Skills for Codex

217,908 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

minimax-mcp

19226

ameno-/pi-minimax-mcp

Skill Claude CodeCodex

MiniMax Web Search & Image Understanding MCP for Pi.

not rated 2 8mo ago A 15 tokens original MIT

ifttt

19227

IFTTT/ifttt-plugins

Skill Claude CodeCodex

Connect OpenClaw to IFTTT's hosted MCP server and automate hundreds of services — discover triggers and actions, build and manage Applets, and run actions and queries. Use when the user mentions IFTTT, asks what they can automate, or describes an automation like "when X happens, do Y".

not rated 2 15d ago A 67 tokens original MIT

xtofuub/frida-mcp-server

Skill Claude CodeCodex

Reverse engineers iOS applications using Frida dynamic instrumentation to understand internal logic, extract encryption keys, bypass security controls, and discover hidden functionality without source code access. Use when performing authorized iOS penetration testing, analyzing proprietary protocols, understanding…

not rated 2 3mo ago B 97 tokens original MIT

wecom

19229

Fortytwoo/codex-tencent-connectors

Skill Claude CodeCodex

Use when the user asks to read or manage enterprise WeChat/WeCom messages, contacts, documents, meetings, schedules, or to-dos through the Tencent Connectors plugin.

not rated 2 2mo ago A 39 tokens original MIT

using-claude-cli

19230

developerz-ai/ui-debugger-mcp

Skill Claude CodeCodex

How to drive claude (Claude Code) as a non-interactive CLI tool — headless runs, MCP servers, permissions, output formats, and piping. Use when scripting Claude, spawning a sub-agent from another process, or wiring Claude into CI/automation.

not rated 2 15d ago A 61 tokens original MIT

arcagent-mcp

19231

araujota/arcagent

Skill Codex

Execute ArcAgent bounty workflows end-to-end via MCP tools. Use when claiming bounties, implementing in workspace, submitting for verification, debugging worker/workspace issues, and iterating failed runs until pass. Continue retry/resubmit loops based on verification feedback until either (1) verified PR and payout…

not rated 2 7mo ago A 77 tokens

protect-agent-action

19232

JesseGdotIO/hermesplant-mcp-server

Skill Codex

Gate consequential shell, Git, SQL, package, deployment, infrastructure, MCP, wallet, or x402 actions with Hermes Plant Agent Action Safety. Use before executing commands that mutate data, production, money, infrastructure, or shared history; require authorized external disclosure and route unmatched consequential…

not rated 2 +1 2mo ago A 69 tokens original MIT

openeye

19234

dumbspacecookie/openeye

Skill Claude CodeCodex

Use this skill when the user wants to verify that a real-world physical procedure was performed correctly using camera input — bolt installation, equipment pre-op checks, lockout/tagout, PPE verification, lab protocols, surgical site prep. Also use when the user asks about AR/XR procedure verification, persistent…

not rated 2 4mo ago A 84 tokens original MIT

hugo-to-markdown

19235

chaunsin/agent-skills

Skill Codex

Convert Hugo documentation sites and Hugo-managed content into standard Markdown. Use when Agent needs to inspect a local Hugo repository, read hugo.toml or config files, content/, archetypes/, layouts/shortcodes/, layouts/markup/, and related docs content, then produce Markdown output with Hugo front matter…

not rated 2 14d ago A 137 tokens original Apache-2.0

velen-cli

19236

wordbricks/skills

Skill Codex

Use when the user wants to inspect company or customer data that lives behind Velen, configure Velen CLI org selection or local profiles, run ad hoc read-only SQL or source API operations advertised by a Velen-connected source, explicitly inspect a past Velen insight by public ID or catalog request, manage org-scoped…

not rated 2 2mo ago A 108 tokens

clicks-protocol

19237

clicks-protocol/clicks-protocol

Skill Claude CodeCodex

Integrate Clicks Protocol settlement routing into AI agent projects on Base. Use when building agents that hold, earn, receive, or transfer USDC, when asked about agent treasury management, x402 payment settlement, idle USDC routing, or agent referral attribution.

not rated 2 2mo ago A 57 tokens original MIT

abap-from-spec

19238

palimkarakshay/abap-mcp

Skill Claude CodeCodex

Turn a functional or technical spec into working, validated modern ABAP/RAP using abap-mcp — scaffold the foundation deterministically, implement behaviors, gate every file through fix/lint, generate tests, deliver in activation order. Use when the user has a requirement or spec and wants code started for them; do not…

not rated 2 changed 26d ago A 89 tokens original MIT

using-lwc

19239

JanYork/using-lwc

Skill Codex

Use when substantive project work, structural code questions, research, planning, debugging, architecture, decisions, document ingest, incident recovery, or verified context and results should survive future sessions; also when the user invokes $using-lwc or asks to search, update, repair, configure, or maintain an…

not rated 2 1mo ago A 76 tokens copy · 88% Apache-2.0

strikeradar

19240

alexpolonsky/agent-skill-strikeradar

Skill Claude CodeCodex

Monitor US-Iran strike probability using open-source indicators - news alerts, Iran internet connectivity, oil prices, flight traffic, military tanker detection, weather, Polymarket odds, and Pentagon activity. Use when user asks about "Iran strike probability", "strike radar", "Iran situation", "US attack Iran"…

not rated 2 7mo ago A 112 tokens original MIT

shiplight

19241

ShiplightAI/agent-skills-v2

Skill Claude CodeCodex

Shiplight QA toolkit — the single entry point for all Shiplight test/QA work. Use ONLY when the user explicitly says 'shiplight' (e.g. 'write a shiplight test', 'use shiplight to verify X', 'shiplight cover') or invokes /shiplight. Routes to subcommands: init, setup-test-auth, update, create-yaml-tests…

not rated 2 changed 1mo ago A Socket: warnSnyk: warn 101 tokens

music-producer-os

19242

frankxai/agentic-music-producer-os

Skill Claude CodeCodex

Orchestrate original songs, score-first piano/orchestra works, instrumentals, or guided meditations from brief through craft, notation, Suno/Lyria packets, taste review, and verified generation. Use for "make a song", "compose piano", "orchestra", "sheets/tabs", "produce this", "create in Suno", "Lyria", "guided…

not rated 2 changed 4d ago A 84 tokens

iterm2

19243

Mitscherlich/skills

Skill Claude CodeCodex

A skill for controlling the iTerm2 terminal app through its programming interface. It can work with terminal windows, tabs, sessions, panels, profiles, and layouts.

not rated 2 29d ago A 129 tokens

analysis

19244

microchipgnu/blindspot.news

Skill Claude CodeCodex

Produces structured judgment briefs for contested situations — news events, decisions, conflicts, strategy questions. Surfaces hidden bets, real disagreements, unspeakable truths, and who concretely pays. Use when the user wants sharper thinking about something messy, not a summary.

not rated 2 4mo ago A Socket: passSnyk: pass 54 tokens

dinero-best-practices

19245

dinerojs/skills

Skill Claude CodeCodex

Core best practices for the Dinero.js money library. Use when writing, reviewing, or refactoring code that creates Dinero objects, performs arithmetic on monetary values, or handles money in JavaScript/TypeScript. Triggers on imports from 'dinero.js', monetary calculations, or price/cost handling logic.

not rated 2 7mo ago A 70 tokens copy · 100% MIT

shux

19246

indrasvat/shux

Skill Claude CodeCodex

Drive terminal sessions, panes, and TUIs from an agent, and prove what they render. Five distinct jobs — multiplex terminal work (sessions/windows/panes) as a tmux/screen replacement; snapshot any pane as a pixel-perfect PNG, headless, with no terminal emulator or display server; run the lens verify loop (run → settle…

not rated 2 1mo ago A Socket: warnSnyk: warn 250 tokens

context-pod

19247

Nervous-Machine/context-pod

Skill Claude CodeCodex

Event Pod gives your agent a persistent world model — structured context that survives across sessions, models, and tools. Not a transcript. A causal model with certainty scores that gets sharper over time.

not rated 2 7mo ago A 0 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: