1,396 mods tagged openai that install into Codex, measured the same four ways as everything else here: what each costs in tokens on every session, what a security scan found and why, whether it is the original, and what changed.
Skill Claude CodeCodex
Role: YC Office Hours × Your-Actual-Repo Inputs: user task description (conversational) Outputs: .magneto/sprints/ /design.md Next skill: /plan Audit actions: think.started, think.questionsasked, think.designdrafted.
Skill Codex
Direct, design, implement, animate, critique, audit, polish, and deploy distinctive production frontend interfaces for websites, landing pages, web apps, dashboards, mobile concepts, and desktop shells. Use for new frontend builds, redesigns, bland or visually generic UI, messy interfaces, design systems, Vue Bits or…
Skill Codex
Supervise explicitly delegated engineering work across isolated worktrees and resumable tasks, preserving ownership, acceptance evidence, and the overall outcome. Use for requests to coordinate multiple workers or supervise an ongoing delivery queue. Ordinary coding, status questions, worktree operations, and…
Skill Claude CodeCodex
Guidance for choosing the smallest suitable development process based on a task's risk and complexity.
Skill Codex
A guided BaZi, or Four Pillars, reading method based on a person's Gregorian birth date and exact birth time. BaZi is a Chinese astrology system that maps the birth moment to symbolic pillars, elements, and related patterns.
Skill Claude CodeCodex
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
9398-haha/codex-reconnect-repair
Skill Codex
Diagnose and safely repair Codex "Reconnecting... 1/5" through "5/5" loops in the CLI, desktop app, or IDE on macOS, Linux, and Windows. Use when a Codex turn stalls on repeated stream reconnects or only succeeds after HTTPS fallback; do not use for generic login, quota, model, or rate-limit errors.
Skill Claude CodeCodex
API operations for pets (6 endpoints).
Skill Codex
Implement a feature, bug fix, or refactor after checking its architectural fit. Use for issues, legacy tickets, or direct coding requests that need decisions about component responsibilities or interfaces. Plan, implement, and verify against focused acceptance cases. Do not use for issue writing, planning-only…
Skill Codex
Run a structured pre-task alignment interview for complex or ambiguous work. Use when the user asks to be grilled, wants questions before execution, requests requirements discovery or scope alignment, or when unresolved goals, constraints, tradeoffs, risks, or acceptance criteria could materially change a complex…
Skill Codex
Use for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs/products and ChatGPT Work. Also use for model choice/migration, prompting…
MCP server Claude CodeCodexCursor +2
A Semantic Type System for AI outputs — validate intent, not just shape. Runs locally from the semantix-ai Python package.
Skill Codex
Plan or revise the smallest reliable AI setup for a concrete project. Use when the user explicitly invokes $build-ai-team; asks whether one Agent or several Agents are needed; requests a team plan or an add, merge, replace, keep, ownership, or handoff change to an existing Agent team; or asks which model configuration…
MCP server Claude CodeCodexCursor +2
Typed MCP server for OpenAI Ads and ChatGPT Ads via the Advertiser API. Runs locally from the openai-ads-mcp Python package.
MCP server Claude CodeCodexCursor +2
Semantic search over WSO2 docs (APIM, IS, MI, Choreo, Ballerina) via RAG and pgvector. Runs locally from the wso2-docs-mcp-server npm package. Needs 5 environment variables to run.
trakkr-aisearch/openai-ads-mcp
MCP server Claude CodeCodexCursor +2
OpenAI Ads MCP for ChatGPT Ads campaigns, creatives, audiences, insights, and conversions. Runs locally from the openai-ads-mcp npm package. Needs 3 environment variables to run.
Skill Claude CodeCodex
Multi-agent orchestration engine for complex tasks. Use when you need to break a complex query into subtasks, run them in parallel with a DAG engine, and synthesize results. Triggers on: multi-agent, parallel execution, orchestrate, DAG, decompose task, dynamic workflow.
MCP server Claude CodeCodexCursor +2
TypeScript stdio MCP server and CLI for Telegram bots. Runs locally from the tgfmcp npm package.
Skill Claude CodeCodex
Find the LLM call you didn't need — your GPT call is a regex. Static, zero-config linter that flags unnecessary GPT/Claude/AI API calls a regex, the stdlib, or a library already does (parsing dates, extracting emails/JSON, sorting, classifying with fixed labels). Runs locally, no model, no API key, nothing phones…
MCP server Claude CodeCodexCursor +2
MCP server "mcp-ask-questions" as configured in bernierllc/brain-trust-mcp. Runs locally from the mcp-ask-questions Python package.
benitomartin/gmail-telegram-mcp-server
MCP server Claude CodeCodexCursor +2
MCP server "gmail-telegram-mcp-server" as configured in benitomartin/gmail-telegram-mcp-server. Runs locally from the gmail-telegram-mcp-server Python package.
zhoufz021/interpret-modeling-problems
Skill Codex
A method for turning a mathematical modelling contest problem and its attachments into a checked plan for solving and documenting it.
MCP server Claude CodeCodexCursor +2
Drop-in compression for LLM agent tool outputs. Shrink bloated HTML/JSON/log results before they re-enter context — cut tokens, stay on-task, keep full output retrievable. Runs locally from the tooltrim Python package.
Knuckles-Team/audio-transcriber
Skill Claude CodeCodex
Develop and maintain the Audio Transcriber connector while preserving its Whisper backend boundary, MCP tool surface, typed transcript ingestion, optional hardware behavior, package resources, and public-first evidence.
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: