CLI
The lazycodex-ai npm bin, how it forwards to OmO, the --dry-run flag, and the in-session command pillars.
LazyCodex provides one CLI: the lazycodex-ai npm bin. It is a thin forwarder — every invocation expands into an omo command run through npx. There is no global install; always invoke via npx.
How it forwards to OmO
The bin reads your arguments and forwards them to oh-my-openagent. The install subcommand is special-cased to pin the Codex platform; everything else passes straight through.
npx lazycodex-ai installexpands to:
npx --yes --package oh-my-openagent omo install --platform=codexAny arguments after install are appended verbatim. For example:
npx lazycodex-ai install --no-tui --codex-autonomous
# → npx --yes --package oh-my-openagent omo install --platform=codex --no-tui --codex-autonomousAny first argument other than install forwards directly to omo with no platform pin added:
npx lazycodex-ai <args...>
# → npx --yes --package oh-my-openagent omo <args...>--dry-run
Put --dry-run as the first argument to print the resolved npx command instead of running it, then exit:
npx lazycodex-ai --dry-run install --no-tui --codex-autonomousprints:
npx --yes --package oh-my-openagent omo install --platform=codex --no-tui --codex-autonomous--dry-run is stripped before forwarding, so the remaining arguments resolve exactly as they would in a real run. Use it to confirm the exact omo invocation before executing.
Exit behavior
The bin runs the resolved command with inherited stdio and exits with that command's status. If npx itself fails to spawn, it prints the error and exits non-zero.
In-session command pillars
Once installed, LazyCodex registers OmO's command pillars inside Codex. These are typed in your Codex session, not on the shell. The installer shows the exact $command syntax.
| Command | Type this | What it does |
|---|---|---|
$ulw-plan | $ulw-plan "what to build" | Prometheus strategic planner. Writes a plan to plans/<slug>.md. Never writes product code. |
$start-work | $start-work [plan-name] [--worktree <path>] | Executes a plan until every checkbox is done. Prints ORCHESTRATION COMPLETE. |
$ulw-loop | $ulw-loop "task" [--completion-promise=TEXT] [--strategy=reset|continue] | Self-referential loop until Oracle-verified completion. Caps at 500 iterations in ultrawork mode, 100 in normal mode. |
/init-deep | /init-deep | Generates hierarchical AGENTS.md project memory. |
See the Commands overview for the full breakdown.