A setup command that checks whether the local Grok Build command-line tool is installed and signed in, and can guide installation or login.

It is for checking readiness, installing Grok when it is missing, and starting the sign-in process when authentication is needed.

It helps identify why the local tool is unavailable before other Grok commands are used.

setup — Command by dashpot4

Install

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.

agentmods

npx agentmods add commands/dashpot4/grok-plugin-for-claude/setup

Clone the repo

git clone --depth 1 https://github.com/dashpot4/grok-plugin-for-claude

Or install grok, the plugin that ships this one along with the rest of its 2 skills, 17 commands, 1 agent, 1 hook.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 578 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00018	$0.00578
Opus 5	$0.00009	$0.00289
Sonnet 5	$0.00004	$0.00116
Haiku 4.5	$0.00002	$0.00058

Measured 2d ago against content hash 2e84fc1cafec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

setup scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://x.ai/cli/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(node:*), Bash(powershell:*), Bash(curl:*), AskUserQuestion

plugins/grok/commands/setup.md · 67 lines

What it actually says

Run:

node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" setup --json $ARGUMENTS

If the result says Grok is unavailable:

Use AskUserQuestion exactly once to ask whether Claude should install Grok now.
Put the install option first and suffix it with (Recommended).
Use these two options:
- Install Grok (Recommended)
- Skip for now
If the user chooses install on Windows, run:

powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://x.ai/cli/install.ps1 | iex"

If the user chooses install on macOS/Linux, run:

curl -fsSL https://x.ai/cli/install.sh | bash

Then rerun:

node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" setup --json $ARGUMENTS

If Grok is already installed:

Do not ask about installation.

If Grok is installed but not authenticated:

Use AskUserQuestion exactly once to ask whether Claude should run Grok login now.
Use these two options:
- Run Grok login (Recommended)
- Skip for now
If the user chooses login on Windows, run:

powershell -NoProfile -Command "& \"$env:USERPROFILE\.grok\bin\grok.exe\" login"

If the user chooses login on macOS/Linux, run:

"$HOME/.grok/bin/grok" login

Then rerun setup:

node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" setup --json $ARGUMENTS

Output rules:

Present the final setup output to the user.
When setup is ready, the output includes workspace settings (default model, web search default, reasoning effort default). Present those lines to the user. For advanced features involving files (images, videos, uploads, vision), remind the user that Grok will use workspace-relative paths and inherit shell permissions—exact paths in the request help Claude handle any permission prompts gracefully.
If installation or login was skipped, present the original setup output.
If !grok login fails with command not found, explain that Claude Code may have started before PATH was updated. Recommend the PowerShell login command above or restarting Claude Code after adding %USERPROFILE%\.grok\bin to PATH.

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.

2d ago First seen · 67 lines · 18 tokens per session scan C 2e84fc1cafec

Subscribe to this mod's changes

setup is a command published in the GitHub repository dashpot4/grok-plugin-for-claude (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 578 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

claude forclaude grok grokplugin plugin

setup

Getting it into your agent

What it costs to keep this loaded

Grade C, and why

Downloads and executes remote codehighSupply chain

Makes network callslowCapability

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

critique

check

review

adversarial-review

rescue

setup