openai for Codex

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.

Also for Codex: anthropic · Git and workflow · Python · Web3 and blockchain · React · TypeScript · Go · android · docker · Rust · bun · Localization

codex-skill-builder

121

hey-zeyu/codex-skill-builder

Skill Codex

Build, improve, package, and review Codex skills from rough ideas, workflows, scripts, README/API/CLI docs, or existing skill folders. Use when the user wants to create a new Codex skill, convert a repeatable workflow into a reusable skill, scaffold SKILL.md plus references/scripts/assets, validate a skill, or prepare…

not rated 2 4mo ago A 82 tokens original MIT

reconnect

122

SeemSeam/codex-reconnect

Skill Codex

Enable or disable tmux-bound disconnect recovery for the current Codex thread. Use only for the explicit invocations $reconnect on or $reconnect off inside a Codex CLI running in tmux.

not rated 2 3mo ago A 46 tokens

scalattice-cli

123

scalattice/scalattice-cli

MCP server Claude CodeCodexCursor +2

Scalattice CLI - session login, credits, fleet, Bracket coding harness, MCP. Runs locally from the scalattice-cli npm package.

not rated 2 today A tokens not measured original MIT

caozhangni/codex-plugin-discovery

Skill Codex

Use when a user asks what Codex plugins are available or can be used, wants plugin recommendations for a task, asks to find/search/discover installable plugins, asks about the plugin marketplace, or asks whether a plugin can help with a task.

not rated 2 5mo ago A 56 tokens original MIT

cao-operating-pulse

125

ClarentCinematics/Codex-Skills-for-Enterprise

Skill Codex

Produce Chief AI Officer operating pulses that blend portfolio governance, adoption reality checks, board-ready narratives, and playful signal framing. Use when Codex needs to brief a CAO, synthesize AI strategy updates, review initiative portfolios, assess shadow AI risk, or prepare executive AI operating rhythm…

not rated 2 4mo ago A 64 tokens original MIT

typecast

126

Alee02/typecast

Skill Claude CodeCodex

Use TypeCast to turn LLM output into validated, typed JVM values. Reach for it whenever code calls an LLM and then parses/validates the response by hand: extraction of case classes or Java records from text, classification/routing via sealed traits, constraint enforcement with retry, streaming partial JSON into a UI…

not rated 2 3mo ago A 86 tokens original Apache-2.0

ytunahankskn/oh-meine-excode

Skill Claude CodeCodex

Use when the user wants Codex to split work across multiple subagents, especially for implementation plus exploration or verification in parallel.

not rated 2 7mo ago A 31 tokens original MIT

erida34/encoding-fix-codex-skill

Skill Codex

Enforce script-only text encoding fixes in any repository. Use when files contain mojibake, broken Cyrillic/UTF-8 text, or UTF-8 BOM issues, and require Codex to run the bundled scripts/fixmojibake.py instead of manual or ad-hoc encoding edits.

not rated 2 7mo ago A 69 tokens

fork-tab

129

theelgreco/codex-fork-tab

Skill Codex

Open an exact fork of the active Codex CLI chat in a new terminal tab while leaving the source chat open. Use when the user asks to fork, branch, duplicate, or continue the current Codex conversation in another terminal, including phrases such as “fork this into a new tab” or “open a parallel copy of this chat.”.

not rated 2 2mo ago A 71 tokens original MIT

mcp

130

ianreboot/safeprompt

MCP server Claude CodeCodexCursor +2

Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM. Runs locally from the @safeprompt.dev/mcp npm package. Needs 3 environment variables to run.

not rated 2 4d ago A tokens not measured original MIT

token-saver

131

OpenWorkai/codex-token-saver

Skill Claude CodeCodex

A guide to reducing token use in Codex conversations, where tokens are the units of text sent to and from the language model.

not rated 2 7mo ago B 0 tokens original MIT

tokencost-dev

132

atriumn/tokencost-dev

MCP server Claude CodeCodexCursor +2

LLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM. Runs locally from the tokencost-dev npm package.

not rated 1 3d ago A tokens not measured original MIT

whisper-telegram-mcp

133

abid-mahdi/whisper-telegram-mcp

MCP server Claude CodeCodexCursor +2

MCP server "whisper-telegram-mcp" as configured in abid-mahdi/whisper-telegram-mcp. Runs locally from the git+https://github.com/abid-mahdi/whisper-telegram-mcp.git Python package. Needs 2 environment variables to run.

not rated 1 7mo ago A tokens not measured original MIT

codex-model-sync

134

gzy3894-png/codex-model-sync

Skill Codex

Repair and synchronize Codex CLI model catalogs for OpenAI-compatible third-party providers. Use when /model shows stale, missing, duplicated, or nested "All models" entries; reasoning efforts or context windows disagree with upstream; a provider exposes /models but Codex does not refresh it; or modelcatalogjson and…

not rated 1 3mo ago A 85 tokens original MIT

BlacklineCloud/agent-skills

Skill Codex

Review a Codex, Claude Code, or agent skill/plugin before public release. Use when the user wants to assess trigger quality, folder structure, documentation, validation gaps, GitHub readiness, or OSS release quality for an agent extension.

not rated 1 1mo ago A 53 tokens original MIT

windows-appshot

136

josephbartlett/windows-appshot-codex

Skill Claude CodeCodex

Use when the user invokes $windows-appshot or asks to create a Windows appshot bundle, including foreground-window screenshots, UI Automation text, metadata.json, prompt.md, or appshots generated by scripts/New-Appshot.ps1.

not rated 1 5mo ago A 50 tokens original MIT

openai-responses-mcp

137

uchimanajet7/openai-responses-mcp

MCP server Claude CodeCodexCursor +2

Lightweight MCP server (Responses API core). OpenAI integration + websearch. Runs locally from the openai-responses-mcp npm package.

not rated 1 2d ago A tokens not measured original MIT

mcp-knowledge-base

138

m4k00/mcp-knowledge-base

MCP server Claude CodeCodexCursor +2

MCP server for knowledge base functionality - Coming Soon. Runs locally from the mcp-knowledge-base npm package.

not rated 1 7mo ago A tokens not measured original MIT

sid12super/MCP-Deep-Researcher

MCP server Claude CodeCodexCursor +2

MCP server "agenticdeepresearcher" as configured in sid12super/MCP-Deep-Researcher. Runs locally from the agentic_deep_researcher Python package.

not rated 1 7mo ago A tokens not measured original MIT

openai-image-mcp

140

aleslanger/OpenAI-image-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server "openai-image-mcp" as configured in aleslanger/OpenAI-image-mcp-server. Runs locally from the openai-image-mcp npm package.

not rated 1 3mo ago A tokens not measured original MIT

llm-cost-guard

141

Wimoron/llm-cost-guard

MCP server Claude CodeCodexCursor +2

Track LLM costs, set budget limits, get alerts. One command to install, one line to use. Runs locally from the @wimoron/llm-cost-guard npm package.

not rated 1 4mo ago A tokens not measured original MIT

context7

142

JustineDevs/CRUX

MCP server Claude CodeCodexCursor +2

One of 3 in .mcp.json

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 1 2mo ago A tokens not measured

openai-image-mcp

143

lpenguin/openai-image-mcp

MCP server Claude CodeCodexCursor +2

MCP server for generating images using OpenAI's DALL-E 3. Runs locally from the @lpenguin/openai-image-mcp npm package.

not rated 1 6mo ago A tokens not measured

gpt-image-mcp

144

naporin0624/gpt-image-1-mcp

MCP server Claude CodeCodexCursor +2

OpenAI gpt-image (gpt-image-1 / gpt-image-2) MCP server with advanced image generation and editing capabilities. Runs locally from the @napolab/gpt-image-mcp npm package.

not rated 1 6mo ago A tokens not measured

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: