Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,942 indexed, measured the same four ways as everything else here.
Scaffold a new service under services/ in the builders-stack monorepo. Use when something needs its own URL, port, or independent deploy. Covers the package, entrypoint, config, Tilt, deployment registry, and shared small-image build path.
MCP server "pydepmancompanion" as configured in KemingHe/python-dependency-manager-companion-mcp-server. Runs locally from the py_dep_man_companion Python package.
★not rated 41 7mo agoA
tokens not measured
originalMITarchived
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
★not rated 41 6d agoA
tokens not measured
AGPL-3.0
Use when writing or reviewing Kotlin code that stores CoroutineScope, launches from init/non-suspending APIs, calls runBlocking, or catches broad exceptions around suspend calls.
A local MCP server for researching Korean law through 42 government APIs. It covers statutes, court decisions, local ordinances, treaties, tax interpretations, time-based comparisons, and guided legal research.
An MCP gateway that aggregates your existing MCP servers and lets you define which servers and individual tools each agent or subagent can access. Solves Claude Code's MCP context window waste where all tool definitions load upfront instead of being discovered when actually needed. Runs locally from the…
★not rated 41 9mo agoA
tokens not measured
originalMIT
Full Reality Check analysis - fetch source, perform 3-stage analysis, extract claims, register to database, and validate. The flagship command for rigorous source analysis.
Design an API end-to-end — from requirements to a validated OpenAPI spec. Generates stories for review, then produces a linted spec. Emmanuel Paraskakis's method for designing APIs with LLMs. Use when user says "/design-api" or asks to design an API from requirements or stories. For a single step only, use…
Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step…
Implements SEO, AEO, and GEO for Next.js App Router: Google Search Console + Naver Search Advisor (sitemap, robots, verification, Naver 80-char metadata), plus Answer/Generative Engine optimization (FAQPage, Review, Organization, BreadcrumbList JSON-LD, SSR crawlable pages, dynamic OG). Use when deploying a web app…
Drive the cmux native macOS terminal app from CLI or socket — workspaces, panes, surfaces, browser automation, notifications, sidebar metadata, session restore. Use whenever the user mentions cmux, wants to control terminal layout from an agent, automate browser panels on macOS, send notifications/flashes to the…
Product analytics with your AI agent: set up consent-based tracking, read funnels, paths, retention, experiments, and context, then recommend the smallest growth action using the official Agent Analytics CLI.
Expert sales council with 6 advisors (Cialdini, Hormozi, Rackham, Voss, Klaff, Schwartz) for pricing, persuasion, negotiation, copywriting, and pitch strategies.
Use for the H100 Triton fused RMSNorm + SiLU gate optimization task. Provides the workflow and MCP tooling for objective runs, rollback-safe config sweeps, source diagnostics, benchmark history, and final held-out verification.
Use when installing or setting up gossipcat multi-agent orchestration (parallel review, consensus, adaptive dispatch) in Claude Code or Cursor. Installs the gossipcat MCP server and hands off to gossipstatus() for all live rules.
Unofficial MCP server connecting OpenEvidence to AI agents via authenticated browser sessions. Runs locally from the openevidence-mcp npm package. Needs 1 environment variable to run.
★not rated 41 2mo agoA
tokens not measured
originalApache-2.0
The First-Time Principle at four layers: thought, planning, execution, output (including conversation). Write everything as if for the first time. Triggers on implementation, refactor, bug fix, doc/memory edit, planning, and any "just patch it" urge. Cross-platform: Claude Code, OpenAI Codex, OpenCode, OpenClaw…
Use when Codex work should route bounded implementation to lower-cost workers and reserve Sol for risky plan review or final evidence gates, or when installing or validating this workflow.
High-quality C++ OOP coding style (archibate / parallel101 lineage) that overrides sloppy AI-default C++. Use this skill WHENEVER writing, editing, refactoring, or reviewing C++ code (.cpp / .h / .hpp / .cc / .cxx), designing C++ classes, interfaces, APIs, or libraries, or when the user mentions C++ design, OOP…
★not rated 41
changed 8d agoA201 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: