agentmods.dev

research

research is a command for Claude Code from LovelaceLoom/grok-plugin-cc. It costs 20 tokens per session (429 once invoked), scanned A, original, Apache-2.0.

A command for sending a research question to Grok with web search, page fetching, and self-checking enabled by default.

In plain words
What is it for?
Use it for deep research, including questions that require searching the web or reading a specific URL.
Why use it?
It helps investigate questions using current online information and adds a verification pass to the answer. These options can be turned off when needed.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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

not rated 5repo 2mo ago A scan 20 tokens original Apache-2.0

Good fit Use it for deep research, including questions that require searching the web or reading a specific URL.

Compare 6 commands from other repositories ↓
View source ↗ LovelaceLoom/grok-plugin-cc
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 research

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/lovelaceloom/grok-plugin-cc/research"><img src="https://agentmods.dev/badge/commands/lovelaceloom/grok-plugin-cc/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 429 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 $0.00020 $0.00429
Opus 5.5 $0.00008 $0.00172
Sonnet 5.5 $0.00004 $0.00086
Haiku 4.5 $0.00002 $0.00043

Measured 1mo ago against content hash 56ed0fc3d141, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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/commands/research.md · 30 lines

What it actually says

Forward the user's research question to Grok in deep-research mode and return the answer verbatim.

This command exists to exploit Grok's distinctive strengths:

  • Live web search is on by default (pass --no-web-search to turn it off).
  • web_fetch is on by default (v1.2.0) — Grok can fetch a specific URL, not just search (pass --no-web-fetch to turn it off).
  • --effort max is requested by default but only applies on models that support reasoning effort; the current default grok-build does not, so it is stripped with a warning. (No action needed — web search + --check do the heavy lifting.)
  • --check is on by default — Grok appends a self-verification loop to its own answer (pass --no-check to turn it off).
  • --stream (v1.2.0) streams the answer live as Grok produces it (uses --output-format streaming-json) — useful for long runs where you'd otherwise wait minutes for the buffered result.

Raw user input: $ARGUMENTS

Run:

node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" research "$ARGUMENTS"

Output rules:

  • Return the companion's stdout verbatim. Do not paraphrase or summarize.
  • If stderr contains a [hint: ...] line about auth, also surface that hint and suggest /grok:setup.
  • If $ARGUMENTS is empty, ask the user what they want Grok to research instead of running the command.
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. 1mo ago First seen · 30 lines · 20 tokens per session scan A 56ed0fc3d141

Subscribe to this mod's changes

research is a command published in the GitHub repository LovelaceLoom/grok-plugin-cc (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 429 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude CodeResearchai-assistantai-toolsclaude-code-plugindeveloper-tools
Related

Other commands, from other repositories

ia-verify

Run pre-PR verification chain: build, types, lint, tests, security scan, diff review.

iliaal/whetstone · 24 tokens

announce

Draft X/Twitter announcement post (or thread) for the latest plugin release.

iliaal/whetstone · 17 tokens

orchestrate

Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.

egorfedorov/claude-context-optimizer · 0 tokens

release

Generate changelog, bump version, and create git tag.

Joncik91/ucai · 11 tokens

render

Inspect an archived transcript (gzipped) — show counts, tool calls, errors. Useful after a PreCompact or SessionEnd, before deciding to write a retroactive /continuum:checkpoint.

DevZonayed/Mochi · 39 tokens

playbook

Manage Mochi playbooks (list, show, run, delete). Plays through the browser MCP tools.

DevZonayed/Mochi · 21 tokens