

not rated 139 +1 3mo ago A 123 tokens

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: