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.
Borrowing it
Nothing to install: this file belongs to superagent-ai/grok-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/superagent-ai/grok-cli/main/AGENTS.mdgit 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/instructions/superagent-ai/grok-cli/agents-md)<a href="https://agentmods.dev/instructions/superagent-ai/grok-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/superagent-ai/grok-cli/agents-md/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/instructions/superagent-ai/grok-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/superagent-ai/grok-cli/agents-md.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 | $0.00467 | $0.00467 |
| Opus 5.5 | $0.00187 | $0.00187 |
| Sonnet 5.5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
grok-cli AGENTS.md 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 2mo 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
AGENTS.md
Cursor Cloud specific instructions
Overview
Grok CLI (@vibe-kit/grok-cli) is a single-package TypeScript CLI tool — no databases, Docker, or background services. See README.md for full documentation and usage.
Quick reference
| Action | Command |
|---|---|
| Install deps | bun install (installs Husky; pre-commit runs Biome on staged files) |
| Typecheck | bun run typecheck |
| Build | bun run build |
| Run built CLI | node dist/index.js |
| Headless mode | node dist/index.js --prompt "..." --max-tool-rounds N |
| CLI help | node dist/index.js --help |
Known issues
- ESLint config is broken: The repo has
.eslintrc.js(legacy format) but uses ESLint 9 (^9.31.0) +@typescript-eslintv8, which require flat config (eslint.config.js). Additionally,.eslintrc.jsusesmodule.exports(CJS) butpackage.jsonhas"type": "module"(ESM). Runningbun run lintwill fail. Usebun run typecheckas the primary code quality check (this is also what CI enforces). - Dev mode (
bun run dev/bun run dev:node) fails at runtime:src/utils/model-config.tsimports TypeScript interfaces (UserSettings,ProjectSettings) as value imports fromsettings-manager.ts. These type-only exports are erased at runtime by Bun and tsx, causingSyntaxError: export '...' not found. The fix is to useimport typesyntax, but this is a pre-existing repo issue. Workaround: build first (bun run build), then run the compiled version (node dist/index.js).
Environment
- Bun must be installed (not pre-installed on Cloud VMs). The update script handles this.
GROK_API_KEYenvironment variable is required for API calls. Set it as a secret.
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.
- 2mo ago First seen · 30 lines · 467 tokens per session scan A 7b37803590da
grok-cli AGENTS.md is an instructions file published in the GitHub repository superagent-ai/grok-cli (3,505 stars, last pushed 4mo ago), licensed MIT. It adds 467 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.
grok-cli AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| grok-cli AGENTS.mdsuperagent-ai/grok-cli | Instructions file | 3.5k | 4mo ago | MIT | A | 467 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |