Skills for Codex

217,404 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

Nyrest/capacities-mcp-enhanced

Skill Codex

Operate Capacities safely and precisely through the Capacities MCP server. Use whenever a user asks to inspect, search, read, create, update, append to, delete, or upload Capacities objects, pages, tasks, tags, web links, media files, blocks, properties, collections, or Daily Notes; when choosing structured blocks…

not rated 2 1mo ago A 97 tokens original MIT

agents

17474

IlkhamFY/epistemic-foraging

Skill Claude CodeCodex

Drop-in instructions for any AI agent connected to the foragekit MCP server (uvx foragekit serve --mcp). Paste this into your agent's instructions, or install it as a skill. It teaches the loop; the tools enforce the rules.

not rated 2 2mo ago A 0 tokens original Apache-2.0

use-wsl

17475

Yuyu123fish/codex-win-to-wsl

Skill Claude CodeCodex

Use one wslexec call per user-requested non-interactive Linux execution when Windows-native Codex needs WSL. Preserve the project working directory and never probe or retry automatically.

not rated 2 2mo ago A 40 tokens original MIT

fan-manager-automatic

17476

Knuckles-Team/fan-manager

Skill Claude CodeCodex

Use when you need automatic, temperature-driven fan speed control on a Dell PowerEdge server — continuously adjusts fans to a logarithmic curve between configured min/max temperature and fan-speed bounds (CONCEPT:FM-OS.governance.service-writes-fan-level).

not rated 2 7d ago A 57 tokens original MIT

multi-user-trip-planner

17477

ZGentleman/SyncTravel-skills

Skill Claude CodeCodex

Plan coordinated multi-user high-speed rail trips; when users need multi-person trip planning from different origins to one destination.

not rated 2 5mo ago A 28 tokens

cel-lib-doc-generator

17478

cel-expr/skills

Skill Claude CodeCodex

Generates and updates standardized README.md documentation for CEL extension libraries in C++, Go, and Java by extracting declarations, functions, macros, types, signatures, and examples from source code.

not rated 2 23d ago A 42 tokens original Apache-2.0

dig-for-discogs

17479

WOIII-me/Discogs-MCP

Skill Codex

Use DIG's read-only Discogs workflows to search the catalogue or an authenticated collection, inspect releases and masters, compare pressings, rank sonic/collector/value evidence, summarize collection taste, inspect an own wantlist, and request collection-aware recommendations. Trigger for Discogs release IDs…

not rated 2 yesterday A 106 tokens original MIT

pursr

17480

0xheycat/pursr

Skill Claude CodeCodex

Use Pursr for browser screenshots, scripted visual operation, visual regression, accessibility audits, DOM inspection, and MCP-driven browser sessions. Use when a user asks an agent to inspect a site, operate an existing browser session, fill or draft UI content, record a tutorial, compare visuals, debug layout, or…

not rated 2 2mo ago A 85 tokens original MIT

searxng-settings-editor

17481

Knuckles-Team/searxng-mcp

Skill Claude CodeCodex

Inspect and edit the EMBEDDED SearXNG instance's settings.yml (the private, loopback-only, zero-config search fallback the searxng-mcp server can own end to end when no external SEARXNGURL is configured). Use when the agent or operator wants to change what the embedded instance does — enable/ disable formats, flip…

not rated 2 7d ago A 152 tokens original MIT

jordnlvr/MendixToolkit

Skill Claude CodeCodex

GATED WRITE. Clone an existing well-built Mendix page (ideally a gold page) to a new name with optional entity rebinding, via the mxcli MDL round-trip. Routes through the shadow-write engine (7 safety pillars; live .mpr untouched until atomic swap). Pre-classifies the source page as SIMPLE / COMPLEX / UNCLONEABLE…

not rated 2 4mo ago A 146 tokens

alf

17483

blacktop/alf

Skill Claude CodeCodex

Agentic LLDB fuzzer and crash-triage toolkit for Apple Mach-O on arm64(e). Use this skill whenever a user mentions alf, wants an AI agent to drive LLDB over MCP, asks about triaging a crash on macOS, wants to fuzz a Mach-O target with LLM guidance, is debugging a macOS kernel via Virtualization.framework / KDP /…

not rated 2 5mo ago A 177 tokens original Apache-2.0

agent-routing

17484

learn-by-exploration/ai-powerhouse

Skill Claude CodeCodex

Use this FIRST when unsure which agent, skill, or command to invoke. Maps task types to the right tool from this harness.

not rated 2 3mo ago A 29 tokens original MIT

commune-email

17485

black22345/commune-cookbook

Skill Claude CodeCodex

I give you a real email inbox and let you send, receive, search, and manage email threads programmatically via the Commune API. Every inbox I create is RFC 5322 compliant — replies thread correctly in any email client, including Gmail, Apple Mail, and Outlook.

not rated 2 2d ago A 0 tokens original MIT

agnes-media-generation

17486

Ryderey/agnes-mcp-studio

Skill Claude CodeCodex

Use only when the user explicitly mentions "agnes" (case-insensitive) and asks to generate, edit, combine, or animate images or videos with Agnes AI. Do not trigger for generic media generation without Agnes, media analysis, text generation, search, or live streaming.

not rated 2 11d ago A 59 tokens original MIT

iot-gateway

17487

KerberosClaw/kc_iot_gateway

Skill Claude CodeCodex

Read and control IoT devices across multiple protocols (MQTT, Modbus, CoAP, Webhook) via a unified gateway.

not rated 2 6mo ago A 31 tokens original MIT

hive-connect-repo

17488

Hivemind-OSS/Hivemind

Skill Claude CodeCodex

Register a repo with the server-side census sync: hive repo add writes the durable repo registry (the sync daemon picks it up on its next tick — no restart), private remotes authenticate via a token env var NAME (never a stored secret), and hivehealth(includecensushealth=true) verifies both that the sync daemon itself…

not rated 2 2mo ago A 150 tokens original Apache-2.0

gatekeeper

17489

Gldywn/gatekeeper

Skill Claude CodeCodex

Read and change a database safely through Gatekeeper. You propose SQL, a human approves and runs it in Beekeeper Studio, and the rows come back to you; you never connect to the DB or run SQL yourself. Reads are the default; a write runs only if a human arms write mode. Use this whenever you need to read data, run a…

not rated 2 changed 11d ago A 125 tokens original MIT

paper-writing

17490

Morningstar202604/ScholarSeed

Skill Claude CodeCodex

A Chinese-language workflow for producing research papers from topic selection through final checks. It covers research, outlining, writing, charts, citations, formatting, and review, with required checks between stages.

not rated 2 changed 28d ago A 121 tokens

choice-pilot

17491

houguangyu010416-star/choice-pilot

Skill Codex

Present context-aware ChoicePilot buttons and progressively clarify ambiguous requests. Use when uncertainty about the objective, scope, constraints, authorization, risk, cost, privacy boundary, external effects, preservation requirements, or acceptance criteria could materially change the work. Ask one high-value…

not rated 2 2mo ago A 98 tokens

machineread-audit

17492

georgejieh/MachineRead-Preview

Skill Claude CodeCodex

Use when auditing a public website for AI visibility, agent accessibility, scrapability, or search-discovery readiness with the free MachineRead Essentials audit. Triggers: 'audit this URL for AI readiness', 'check if the site is agent-friendly', 'run a MachineRead audit', 'get a public-readiness score'. Calls POST…

not rated 2 2mo ago A 127 tokens original MIT

hermes-dispatch

17494

AojdevStudio/hermes-satellite

Skill Claude CodeCodex

Dispatch a task to Hermes over the async MCP bridge, optionally run the background watcher, then verify Hermes's result as an independent satellite verifier. Use when dispatching work to Hermes ("send this to Hermes"), running the Hermes work queue, or acting as the satellite verifier of a Hermes result. Reach for it…

not rated 2 6d ago A 85 tokens original MIT

reactor

17495

keugenek/reactor

Skill Claude CodeCodex

Predict LinkedIn post performance before publishing. Get GO/WAIT/IMPROVE/NO verdict, estimated impressions, debate score, cringe detection, hook analysis, and timing optimization. Use when user mentions LinkedIn posts, content strategy, post drafts, or engagement optimization. Zero LLM calls — instant predictions via…

not rated 2 6mo ago A 70 tokens original MIT

execplan-run

17496

CueCrux/Crux

Skill Claude CodeCodex

Execute and CLOSE an ExecPlan end-to-end in CueCrux — the execution half that execplan-synthesize/appraise/research (authoring half) hand off to. Runs the milestone loop: claim from the ranked board, announce focus for collision detection, worktree, implement, gate fact, PR, shepherd checks, merge, next milestone…

not rated 2 changed 16d ago A 174 tokens original Apache-2.0

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: