Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,469 indexed, measured the same four ways as everything else here.
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
★not rated 34 4mo agoA
tokens not measured
originalBSD-3-Clause
A workflow for analysing a reference video and creating prompts and replacement-material plans for a similar video. FFmpeg extracts video frames, and a vision model examines them.
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.
MCP server exposing UniFi application API documentation (Network, Protect, Site Manager, InnerSpace, Mobility, Carrier Fabric) as queryable tools. Runs locally from the mcp-unifi-applications Python package.
★not rated 34 4d agoASocket: warn
tokens not measured
originalMIT
Builds x402 HTTP-native payment applications on Algorand using TypeScript. Covers clients (fetch, axios), servers (Express, Hono), facilitators, paywalls, Next.js integration, and the @x402/core library. Use when implementing x402 payment flows in TypeScript, creating payment-gated APIs, building x402 facilitators or…
Guidance for an AI agent to enrich an Open Knowledge Format (OKF) bundle with high-quality concept descriptions using its own LLM — grounded in the bundle's schema, data profile, and samples — then optionally sync them back to the source. Use when an OKF bundle has missing, weak, or low-quality descriptions that…
Send the user a Slack message as Claude — progress, a finished task, an alert, anything worth interrupting them for. Use whenever you want to reach the user outside this chat. Required instead of the Slack connector, which posts as the user and doesn't notify them.
A 4x pipeline audit that scans past project artifacts for unresolved problems. It checks feature gaps, escalation and review reports, and repeated lessons, then classifies findings by priority and category.
Build interactive HTML artifacts for the Telegram Mini App. Use for ANYTHING that benefits from being visual/interactive: recipes (with portion calculators), shopping lists (with localStorage), calculators, charts, diagrams, reference sheets, reports, and tools. When a user asks for food, recipes, meal planning…
Professional personal finance advisor specializing in plain-text accounting with Beancount and Fava. Use when users need help with: (1) Analyzing spending habits and financial patterns from Beancount files, (2) Creating or understanding Beancount transactions and syntax, (3) Financial planning, budgeting, and…
A guided tool for creating personalised IELTS speaking practice materials. IELTS is an English exam, and the tool turns a learner’s answers and conversation into a personal profile and a static study website.
Perform statistical tests, hypothesis testing, correlation analysis, and multiple testing corrections using scipy and statsmodels. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
Refine an Original Goal into an acceptance-testable Overall Goal for Ultra-Goal through read-only exploration and user alignment. Manual invocation only.
A 100-day action plan for an early-stage one-person AI company, meaning an AI business run mainly by one person. It provides daily actions, milestones, progress tracking, and a timeline toward first revenue.
Multi-phase delivery framework that MUST preserve session continuity and SHOULD support SHA-based rollback.
★not rated 33 4mo agoA19 tokens
originalMIT
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: