grok-cli is an open-source terminal coding agent that uses the Grok API to work on software projects. Developers use it for interactive or headless coding tasks, with features including web and X search, sub-agents, a terminal interface, and remote control through Telegram.
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.
git clone --depth 1 https://github.com/superagent-ai/grok-cliWrote 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.
[](https://agentmods.dev/rules/superagent-ai/grok-cli/development-workflow)<a href="https://agentmods.dev/rules/superagent-ai/grok-cli/development-workflow"><img src="https://agentmods.dev/badge/rules/superagent-ai/grok-cli/development-workflow/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.
<a href="https://agentmods.dev/rules/superagent-ai/grok-cli/development-workflow"><img src="https://agentmods.dev/badge/rules/superagent-ai/grok-cli/development-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00486 | $0.00486 |
| Opus 5.5 | $0.00194 | $0.00194 |
| Sonnet 5.5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
development-workflow 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.
What it actually says
Development Workflow
Prerequisites
- Bun 1.0+ (required)
Common Commands
# Install dependencies
bun install
# Development (runs from source with Bun)
bun run dev
# Build (compile TypeScript to dist/)
bun run build
# Type checking (no emit)
bun run typecheck
# Linting
bun run lint
# Format (check / write)
bun run format
bun run format:fix
# Run the built CLI
bun run start
Environment Variables
| Variable | Required | Description |
|---|---|---|
GROK_API_KEY |
Yes | API key for xAI Grok |
GROK_BASE_URL |
No | Custom API endpoint (default: https://api.x.ai/v1) |
GROK_MODEL |
No | Model override (default: grok-4.3) |
GROK_MAX_TOKENS |
No | Max tokens per response (default: 16384) |
Copy .env.example to .env and fill in your values.
Git hooks
After bun install, Husky installs a pre-commit hook that runs lint-staged: Biome format + lint (check --write) on staged *.{ts,tsx,js,mjs,cjs,json} files. Fixes are written to disk and re-staged automatically when possible.
Before Submitting Changes
- Run
bun run typecheck— CI enforces this on every PR. - Run
bun run lint— fix any Biome issues (or let pre-commit apply safe fixes). - Ensure no secrets or
.envfiles are committed. - Follow the PR template in
.github/pull_request_template.md.
Project Structure Conventions
- Source code lives in
src/, compiled output indist/(gitignored). - The CLI entry point is
src/index.tswhich uses Commander.js for argument parsing. - UI is built with OpenTUI React (
@opentui/react). - Only tool is bash — all file operations happen through shell commands.
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.
- 1mo ago First seen · 67 lines · 486 tokens per session scan A 67d4d6a7e699
development-workflow is a cursor rule published in the GitHub repository superagent-ai/grok-cli (3,502 stars, last pushed 3mo ago), licensed MIT. It adds 486 tokens to every session, about $0.0019 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 2026-08-30.
Other cursor rules, from other repositories
use-bun-instead-of-node-vite-npm-pnpm
../../CLAUDE.md.
po
AIOX agent @po - Product Owner.
hatch3r-dynamic-stack-verification
Runtime-evidence gates for stacks with no static type layer (plain-JS Vue, dynamic persistence) — smoke-mount changed components, dormant-collection-read ratchet, runtime smoke evidence on module-boundary changes; a green lint+build+mock-suite proves a layer, not the system.
hatch3r-spec-currency
Spec-currency mandate — any diff changing user-observable behavior covered by a docs/specs/ file updates that spec in the same delivery; staleness definition, review-gate drift finding with a named owner, and a release-readiness sweep.
bundling
The project uses a custom type bundling system to provide full TypeScript IntelliSense support in the Monaco editor for @bubblelab/bubble-core and its dependencies. This is necessary because Monaco cannot directly resolve workspace packages or external dependencies.
hatch3r-api-design
REST, GraphQL, and gRPC contract patterns covering versioning, auth, CORS, pagination, webhooks, rate limiting, and security headers.