project-overview

An overview of Grok CLI, an open-source terminal program that provides AI coding assistance through the Grok service.

In plain words
What is it for?
Use it to locate the agent, API client, search tools, terminal interface, settings, and Git repository discovery code.
Why use it?
It explains the project's main parts, technologies, and command-line architecture before someone changes the code.

Cursor rule for Cursor

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 rules/superagent-ai/grok-cli/project-overview
Clone the repo
git clone --depth 1 https://github.com/superagent-ai/grok-cli

Made for: Cursor.

Per session 753 This file is loaded in full into every session.
When invoked 753 The same file — it is already loaded in full.
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 $0.00753 $0.00753
Opus 5 $0.00377 $0.00377
Sonnet 5 $0.00151 $0.00151
Haiku 4.5 $0.00075 $0.00075

Measured 2d ago against content hash 523d3251e067, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-overview 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.

.cursor/rules/project-overview.mdc · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grok CLI — Project Overview

Grok CLI (@vibe-kit/grok-cli) is an open-source AI coding agent powered by Grok that brings AI assistance directly into the terminal.

Tech Stack

  • Language: TypeScript (ES2022, ESNext modules)
  • Runtime: Bun (primary)
  • UI Framework: React with OpenTUI for terminal rendering
  • Build: tsc (TypeScript compiler)
  • Package Manager: Bun
  • API Client: OpenAI SDK (for OpenAI-compatible xAI API)
  • Tools: Bash-only (all file operations via shell commands)
  • Search: X Search API + Web Search via xAI Responses API

Architecture

src/
├── index.ts          # CLI entry point (Commander.js + OpenTUI)
├── agent/
│   └── agent.ts      # Agent — orchestrates client, bash tool, search
├── grok/
│   ├── client.ts     # Grok API client (Chat Completions + Responses API)
│   ├── models.ts     # Model definitions and metadata
│   └── tools.ts      # Tool schemas (bash, search_web, search_x)
├── tools/
│   └── bash.ts       # Bash command execution
├── ui/
│   └── app.tsx       # OpenTUI React terminal UI
├── utils/
│   ├── settings.ts   # User and project settings
│   ├── git-root.ts   # Resolve git repository root for AGENTS.md discovery
│   └── instructions.ts # AGENTS.md (ecosystem) custom instructions
└── types/
    └── index.ts      # Shared TypeScript types

Key Patterns

  • Agent loop: Agent.processMessage() is an async generator that yields StreamChunk objects — the LLM responds, tools execute, results feed back until no more tool calls remain.
  • Bash-only tools: The agent uses bash for everything (file editing, searching, git, builds, etc.).
  • X Search & Web Search: Integrated via the xAI Responses API for real-time information.
  • Settings hierarchy: Environment variables → User-level (~/.grok/user-settings.json) → Project-level (.grok/settings.json).
  • Custom instructions: ~/.grok/AGENTS.md, then AGENTS.override.md / AGENTS.md per directory from git root through the workspace cwd (Codex-style merge).
  • ESM only: The project uses "type": "module" — all imports use .js extensions for compiled output.

Read the full file on GitHub · 66 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 · 66 lines · 753 tokens per session scan A 523d3251e067

Subscribe to this mod's changes

project-overview is a cursor rule published in the GitHub repository superagent-ai/grok-cli (3,441 stars, last pushed 1mo ago), licensed MIT. It adds 753 tokens to every session, about $0.0038 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 2026-08-30.