No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by only-cli · Agent Tool · ★ 530
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is oc safe to install? View the security audit →
only-cli Turns websites into a command line interface for AI agents. fetches a page and hands back a compact, numbered view instead of raw HTML or a screenshot, so agents like Claude Code, Codex, and Antigravity can browse without burning tokens. It also gets past blocks that stop naive fetchers on some sites, by talking to the page the way a real browser would. A typical page is tens of thousands of tokens of markup; the view above fits in a few hundred. No per-site adapters required, no browser extension, no daemon. If you are an LLM reading this repository, llms.txt is the short version. Install Requires Node 20+. Requests impersonate Chrome via impers; falls back to native fetch if impers is unavailable. #
| Stars | 530 |
| Forks | 32 |
| Language | JavaScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 69.209758844313/100 |
| Last Updated | 2026-10-05 |
| Created | 2026-08-18 |
| Platforms | browser, claude-code, cli, node |
| Est. Tokens | ~16k |
Looking for a oc alternative? If you're comparing oc with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute
Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw C
A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.
Review AI coding agents' plans, diffs and running apps in the browser. Local-first, works with any agent.
Open-source AI coding agent and agent runtime: one binary, any model, MCP-native. Runs in terminal, CI, or as
Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microso
Explore other popular agent tool tools:
oc is Turn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.. It is categorized as a Agent Tool with 530 GitHub stars.
oc is primarily written in JavaScript. It covers topics such as ai-agents, browser-automation, claude-code.
You can find installation instructions and usage details in the oc GitHub repository at github.com/only-cli/oc. The project has 530 stars and 32 forks, indicating an active community.
oc is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to oc on Agent Skills Hub include ggsrun, browser-debugger-cli, brightdata-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: