unicli-operate

unicli-operate is a skill for Claude Code, Codex from olo-dot-io/Uni-CLI. It costs 31 tokens per session (972 once invoked), scanned A, original, Apache-2.0.

A compatibility guide for controlling a web browser from the command line. It explains how to open pages, inspect their visible elements, click and type into them, and extract information.

In plain words
What is it for?
Use it to navigate websites, inspect page structure, fill forms, take screenshots, switch tabs or frames, and collect structured page data.
Why use it?
It provides a repeatable way to interact with websites and confirm that each action worked. The older operate commands remain available, while newer browser commands provide the preferred interface.

Skill for Claude CodeCodex

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 skills/olo-dot-io/uni-cli/unicli-operate
Any agent
npx skills add olo-dot-io/Uni-CLI --skill unicli-operate
Clone the repo
git clone --depth 1 https://github.com/olo-dot-io/Uni-CLI

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for unicli-operate

README.md
[![agentmods](https://agentmods.dev/badge/skills/olo-dot-io/uni-cli/unicli-operate.svg)](https://agentmods.dev/skills/olo-dot-io/uni-cli/unicli-operate)
Your own site
<a href="https://agentmods.dev/skills/olo-dot-io/uni-cli/unicli-operate"><img src="https://agentmods.dev/badge/skills/olo-dot-io/uni-cli/unicli-operate.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 972 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00031 $0.00972
Opus 5 $0.00015 $0.00486
Sonnet 5 $0.00006 $0.00194
Haiku 4.5 $0.00003 $0.00097

Measured 5d ago against content hash c7ebd2e43f7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unicli-operate 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 5d 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.

skills/unicli-operate/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to Use

Prefer unicli browser for new work:

unicli browser open <url>
unicli browser state
unicli browser click <ref>
unicli browser type <ref> <text>
unicli browser find --css <selector>
unicli browser extract
unicli browser tabs
unicli browser frames

unicli operate ... still works, but it is now the compatibility path over the same implementation.

Core Workflow

  1. open -> navigate to URL
  2. state -> inspect DOM, get [ref] numbers for interactive elements
  3. interact -> click, type, select, keys using ref numbers
  4. verify -> state again or get value <ref> to confirm
  5. extract -> eval for structured data

Always state before interacting. Never guess ref numbers.

All Operate Subcommands

# Navigation
unicli operate open <url>             # Navigate to URL
unicli operate back                   # Go back in history
unicli operate scroll [direction]     # down, up, bottom, top
unicli operate close                  # Close automation window

# Inspection
unicli operate state                  # DOM tree with [ref] indices
unicli operate screenshot [path]      # Save visual capture

# Get data
unicli operate get title|url          # Page title or URL
unicli operate get text <ref>         # Element text by ref
unicli operate get value <ref>        # Input value (verify after type)
unicli operate get html [selector]    # Page or scoped HTML
unicli operate get attributes <ref>   # Element attributes

# Interaction
unicli operate click <ref>            # Click element
unicli operate type <ref> <text>      # Type into element
unicli operate select <ref> <option>  # Select dropdown
unicli operate keys <key>             # Press key (Enter, Escape, Control+a)
unicli operate upload <ref> <path>    # Upload file
unicli operate hover <ref>            # Hover over element

# Wait
unicli operate wait time <ms>         # Fixed delay
unicli operate wait selector <sel>    # Until element appears
unicli operate wait text <str>        # Until text appears

# Advanced
unicli operate eval <js>              # Execute JS in page
unicli operate network [pattern]      # Captured network requests
unicli operate observe <query>        # Natural language observation

Read the full file on GitHub · 114 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. 5d ago First seen · 114 lines · 31 tokens per session scan A c7ebd2e43f7f

Subscribe to this mod's changes

unicli-operate is a skill published in the GitHub repository olo-dot-io/Uni-CLI (270 stars, last pushed 2d ago), licensed Apache-2.0. It adds 31 tokens to every session and 972 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

x402

Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…

browser-use/browser-use · 175 tokens

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

browser-use/browser-use · 26 tokens

remote-browser

Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.

browser-use/browser-use · 22 tokens

opencli-browser

Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing…

jackwener/OpenCLI · 80 tokens

opencli-adapter-author

Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level…

jackwener/OpenCLI · 88 tokens

cloud

Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…

browser-use/browser-use · 177 tokens