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.
npx agentmods add skills/olo-dot-io/uni-cli/unicli-browsernpx skills add olo-dot-io/Uni-CLI --skill unicli-browsergit clone --depth 1 https://github.com/olo-dot-io/Uni-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/skills/olo-dot-io/uni-cli/unicli-browser)<a href="https://agentmods.dev/skills/olo-dot-io/uni-cli/unicli-browser"><img src="https://agentmods.dev/badge/skills/olo-dot-io/uni-cli/unicli-browser.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.01309 |
| Opus 5 | $0.00015 | $0.00655 |
| Sonnet 5 | $0.00006 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
unicli-browser 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Use unicli browser for browser lifecycle, page interaction, session sharing,
target handoff, and diagnostics. unicli operate is a compatibility alias for
the page-action subset.
Provider Decision
| Requirement | Provider and visibility |
|---|---|
| No window; default automation | managed + hidden (default) |
| Existing signed-in Chrome tab, no activation | chrome + background |
| Explicit user-visible Chrome interaction | chrome + foreground |
| Explicit cloud/browser service | remote + hidden |
No provider falls back to another. Managed and remote providers cannot become foreground. Existing Chrome cannot promise hidden operation.
Quick Start
unicli browser doctor --json # Probe only; starts nothing
unicli browser broker start # Start windowless control plane only
unicli browser start # Lazily start default managed hidden target
unicli browser open https://example.com
unicli browser state
unicli browser click <ref>
unicli browser screenshot ./page.png
unicli browser sessions --json
Agent Sessions and Reuse
A stable Agent session owns targets across turns. Different Agent sessions use different targets, while a shared profile partition can reuse login/storage.
unicli browser --session thread-42 --turn turn-1 open https://example.com
unicli browser --session thread-42 --turn turn-2 state
unicli browser --session thread-42 --turn turn-3 click 7
unicli browser sessions --json
unicli browser session-end thread-42
Use --profile-partition team-login to share storage deliberately. Use
--isolated for a disposable browser context inside that partition. --workspace
is a compatibility spelling for the same partition concept.
Existing Chrome Without Foreground Activation
Install the native host and extension once, keep an existing normal Chrome window open, list tabs, then claim a specific tab:
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.
- 3d ago First seen · 163 lines · 30 tokens per session scan A 172df357b5e8
unicli-browser is a skill published in the GitHub repository olo-dot-io/Uni-CLI (270 stars, last pushed 13d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,309 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.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
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…
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…
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…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.