grok-research

grok-research is a skill for Claude Code from LovelaceLoom/grok-plugin-cc. It costs 63 tokens per session (707 once invoked), scanned A, original, Apache-2.0.

A deep-research skill that uses xAI Grok to investigate topics with live web search, fetch specific web pages, and check its own findings. Grok is an AI model made by xAI.

In plain words
What is it for?
Use it for non-trivial research, recent events, source-grounded claims, and investigations of a specific URL or topic.
Why use it?
It helps when an answer needs current information, thorough investigation, or claims checked against sources rather than relying only on existing knowledge.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the grok plugin — 8 skills, 21 commands, 2 agents, 3 hooks shipped together

Good fit Use it for non-trivial research, recent events, source-grounded claims, and investigations of a specific URL or topic.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add LovelaceLoom/grok-plugin-cc
Claude Code
/plugin install grok

Made for: Claude Code.

Or install grok, the plugin that ships this one along with the rest of its 8 skills, 21 commands, 2 agents, 3 hooks.

Wrote 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.

agentmods badge for grok-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-research/github.svg)](https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-research)
Your own site
<a href="https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-research"><img src="https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-research/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.

agentmods 80×15 button for grok-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-research"><img src="https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 707 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.00707
Opus 5 $0.00032 $0.00353
Sonnet 5 $0.00013 $0.00141
Haiku 4.5 $0.00006 $0.00071

Measured 10d ago against content hash 62c470d60c96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

grok-research 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.

plugins/grok/skills/grok-research/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grok — Deep Research

Use this skill for non-trivial investigation tasks that benefit from Grok's full reasoning + verification stack. The companion sets sane research defaults:

  • --effort max — requested by default, but only applied on models that support reasoning effort. The current default model (grok-build) declares none, so the companion strips --effort with a stderr warning. The real depth here comes from web search + --check, not --effort.
  • Web search enabled by default — Grok queries the live web during reasoning.
  • Web fetch (web_fetch) enabled by default (v1.2.0) — Grok can fetch a specific URL the user pasted, not just search. Opt out with --no-web-fetch.
  • --check enabled by default — Grok appends a self-verification loop and revises its own answer.

Override any of these with the flags below if the user explicitly asks for a cheaper / faster / web-less run.

When to use

  • The user asks "research…", "investigate…", "find out…", "what's the current state of…", "is X still true as of ".
  • Claims need verification against live sources.
  • The task is research-shaped, not code-shaped (for coding tasks → grok-rescue).

Do not use this skill for:

  • One-off questions or quick lookups → grok-ask.
  • Long-form coding / fixing / refactoring → grok-rescue.
  • Image generation → grok-imagine.

How to invoke

Run exactly one bash command:

node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" research "<the user's research question, properly quoted>"

CLAUDE_PLUGIN_ROOT is set by both Claude Code and Codex CLI.

Common flags

  • --model <name> — override default Grok model.
  • --effort <low|medium|high|xhigh|max> — override the default max. Use high or lower for cheaper runs.
  • --no-check — disable the self-verification loop (faster, less rigorous).
  • --no-web-search — disable live web search (rare; usually leave on).
  • --no-web-fetch — disable the default-on web_fetch tool (rare).
  • --stream — stream the answer live as Grok produces it (good for long runs).
  • --timeout <duration>0 for unbounded (default). 5m, 30m, etc.

Read the full file on GitHub · 53 lines

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.

  1. 10d ago First seen · 53 lines · 63 tokens per session scan A 62c470d60c96

Subscribe to this mod's changes

grok-research is a skill published in the GitHub repository LovelaceLoom/grok-plugin-cc (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 707 once invoked, about $0.0003 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.

Related

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.

Joncik91/ucai · 42 tokens

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".

Joncik91/ucai · 56 tokens

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".

Joncik91/ucai · 54 tokens

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…

harnessprotocol/harness-kit · 68 tokens

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…

harnessprotocol/harness-kit · 94 tokens

explain

Use when user invokes /explain with a file path, directory path, function/class name, or natural language concept. Also triggers on "explain this", "how does X work", "walk me through". Produces a structured, layered explanation of what the code does, how it connects, and where to start if you need to change it. Do…

harnessprotocol/harness-kit · 95 tokens