A command that sends an investigation, explicit fix request, or follow-up task to a MiniMax rescue subagent. A subagent is a separate agent process used to work on a delegated task.

Use it to delegate a task, run it while continuing other work, wait for its result, resume eligible rescue work, or cancel a background job.

It provides a defined route for handing difficult or follow-up work to that rescue agent. It also supports foreground, background, cancellation, and resumable-job options.

rescue — Command by robbedoo

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/robbedoo/minimax-plugin-claude-code/rescue

Clone the repo

git clone --depth 1 https://github.com/robbedoo/minimax-plugin-claude-code

Or install minimax, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 1 agent, 3 hooks.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 786 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 88% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00020	$0.00786
Opus 5	$0.00010	$0.00393
Sonnet 5	$0.00004	$0.00157
Haiku 4.5	$0.00002	$0.00079

Measured 2d ago against content hash ad7666678e32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rescue scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

88% identical to rescue — 42 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/minimax/commands/rescue.md · 50 lines

What it actually says

Route this request to the minimax:minimax-rescue subagent. The final user-visible response must be MiniMax's output verbatim.

Raw user request: $ARGUMENTS

Execution mode:

If the request includes --background, run the minimax:minimax-rescue subagent in the background.
If the request includes --wait, run the minimax:minimax-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 --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.
If the request includes --resume, do not ask whether to continue. The user already chose.
If the request includes --fresh, do not ask whether to continue. The user already chose.
Otherwise, before starting MiniMax, check for a resumable rescue thread from this Claude session by running:

node "${CLAUDE_PLUGIN_ROOT}/scripts/minimax-companion.mjs" task-resume-candidate --json

If that helper reports available: true, use AskUserQuestion exactly once to ask whether to continue the current MiniMax thread or start a new one.
The two choices must be:
- Continue current MiniMax thread
- Start a new MiniMax thread
If the user is clearly giving a follow-up instruction such as "continue", "keep going", "resume", "apply the top fix", or "dig deeper", put Continue current MiniMax thread (Recommended) first.
Otherwise put Start a new MiniMax thread (Recommended) first.
If the user chooses continue, add --resume before routing to the subagent.
If the user chooses a new thread, add --fresh before routing to the subagent.
If the helper reports available: false, do not ask. Route normally.

Operating rules:

The subagent is a thin forwarder only. It should use one Bash call to invoke node "${CLAUDE_PLUGIN_ROOT}/scripts/minimax-companion.mjs" task ... and return that command's stdout as-is.
Return the MiniMax companion stdout verbatim to the user.
Do not paraphrase, summarize, rewrite, or add commentary before or after it.
Do not ask the subagent to inspect files, monitor progress, poll /minimax:status, fetch /minimax:result, call /minimax:cancel, summarize output, or do follow-up work of its own.
Leave --effort unset unless the user explicitly asks for a specific reasoning effort.
Leave the model unset unless the user explicitly asks for one.
Leave --resume and --fresh in the forwarded request. The subagent handles that routing when it builds the task command.
If the helper reports that MiniMax is not configured, stop and tell the user to run /minimax:setup.
If the user did not supply a request, ask what MiniMax should investigate or fix.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 50 lines · 20 tokens per session scan A ad7666678e32

Subscribe to this mod's changes

rescue is a command published in the GitHub repository robbedoo/minimax-plugin-claude-code (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 786 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to rescue, differing in 42 lines, and is treated as a copy.

ai-coding ai-plugin claude-code developer-tools function-calling

rescue

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

analyze-repo

go-review

review-branch

doctor

handoff

example-only