Claude Code mod
codex-mod
Subagent types codex-mod:codex and project-declared roles answered by the local OpenAI Codex CLI (codex exec) instead of an Anthropic model.
Install
/plugin marketplace add diegoaleyvag/codex-mod
/plugin install codex-mod@codex-modMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L3Network: network, runs processes, writes files, drives Claude, reads files, reads env vars, reads the transcript, reads mod state, persists state, draws
- Sees
- every tool call, subagent spawns
- Draws in
AssistantMessageToolUse- Hooks
session.startsession.endtool.calltool.checkui.rendersession.receivesession.appendagent.offeragent.spawnturn.startturn.completeturn.step
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- diegoaleyvag/codex-mod
- Folder
.- Marketplace
codex-mod- Author
- Diego Leyva
- Type
- Workflow mods
- License
- MIT
- Last updated
- 21 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is codex-mod?
Subagent types codex-mod:codex and project-declared roles answered by the local OpenAI Codex CLI (codex exec) instead of an Anthropic model. It is a mod for Claude Code, from diegoaleyvag/codex-mod on GitHub.
What can the codex-mod mod access?
Its widest reach is "network" (network, runs processes, writes files, drives Claude, reads files, reads env vars, reads the transcript, reads mod state, persists state, draws). It sees every tool call, subagent spawns. It draws in AssistantMessage, ToolUse. Like any mod, it runs with your permissions.
How do I install codex-mod?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add diegoaleyvag/codex-mod and then /plugin install codex-mod@codex-mod.
Is codex-mod popular?
diegoaleyvag/codex-mod has 1 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 21 October 2026.
More workflow mods
codex-imagegen
1bngxyz/codex-imagegen
Adds a generate_image tool: Claude hands image requests to the local Codex (ChatGPT) CLI and gets back the saved file.
collapse-work
1FrogAi/Xenopus
Folds a finished turn's work under a "Worked for" row, leaving the final answer, like Codex
code-tab-latex-fix
1RainZL0/code-tab-latex-fix
Rewrite LaTeX in replies so the Claude desktop app's Code tab renders inline math instead of raw text
compact-jev
1edoproch/compact-jev
/compact-jev: Jev-guided verbatim compaction for Claude Code, called through Vercel AI Gateway. Never replaces /compact or auto-compaction.
cleaner-tool-lines
1macwilk/cc-extensions
Draws each tool call as one line, so the conversation reads straight through. Click a line to open the call.
cornerman
1m4cd4r4/cornerman
When a Claude Code chat gets long, Cornerman saves a handover, clears the chat and carries on by itself, up to the number of clears you set. Tables, lists, links and paths from the cleared chat stay one click away.
Browse the most popular Claude Code mods, all workflow mods, or the skills and MCP server directories.