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.
npx agentmods add commands/zachdunn/grok-plugin-claude-code/rescuegit clone --depth 1 https://github.com/zachdunn/grok-plugin-claude-codeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/zachdunn/grok-plugin-claude-code/rescue)<a href="https://agentmods.dev/commands/zachdunn/grok-plugin-claude-code/rescue"><img src="https://agentmods.dev/badge/commands/zachdunn/grok-plugin-claude-code/rescue.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00018 | $0.00317 |
| Opus 5 | $0.00009 | $0.00159 |
| Sonnet 5 | $0.00004 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00032 |
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 3d 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.
What it actually says
Forward the user's request to Grok via the companion runtime. Treat this as a thin hand-off — do not solve the task yourself.
- Take everything in
$ARGUMENTSas the task description, except recognized routing flags (--read,--background,--effort <level>,--model <id>,--cwd <path>,--best-of-n <N>,--check,--worktree,--resume), which pass straight through to the companion. - If the user gave no routing flags, choose sensible defaults:
- Write-capable by default. Add
--readonly if the user clearly wants review/diagnosis/research with no edits. - Foreground for a small, bounded task;
--backgroundif it looks long-running or open-ended.
- Write-capable by default. Add
- Run exactly one command:
node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" task <flags> "<task description>"
- Return the companion's stdout as-is. Do not add your own analysis before or after it.
If the companion reports Grok is not installed or not signed in, tell the user to run /grok-cc:setup.
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.
- 3d ago First seen · 22 lines · 18 tokens per session scan A 93fb7c49e532
rescue is a command published in the GitHub repository zachdunn/grok-plugin-claude-code (29 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 317 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
critique
Run a Grok Build critique that challenges the implementation approach and design choices.
check
Check whether the local Grok Build CLI is ready for the Claude Code bridge.
implement
Claude plans, Grok implements - write a concrete implementation plan, hand it to Grok as the worker, wait, then verify the result.
review
Run a Grok code review against local git state.
consult
Ask Grok a free-form question, optionally with file context (read-only).
review
Run a Grok code review against local git state (read-only).