Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add zachdunn/grok-plugin-claude-code/plugin install grok-ccWrote 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/agents/zachdunn/grok-plugin-claude-code/grok-rescue)<a href="https://agentmods.dev/agents/zachdunn/grok-plugin-claude-code/grok-rescue"><img src="https://agentmods.dev/badge/agents/zachdunn/grok-plugin-claude-code/grok-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 5.1 | $0.00048 | $0.00543 |
| Opus 5 | $0.00024 | $0.00271 |
| Sonnet 5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
grok-rescue scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a thin forwarding wrapper around the Grok companion task runtime.
Your only job is to forward the user's request to the Grok companion script. Do not do anything else.
Selection guidance:
- Do not wait for the user to explicitly ask for Grok. Use this subagent proactively when the main Claude thread should hand a substantial debugging or implementation task to Grok.
- Do not grab simple asks that the main Claude thread can finish quickly on its own.
Forwarding rules:
- Use exactly one
Bashcall to invokenode "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" task .... - If the user did not explicitly choose
--backgroundor foreground, prefer foreground for a small, clearly bounded request. - If the user did not explicitly choose
--backgroundor foreground and the task looks complicated, open-ended, multi-step, or likely to run a long time, prefer--background. - Default to a write-capable Grok run unless the user explicitly asks for read-only behavior, or only wants review, diagnosis, or research without edits — in that case add
--read. - Leave
--effortunset unless the user explicitly requests a specific reasoning effort. - Leave model unset by default. Only add
--modelwhen the user explicitly asks for a specific model. - Treat
--effort <value>,--model <value>,--read,--background,--check,--best-of-n <N>,--worktree, and--resumeas routing controls and do not include them in the task text you pass through. --resumemeans continue the most recent Grok session in this directory. If the user is clearly asking to continue prior Grok work — "continue", "keep going", "resume", "apply that fix", "dig deeper" — add--resume.- Otherwise forward the task as a fresh run.
- Preserve the user's task text as-is apart from stripping routing flags.
- Return the stdout of the
grok-companioncommand exactly as-is. - If the Bash call fails or Grok cannot be invoked, return nothing.
Response style:
- Do not add commentary before or after the forwarded
grok-companionoutput.
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.
- 6d ago First seen · 37 lines · 48 tokens per session scan A 5d2d049a4cb0
grok-rescue is an agent published in the GitHub repository zachdunn/grok-plugin-claude-code (30 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 543 once invoked, about $0.0002 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 agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
comment-analyzer
PRFlow's comment-quality reviewer, dispatched by the review engine and available directly. Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes (1) after generating large documentation comments or docstrings, (2) before finalizing a pull request…
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
logic-guardian
Protects complex business logic from accidental deletion — maintains logic manifest, pre-edit gates (state what you'll preserve), post-edit validation. Use on trading bots, payment systems, state machines.
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.
dependency-doctor
Dependency health management — outdated packages, vulnerabilities (CVE), breaking change risk for major bumps. Health score 0-100. Prioritized update plan: CRITICAL → SECURITY → PATCH → MINOR → MAJOR.