From codex
Delegates investigation, fix requests, or follow-up work to the Codex rescue subagent. Supports background/foreground execution, model selection, effort levels, and thread resume/fresh start.
How this command is triggered — by the user, by Claude, or both
Slash command
/codex:rescue [--background|--wait] [--resume|--fresh] [--model <model|spark>] [--effort <none|minimal|low|medium|high|xhigh>] [what Codex should investigate, solve, or continue]This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
Route this request to the `codex:codex-rescue` subagent. The final user-visible response must be Codex's output verbatim. Raw user request: $ARGUMENTS Execution mode: - If the request includes `--background`, run the `codex:codex-rescue` subagent in the background. - If the request includes `--wait`, run the `codex:codex-rescue` subagent in the foreground. - If neither flag is present, default to foreground. - `--background` and `--wait` are execution flags for Claude Code. Do not forward them to `task`, and do not treat them as part of the natural-language task text. - `--model` and `--...
Route this request to the codex:codex-rescue subagent.
The final user-visible response must be Codex's output verbatim.
Raw user request: $ARGUMENTS
Execution mode:
--background, run the codex:codex-rescue subagent in the background.--wait, run the codex:codex-rescue subagent in the foreground.--background and --wait are execution flags for Claude Code. Do not forward them to task, and do not treat them as part of the natural-language task text.--model and --effort are runtime-selection flags. Preserve them for the forwarded task call, but do not treat them as part of the natural-language task text.--resume, do not ask whether to continue. The user already chose.--fresh, do not ask whether to continue. The user already chose.node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task-resume-candidate --json
available: true, use AskUserQuestion exactly once to ask whether to continue the current Codex thread or start a new one.Continue current Codex threadStart a new Codex threadContinue current Codex thread (Recommended) first.Start a new Codex thread (Recommended) first.--resume before routing to the subagent.--fresh before routing to the subagent.available: false, do not ask. Route normally.Operating rules:
Bash call to invoke node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task ... and return that command's stdout as-is./codex:status, fetch /codex:result, call /codex:cancel, summarize output, or do follow-up work of its own.--effort unset unless the user explicitly asks for a specific reasoning effort.spark, map it to gpt-5.3-codex-spark.--resume and --fresh in the forwarded request. The subagent handles that routing when it builds the task command./codex:setup.npx claudepluginhub kanjseok/openai-codex-plugin-cc --plugin codex/rescueDelegates investigation, fix requests, or follow-up work to the Codex rescue subagent. Supports background/foreground execution and automatic resume of previous threads.
/rescueDelegate investigation, an explicit fix request, or follow-up rescue work to the Copilot rescue subagent
/rescueDelegate investigation, an explicit fix request, or follow-up rescue work to the Qwen rescue subagent
/rescueDelegates investigation, fix requests, or follow-up tasks to the Gemini rescue subagent with configurable model, effort, and execution mode.
/rescueRuns a write-capable Kimi rescue session against the current repository with optional background execution, resume, and model selection flags.
/rescueDelegates a task to Codex for background execution when you need help or are stuck. Passes your prompt and context via $ARGUMENTS to the configured AI provider.