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/tools-and-agent)<a href="https://agentmods.dev/rules/superagent-ai/grok-cli/tools-and-agent"><img src="https://agentmods.dev/badge/rules/superagent-ai/grok-cli/tools-and-agent/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/tools-and-agent"><img src="https://agentmods.dev/badge/rules/superagent-ai/grok-cli/tools-and-agent.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 | $0.00000 | $0.00475 |
| Opus 5.5 | $0.00000 | $0.00190 |
| Sonnet 5.5 | $0.00000 | $0.00095 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
tools-and-agent 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
Agent & Tools System
Agent
Agent (in src/agent/agent.ts) is the core orchestrator. It manages:
- The Grok API client (
GrokClient) - Bash tool for all shell operations
- Web search and X search via the Responses API
- Chat history and message accumulation
- Abort/cancellation support
Agent Loop
The agent uses an iterative tool-call pattern via processMessage (async generator):
- Send messages to the LLM via Chat Completions API (streaming).
- If the response contains
tool_calls, execute each tool. - Append tool results to the message history.
- Repeat until no tool calls remain or
maxToolRoundsis reached. - Yield
StreamChunkobjects for real-time UI updates.
Tool Interface
All tools return a ToolResult:
interface ToolResult {
success: boolean;
output?: string;
error?: string;
}
Tools should never throw — wrap errors in { success: false, error: "..." }.
Built-in Tools
| Tool | File | Purpose |
|---|---|---|
BashTool |
src/tools/bash.ts |
Execute any shell command |
search_web |
via GrokClient.searchWeb() |
Web search using Responses API |
search_x |
via GrokClient.searchX() |
X/Twitter search using Responses API |
Grok Client
GrokClient (in src/grok/client.ts) handles two API endpoints:
- Chat Completions (
/v1/chat/completions): Main agent loop with streaming and tool calling - Responses API (
/v1/responses): X Search and Web Search with server-side tools
Adding a New Tool
- Add the tool schema to
src/grok/tools.ts(in theTOOLSarray). - Add the execution case in
Agent.executeTool(). - Update the system prompt in
Agentto document the tool.
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 · 63 lines · 0 tokens per session scan A 347d4f1d026e
tools-and-agent is a cursor rule published in the GitHub repository superagent-ai/grok-cli (3,502 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 475 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.
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.