LazyCodex CLI
A layer on top of OpenAI Codex that adds project memory, planning and completion checks before a task counts as done
- 3,911 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Installs and runs the third-party oh-my-openagent package, which controls Codex's behavior
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/lazycodexDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Installs and runs the third-party oh-my-openagent package, which controls Codex's behavior
This is third-party code. Review the repository files before installing.
What it does
LazyCodex sits on top of the Codex CLI and adds a harness for working with large codebases: the agent keeps project memory across sessions, breaks a task into a plan before executing it, and does not mark work done without passing a verification step. It is implemented as a wrapper around the oh-my-openagent (OmO) project, whose installer runs through an npx command. There is also an experimental way to install it from inside Codex's plugin marketplace.
Who it is for. For developers who use Codex on large or long-lived projects and want the agent to remember context and stop submitting unfinished work.
Good fit when
- Codex loses project context between sessions
- You need a complex task turned into a plan before it is executed
- You need the result verified before a task counts as done
Not a fit when
- You are not using Codex but a different agent
- Tasks are simple and do not need project memory or a separate planning step
Example request
Break this task into a plan, execute it step by step and don't mark it done until it passes verificationLimitations
Works specifically as a layer on top of Codex and needs Node.js to run the npx installer. The project is relatively young; the README points directly to the oh-my-openagent package as its base.
How to disable. Check the oh-my-openagent (omo) installer for its removal command, or delete the configuration and files it added to the project and your Codex profile.
FAQ
How does LazyCodex differ from plain Codex?
Codex on its own does not keep project memory across sessions and does not require an explicit plan or verification. LazyCodex adds these three layers on top of the standard Codex CLI.
Can I install it from the Codex plugin marketplace?
The README calls this an experimental path: run /plugins in Codex, open the Add Marketplace tab, point it at the lazycodex repository, then install omo from the sisyphuslabs marketplace.
Discussion
No questions or reviews yet.
Related
CLI toolsA CLI that gives six coding agents project context, over 80 skills, verification and resumable tasks across sessions
OpenAI's official plugin: Codex reviews of your changes and task delegation to Codex from inside a Claude Code session
Statusline HUD for Codex CLI inside tmux: context fill, tokens, branch, MCP servers and subagents stay visible in the session.
A kit for porting a Claude Code workflow to OpenAI Codex CLI for multi-tenant PHP/Bitrix24-Marketplace projects
Codex MCP Tool (cexll)
Codex MCP Tool
An MCP server that sends tasks to Codex CLI from Claude Code and Cursor: code review via @ refs, a sandbox, patch edits, ideas
A Claude Code skill that drives Codex over JSON-RPC: tasks, code reviews, parallel research and messaging between two agents.
README in short
The README presents LazyCodex as the one true agent harness for complex codebases inside Codex: project memory, planning, execution and verified completion. Installation comes down to a single npx command that actually calls the oh-my-openagent package with the --platform=codex flag. It also describes an experimental install path through the Codex plugin marketplace.