/execute
Delegate execution of a specific plan or plan step to Codex
$ npx -y skills add greenpolo/cc-multi-cli-plugin --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/execute
Context preview
What this command does when you run it.
Delegate execution of a specific plan or plan step to Codex
Command definition
execute.mddescription: Delegate execution of a specific plan or plan step to Codex
argument-hint: "[--plan <path>] [--background|--wait] [--resume|--fresh] [--model <model>] [--effort <low|medium|high|xhigh>] <plan step or addendum>"
allowed-tools: Bash(node:*), AskUserQuestion, Agent
Invoke the `multi:codex-execute` subagent via the `Agent` tool, forwarding the user's request as the prompt.
The subagent runs Codex in structured-execution mode — give it a concrete plan step, it implements it.
This is distinct from the official `openai-codex` plugin's `/codex:rescue`, which handles open-ended rescue. Use `/codex:execute` when you have a clear plan step; use `/codex:rescue` when Claude is stuck.
Raw user request: $ARGUMENTS
Execution:
- **Plan-by-reference (preferred when applicable):** if a plan file is in conversation context (Plan mode `Plan File Info` block, a path like `~/.claude/plans/*.md`, or a plan you authored this session), pass `--plan <path>` instead of paraphrasing. The subagent translates `--plan` to `--prompt-file` and Codex reads the file's bytes directly. See the `multi-plan-handoff` skill for full detection rules. Trigger phrases like "execute it via codex", "delegate to codex", "send this plan to codex" all qualify.
- For a small, clearly bounded step, invoke the subagent in the foreground (blocking).
- For a long-running or high-effort step (or `--until-done`), invoke the subagent with the `Agent` tool's `run_in_background: true`: the subagent runs Codex to completion in the foreground, so the harness wakes you with a `<task-notification>` when it finishes, fails, or the inactivity watchdog kills a hang — instead of stalling silently. Do NOT add the companion's `--background` flag for this (it detaches a worker the harness can't see); keep `--background` as an explicit fire-and-forget opt-in polled via `/multi:status`.
- Preserve `--model` and `--effort` flags for the forwarded command — the subagent reads them.
- If the user passes `--resume`, the subagent will continue the latest Codex execute thread for this repo.
- If the request includes no prompt text AND no plan file in context, ask what Codex should implement before proceeding.
Return Codex's output verbatim.
Read more
description: Delegate execution of a specific plan or plan step to Codex argument-hint: "[--plan <path>] [--background|--wait] [--resume|--fresh] [--model <model>] [--effort <low|medium|high|xhigh>] <plan step or addendum>" allowed-tools: Bash(node:*), AskUserQuestion, Agent
Invoke the `multi:codex-execute` subagent via the `Agent` tool, forwarding the user's request as the prompt.
The subagent runs Codex in structured-execution mode — give it a concrete plan step, it implements it.
This is distinct from the official `openai-codex` plugin's `/codex:rescue`, which handles open-ended rescue. Use `/codex:execute` when you have a clear plan step; use `/codex:rescue` when Claude is stuck.
Raw user request: $ARGUMENTS
Execution:
- **Plan-by-reference (preferred when applicable):** if a plan file is in conversation context (Plan mode `Plan File Info` block, a path like `~/.claude/plans/*.md`, or a plan you authored this session), pass `--plan <path>` instead of paraphrasing. The subagent translates `--plan` to `--prompt-file` and Codex reads the file's bytes directly. See the `multi-plan-handoff` skill for full detection rules. Trigger phrases like "execute it via codex", "delegate to codex", "send this plan to codex" all qualify.
- For a small, clearly bounded step, invoke the subagent in the foreground (blocking).
- For a long-running or high-effort step (or `--until-done`), invoke the subagent with the `Agent` tool's `run_in_background: true`: the subagent runs Codex to completion in the foreground, so the harness wakes you with a `<task-notification>` when it finishes, fails, or the inactivity watchdog kills a hang — instead of stalling silently. Do NOT add the companion's `--background` flag for this (it detaches a worker the harness can't see); keep `--background` as an explicit fire-and-forget opt-in polled via `/multi:status`.
- Preserve `--model` and `--effort` flags for the forwarded command — the subagent reads them.
- If the user passes `--resume`, the subagent will continue the latest Codex execute thread for this repo.
- If the request includes no prompt text AND no plan file in context, ask what Codex should implement before proceeding.
Return Codex's output verbatim.
If you have access to multiple AI coding CLIs (Codex, Cursor, Antigravity, and OpenCode), this plugin lets Claude Code delegate to whichever one is best for the task — without you having to switch tools or run them yourself.
Repo: greenpolo/cc-multi-cli-plugin
Other commands on cc-multi-cli-plugin.
- /explore
Fast codebase exploration with Antigravity's agy CLI (Gemini 3.5 Flash, read-only). EXPERIMENTAL.
Open command - /research
Deep external research with Antigravity's agy CLI (Gemini 3.5 Flash — web search + synthesis, read-only). EXPERIMENTAL.
Open command - /adversarial-review
Adversarial design/code review with Codex — challenges the approach, not just the diff (read-only)
Open command - /rescue
Hand a stuck or open-ended problem to Codex for an independent investigation or rescue pass
Open command - /review
Run a Codex code review of your working tree or a branch (read-only)
Open command - /delegate
Delegate an implementation task or plan step to Cursor (agentic, writes code; default Auto model)
Open command