Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 269,319 indexed, measured the same four ways as everything else here.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-server-shufersal" as configured in matipojo/shufersal-mcp. Runs locally from the mcp-server-shufersal npm package.
Skill Claude CodeCodex
Safely inspect and archive explicitly selected or clearly disposable Paseo agents and test workspaces. Use when the user asks to preview cleanup candidates, reduce agent-list clutter, or archive explicit test, validation, fixture, or temporary sessions. Ordinary idle agents are resumable and are never auto-archived…
hunterLee666/deerflow2.0-project
Skill Claude CodeCodex
Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This…
MCP server Claude CodeCodexCursor +2
MCP server "py-mcp-youtube-toolbox" as configured in jikime/py-mcp-youtube-toolbox. Runs locally from the py-mcp-youtube-toolbox Python package.
MCP server Claude CodeCodexCursor +2
A backend for pydantic-AI agents and MCP servers. Runs locally from the llmling Python package.
yoanbernabeu/mcp-recherche-entreprises
MCP server Claude CodeCodexCursor +2
Ce MCP (Module de Connexion à une API) permet d'interagir avec l'API Recherche d'entreprises mise à disposition par data.gouv.fr. Runs locally from the mcp-recherche-entreprises npm package.
MCP server Claude CodeCodexCursor +2
MCP server "indesign" as configured in chris-enea/indesign-mcp. Runs /Users/honeycomb/indesign_mcp/server.py with /Users/honeycomb/indesign_mcp/venv/bin/python.
MCP server Claude CodeCodexCursor +2
MCP server "gitbook-mcp-server" as configured in tcsenpai/mcpbook. Runs locally from the gitbook-mcp-server npm package.
Skill Claude CodeCodex
Enforce exact, pinned package versions across a JavaScript/TypeScript repo and its agent tooling. Scans package.json dependencies, npm scripts, MCP server configs (.mcp.json, Claude/Cursor settings), and CI workflows for unpinned specs (^, , , latest, missing versions on npx). Pins everything to exact versions…
Nice-Wolf-Studio/claude-code-supabase-skills
Skill Claude CodeCodex
Manage file storage operations in Supabase Storage. Use for uploading, downloading, listing, and deleting files in buckets.
aybelatchane/mcp-server-terminal
MCP server Claude CodeCodexCursor +2
MCP server for AI agents to interact with terminal applications. Think Playwright for terminals. Runs locally from the mcp-server-terminal npm package. Needs 2 environment variables to run.
Skill Claude CodeCodex
Design thinking with forcing questions, anti-sycophancy, adversarial review. Reads past decisions and mistakes to avoid re-debating and front-load failure patterns.
OpenCageData/opencage-geocoding-mcp
MCP server Claude CodeCodexCursor +2
MCP server for OpenCage geocoding API. Runs locally from the @opencage/mcp-opencage-server npm package. Needs 1 environment variable to run.
Skill Claude CodeCodex needs its repo
Operate the belt CLI to evaluate headless coding agents (Claude Code, Cursor, Codex, Gemini, and others) end to end. Use when the user asks to write or run eval scenarios, compare agents, score outputs with rules or LLM judges, register a new agent adapter, interpret reports or benchmark cards, or set up evals in CI.…
Skill Codex
A one-time deployment tool that adds a project governance system built around AGENTS.md, project instructions, documentation, hooks, continuous integration, and maintenance scripts.
Leehyunbin0131/claude-ros2-skills
Skill Claude CodeCodex
Skill "ros2-microros" from Leehyunbin0131/claude-ros2-skills, covering micro-ros instructions (ubuntu 24.04 lts & ros 2 jazzy), 1. architecture, 2. documentation entry points, 3. key concepts & patterns and a. embedded client node setup (rclc in c).
MCP server Claude CodeCodexCursor +2
Authenticated local evidence paths for JavaScript and TypeScript coding agents. Runs locally from the @lubab/madar npm package.
Zaious/translate-academic-paper
Skill Claude CodeCodex
Full workflow for translating an academic paper PDF into a polished, self-contained HTML with a three-way view toggle (Chinese-only / bilingual / original-only). Covers document triage (native vs OCR'd-scan vs no-text-layer scan), column-aware text extraction, glossary building with web-verified standard term…
Skill Claude CodeCodex
Create the minimum execution contract needed to implement accepted product intent.
Skill Claude CodeCodex
Use this skill when the user wants shorter, more direct responses. Activate on: "crisp mode", "go crisp", "/crisp", "be brief", "less tokens", "cut the fluff", "shorter answers", "stop being verbose", "drop the filler", "skip the pleasantries", "no fluff", "just the answer". Do NOT activate for: "explain in detail"…
Skill Claude CodeCodex
Use when the user asks Codex to consult Claude Code, run a Claude advisor pass, get a Claude adversarial review, check a plan or diff with Claude, ask Claude to do a prepared coding, exploration, verifier, scout, or rescue task, inspect Claude advisor job status, fetch a Claude result, or cancel a Claude advisor job.…
Skill Claude CodeCodex
Generates a project closure report aggregating data from charter, plan-fact report, risk register, and lessons learned. Last artifact of the Closing phase. Summarizes project outcomes, deviations, realized risks, and lessons.
Skill Claude CodeCodex
Use when designing, implementing, auditing, hardening, or operating autonomous agent loops in this repository, including Codex/Grok/Claude Code style /loop workflows, explicit /goal runs, Git worktree orchestration, connector-backed automation, sub-agent execution, STATE.md handoffs, cost controls, maker/checker…
Skill Claude CodeCodex
A documentation-writing guide for Zensical, a documentation publishing engine. It covers plain language, consistent formatting, links between documents, and checking the built documentation.
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: