omx --madmax --high
Start the interactive Codex session with recommended settings for trusted environments.
Your codex is not alone.
Multi-agent orchestration layer for OpenAI Codex CLI. Build faster with staged team pipelines, persistent memory/state MCP servers, and extensible hooks.
# 1. Launch interactive Codex session
$ omx --madmax --high
# 2. Use keywords inside Codex for workflows
$deep-interview "clarify the auth change"
$ralplan "approve the implementation plan"
$ralph "carry the plan to completion"
omx --madmax --high
Start the interactive Codex session with recommended settings for trusted environments.
$deep-interview
Use inside Codex when intent or boundaries are still unclear. Socratic clarification before planning.
$ralph or $team
Choose $ralph for persistent completion loops, or $team for coordinated parallel execution.
Released: June 1, 2026 — HUD/session ownership is more durable, Autopilot replay and context handling are safer, plugin hook/cache correctness is stricter, Team startup/disablement behavior is clearer, and release/CI evidence is tighter.
HUD panes are scoped by leader/source pane, duplicate legacy panes are deduped after prompt revive, deleted-cwd doctor panes are avoided, escaped tmux separators parse correctly, and native session-id drift preserves ownership.
Completed terminal turns no longer reactivate Autopilot, context snapshots are seeded and hardened, task-seed provenance is clearer, and planning phases avoid editing under native session drift.
Stale plugin hook cache refresh is fixed, setup mode survives update refresh, launcher JSON fallback behavior is preserved, and mirror sync verifies plugin hook metadata.
Team mode can be disabled, tmux worktree startup compatibility is fixed, native executor lanes remain leaf-only, and default native subagent routing guidance is corrected.
Self-hosted Linux runner selection and GJC evidence lane optimization reduce avoidable CI churn while release readiness records local, e2e, live, pack, and publication gates.
The core OMX skill. Since v0.13.1, every team worker runs in an isolated git worktree by default — no flags needed, no merge conflicts, automatic integration.
Every worker gets a dedicated git worktree at .omx/team/<name>/worktrees/worker-N. No --worktree flag needed — it's the default. Workers write to isolated detached branches; the leader workspace stays clean.
The leader continuously integrates worker commits via merge, cherry-pick, or cross-worker rebase strategies. Conflicts are detected early and reported in integration-report.md. Auto-commit ensures no work is lost.
Run Codex, Claude, and Gemini workers side-by-side with OMX_TEAM_WORKER_CLI_MAP. Each worker gets its own worktree regardless of provider. Full staged pipeline: plan → exec → verify → fix.
# Use $team inside Codex (recommended)
$team 3:executor "refactor auth module"
Team started: refactor-auth-module
workers: 3 (worktrees: automatic, detached)
# Advanced: CLI operator surface
omx team 3:executor "refactor auth module"
omx team status refactor-auth-module
# Mixed providers with worktrees
OMX_TEAM_WORKER_CLI_MAP=codex,claude,gemini \
omx team 3:executor "full-stack implementation"
Everything you need for autonomous software development with OpenAI Codex CLI
33 specialized prompts via /prompts:name for targeted expertise across implementation, review, domain, and coordination lanes.
37 workflow skills and command surfaces via $name syntax for autopilot, team orchestration, planning, recovery, and QA cycles.
Isolated parallel execution with automatic git worktrees. Workers get dedicated worktrees by default — zero merge conflicts, automatic commit integration, and incremental merge tracking.
State, memory, code intelligence, and trace servers (5 total) for persistent context and cross-session learning.
plan → prd → exec → verify → fix lifecycle for structured, evidence-based development workflows.
--yolo, --high, --xhigh, --madmax modes for granular control over reasoning effort and execution intensity.
Get up and running in seconds with npm
npm install -g @openai/codex
npm install -g oh-my-codex
omx setup && omx doctor
omx --madmax --high
33 specialized prompts organized by domain, review depth, and orchestration responsibility
Repeatable workflows triggered by keywords or $syntax
| Keyword | Skill Name | Description |
|---|---|---|
autopilot |
autopilot | Full autonomous execution from idea to working code |
ralph |
ralph | Self-referential loop with verifier verification until completion |
ulw |
ultrawork | Maximum parallelism with parallel agent orchestration |
team |
team | N coordinated agents using Codex CLI native teams |
plan |
plan | Strategic planning with consensus and review modes |
research |
research | Parallel scientist agents for comprehensive research |
cancel |
cancel | Stop execution modes and clear active state |
tdd |
tdd | Test-first development with red-green-refactor cycle |
build-fix |
build-fix | Fix build errors, type errors, and toolchain failures |
code-review |
code-review | Comprehensive code review across all quality dimensions |
security-review |
security-review | Security audit focusing on vulnerabilities and trust boundaries |
Seamlessly connect your Codex workflows with Discord for real-time notifications and team collaboration.
Easily send build status, test results, and agent updates to your Discord channels using the configure-notifications skill.
"configure discord webhook"
Deploy custom bots to listen for commands, trigger workflows, and provide interactive feedback directly within your Discord server.
"setup discord bot"
Unified outbound delivery for all your notification channels with intelligent routing and status signaling.
Send notifications to Discord, Slack, Telegram, and custom webhooks through a single OpenClaw gateway. Intelligent routing ensures messages reach the right channel.
Reliable delivery confirmation with retry logic. Track notification status in real-time and ensure critical alerts never get lost.
Connect your Codex workflows to Telegram for instant mobile notifications and bot interactions.
Configure your Telegram bot to receive build updates, deployment notifications, and agent status messages directly in your chat.
"configure telegram notifications"
Control your Codex agents via Telegram messages. Start workflows, check status, and receive summaries without leaving your mobile device.
"setup telegram commands"