chat

A command-line chat tool that sends prompts to the Grok Responses API, a service for generating text answers. Web search is enabled by default for recent information, and X search can also be requested.

In plain words
What is it for?
Use it for chat, explanations, reasoning, question answering, summaries, and recent-fact lookups.
Why use it?
It lets people and scripts ask questions, summarize text, and get researched answers from a terminal.

Command

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/moore-developers/grok-cli/chat
Clone the repo
git clone --depth 1 https://github.com/Moore-developers/grok-cli
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 928 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00928
Opus 5 $0.00000 $0.00464
Sonnet 5 $0.00000 $0.00186
Haiku 4.5 $0.00000 $0.00093

Measured 2d ago against content hash a2fbadfb6931, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chat 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 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.

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.

docs/commands/chat.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

grok-cli chat

Purpose

Run text chat, summarization, reasoning, and Q&A through the Grok Responses API. General web_search is enabled by default, which makes the command useful for recent facts.

For human use, chat streams readable text by default without exposing raw SSE events or status messages such as Thinking.... For scripts, skills, and automation, prefer --json for a stable single response.

Common Usage

grok-cli chat "Summarize recent AI news"

Pure chat without search:

grok-cli chat "Explain OAuth PKCE" --no-web-search

Use both web search and X search:

grok-cli chat "What are the hottest AI discussions from the last 48 hours?" --with-x-search

Script or skill usage:

grok-cli chat --json --prompt "Summarize today's AI news"

Disable default streaming:

grok-cli chat "Tell a short story" --no-stream

Explicitly request formatted streaming:

grok-cli chat "Tell a short story" --stream

Output raw normalized stream events:

grok-cli chat "Tell a short story" --raw-stream

Parameters

  • PROMPT: positional user prompt.
  • --prompt <PROMPT>: explicit script-friendly prompt.
  • --json: use the standard JSON envelope. This disables streaming by default and returns one stable result.
  • --auth-file <PATH>: override the OAuth state file path.
  • --system <TEXT>: system instruction, mapped to Responses API instructions.
  • --model <MODEL>: override the model for this request only.
  • --no-web-search: disable default web_search.
  • --with-x-search: also attach x_search.
  • --allowed-domain <DOMAIN>: restrict web search domains. Repeatable, up to 10.
  • --excluded-domain <DOMAIN>: exclude web search domains. Repeatable, up to 10.
  • --enable-image-understanding: enable image understanding for search tools.
  • --allowed-x-handle <HANDLE>: restrict X search handles. Repeatable, up to 10.
  • --excluded-x-handle <HANDLE>: exclude X search handles. Repeatable, up to 10.
  • --from-date <YYYY-MM-DD>: X search start date.
  • --to-date <YYYY-MM-DD>: X search end date.
  • --enable-video-understanding: enable video understanding for X search.
  • --stream: explicitly use formatted streaming output.
  • --no-stream: disable default streaming and print one final result.
  • --raw-stream: output raw normalized stream events for debugging or programmatic consumption.
  • --timeout <SECONDS>: request timeout, default 3600.

Read the full file on GitHub · 106 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. 2d ago First seen · 106 lines · 0 tokens per session scan A a2fbadfb6931

Subscribe to this mod's changes

chat is a command published in the GitHub repository Moore-developers/grok-cli (52 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 928 tokens. 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.