Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,012 indexed, measured the same four ways as everything else here.
Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted…
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
A development and debugging guide for vLLM and vLLM-Ascend, tools for running machine-learning models to generate responses. It covers inference accuracy checks, service management, automated tests, and code fixes for single-machine or split deployments.
Detect silent agent failures and memory degradation. Use when asked for an agent health check, when agent behavior seems off or output quality drops, after long unattended runs, or as part of a scheduled maintenance pass.
Search past Claude Code and Codex sessions. Triggers: /memex, "search old conversations", "find a past session", "recall a previous conversation", "search session history", "what did we discuss", "remember when we".
A workflow for creating a custom 3D personal website from a person's résumé, experience, and design direction. It can produce styles such as interactive game worlds, driving explorations, and archival interfaces.
Generate XiaoHongShu / social ranking cards with HTML preview and PNG export. Supports Style A-H: Dark Tech, Apple Minimal, White Editorial, Pastel, Magazine, Dark Cinematic, macOS Skill Card, Compact macOS Card. Use for ranking infographics, GitHub/NPM/AI tool trends, knowledge cards, social carousels, and…
Test quality auditor that reviews existing test suites—audits, deletes, rewrites, and fills genuine gaps. Use when asked to review tests, improve test quality, or audit a test suite. Does NOT blindly add tests.
Write correct, idiomatic THRML code, centered on Ising machines and how they are trained. THRML is Extropic's JAX-based GPU simulator for the block Gibbs sampling programs that run natively on Extropic's probabilistic computing hardware. Use this skill whenever the user mentions THRML, Extropic, probabilistic…
MCP server "microvm-sandbox" as configured in CodeDuet/codeduet-microvm-ai-agent-sandbox. Runs src.mcp.server with python. Needs 3 environment variables to run.
MCP server "naver-blog" as configured in space-cap/naver-blog-mcp. Runs locally from the naver-blog-mcp Python package. Needs 1 environment variable to run.
A MCP server wrapper for using the entire Model Context Protocol without tool limits, missing concepts, or context overload. Runs locally from the jailbreak-mcp npm package.
★not rated 12▲
+1 8mo agoA
tokens not measured
GPL-3.0archived
A local service that lets an AI access Japan’s official public data, including statistics, company records, real-estate information, and invoice data. It requires three environment variables to run.
★not rated 12 8mo agoA
tokens not measured
originalMIT
The trust and intelligence layer between AI agents and your database. Runs locally from the schemabrain Python package. Needs 1 environment variable to run.
★not rated 12 2mo agoA
tokens not measured
originalApache-2.0
Write-capable PDF toolkit MCP: 22 tools to read, create, render, encrypt, merge & fill PDFs. Runs locally from the @aryanbv/pdf-toolkit-mcp npm package.
★not rated 12 3mo agoA
tokens not measured
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: