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 LovelaceLoom/grok-plugin-cc/plugin install grokWrote 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/skills/lovelaceloom/grok-plugin-cc/grok-rescue)<a href="https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-rescue"><img src="https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-rescue/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-rescue"><img src="https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-rescue.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00075 | $0.00815 |
| Opus 5 | $0.00037 | $0.00407 |
| Sonnet 5 | $0.00015 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00081 |
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grok — Rescue (Long-Form Delegated Task)
Use this skill to hand off a substantial, open-ended task to Grok. The companion runs Grok in its full agentic mode (file reads/writes optionally enabled, web search, multi-turn reasoning) and streams the result back.
In Claude Code this skill is invoked via the grok:grok-rescue subagent for isolation. In Codex CLI (and inline in Claude Code when no subagent is available), invoke the companion directly.
When to use
- The task is substantial: requires reading multiple files, planning across boundaries, or running for several minutes.
- You'd want a second implementation pass from a different model family.
- The work is research-shaped + code-shaped: e.g., "investigate this regression and propose a fix", "audit this module for security issues", "find a root cause for the failing test".
- The user explicitly says "ask grok to do this" / "delegate to grok" / "let grok handle this".
Do not use this skill for:
- One-off questions →
grok-ask. - Pure research (no code touch) →
grok-research. - Image generation →
grok-imagine. - Trivial tasks you can complete inline in under a minute.
How to invoke
Run exactly one bash command. Default to read-only:
node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" task "<the user's full task description, properly quoted>"
Write mode (the model edits files)
Only add --write if the user explicitly asked for code changes. Write mode requires GROK_PLUGIN_ALLOW_WRITE=1 in the environment as a safety gate:
node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" task --write "<task>"
If the env var is missing the helper exits with code 2 and a [hint:] message. Surface the refusal verbatim and let the user decide whether to enable write mode.
Common flags (forwarded to companion)
--model <name>— only if user explicitly named one.--effort <low|medium|high|xhigh|max>— only if user explicitly chose one.--session-id <id>— resume a specific session.--resume=<id>— resume by id (note: requires=, not space).--continue— continue the most-recent session for cwd.--timeout <duration>— default unbounded for rescue work.300s,5m,1h,0.
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.
- 10d ago First seen · 62 lines · 75 tokens per session scan A 2b713f75b16e
grok-rescue is a skill published in the GitHub repository LovelaceLoom/grok-plugin-cc (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 815 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ucai-patterns
Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.
architect
This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design".
backend
This skill should be used when the user asks to "design REST APIs", "optimize database queries", "implement authentication", "build microservices", "review backend code", "set up GraphQL", "handle database migrations", or "load test APIs".
frontend-design
Use when user asks to build a web component, page, or application, or when the task involves frontend design, HTML/CSS generation, or UI layout. Applies specific rules for typography, OKLCH color, layout, motion, interaction, and UX writing to produce distinctive, production-grade interfaces that avoid generic AI…
lineage
Use when user invokes /lineage with a column name (optionally qualified with table/schema). Also triggers on "trace this column", "where does X come from", "what reads from Y table". Traces column-level data lineage through SQL, Kafka, Spark, JDBC, and ORM codebases. Produces a structured lineage path with confidence…
dependabot-sweep
Use when the user wants to fix, address, clear, or resolve open Dependabot security/vulnerability alerts for a repository, end to end. Fetches open alerts via the gh CLI, fixes them per ecosystem (pnpm/npm overrides + lockfile regen, cargo update, pip/go/bundler), verifies with audit and frozen-lockfile installs, then…