Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,975 indexed, measured the same four ways as everything else here.
MCP server "second-brain-github-mcp" as configured in manuelblinkert/second-brain-github-mcp. Runs locally from the second-brain-github-mcp Python package.
★not rated 4 2d agoA
tokens not measured
originalMIT
Guide for building a Phoenix-based evaluation harness for an MCP server. Use when you need to create or extend LLM-as-judge evaluations that measure how well an agent can accomplish realistic tasks using only the MCP server's tools. Covers the eval/phoenix module layout, dataset creation, the LangChain agent, judges…
Author RPG Maker XP games in natural language: read, write and render RGSS1 .rxdata. Runs locally from the rpgmaker-xp-mcp npm package. Needs 2 environment variables to run.
Default operating stance — act autonomously inside reversible, non-production surfaces, and HARD-STOP for explicit permission before any irreversible real-world action. Resolve ambiguity through the toolchain (durable memory → working notepad → internet → codebase → team docs) before spending the operator's attention.…
Chart a too-big effort as a shared map of decision tickets on the Gaia headquarters issue tracker, then resolve them one at a time until the way to the destination is clear. Use when someone says: "this is too big for one session", "chart a map", "wayfinder map", "plan this effort", "what do we need to decide first"…
Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
ZITADEL identity management platform (v4 GA, v2 API). Covers resource-based API for managing organizations, projects, applications (OIDC/SAML/API), roles, users, and OIDC settings via Connect RPC (HTTP/1.1 JSON) and REST endpoints. PAT or JWT assertion auth.
Use when analyzing suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules, sandboxing, and anti-analysis behavior.
Cambia el color de los iconos SVG de un proyecto PBIP sin tocar nada más — detecta qué colores hay, sustituye solo los que son colores de verdad (no referencias url(#id) ni selectores CSS), conserva la codificación de cada archivo y avisa de lo que no puede reescribir.
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.
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
Multi-account MCP server and CLI for the QuickFile beta REST API. Runs locally from the quickfile-mcp npm package.
★not rated 4 todayASocket: warn
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: