OpenCLI is a command-line interface that turns websites, logged-in browser sessions, desktop apps, and local tools into interfaces that humans or AI agents can operate. It is used for navigating pages, filling forms, extracting information, and connecting agents to services through browser and tool adapters, with catalogue skills covering these workflows.
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 skills add jackwener/OpenCLI --skill opencli-browsergit clone --depth 1 https://github.com/jackwener/OpenCLIWrote 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/jackwener/opencli/opencli-browser)<a href="https://agentmods.dev/skills/jackwener/opencli/opencli-browser"><img src="https://agentmods.dev/badge/skills/jackwener/opencli/opencli-browser/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/skills/jackwener/opencli/opencli-browser"><img src="https://agentmods.dev/badge/skills/jackwener/opencli/opencli-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 4 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00043 | $0.01020 |
| Opus 5.5 | $0.00017 | $0.00408 |
| Sonnet 5.5 | $0.00009 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
opencli-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 today.
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.
Copies of this mod
2 near-identical copies found in the catalogue:
- opencli-browser — 100% identical, 486 lines differ
- opencli-browser — 100% identical, 478 lines differ
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser tools for agents
Use the capability that fits the task. Discover commands with opencli list <query>;
read exact arguments with opencli browser <command> --help -f json.
Run opencli doctor when diagnosing a connection problem.
Scope and results
Page commands require --session <name>. Reuse that name across a task; different
sessions isolate page work. --profile <name> selects a Chrome profile when needed.
Options can follow command arguments:
opencli browser open https://example.com --session research
opencli browser state --session research
opencli browser click --role button --name Search --session research
opencli browser close --session research
Default output is one JSON value: { "ok": true, "data": ... }.
Failures return { "ok": false, "error": { "code": "...", "message": "...", "hint": "..." } }
and a nonzero exit code. Diagnostic logs go to stderr. network --follow and
console --follow stream one envelope per line. Help, version and shell completion
are inspection/export surfaces; structured help uses --help -f json.
Read the returned data and error fields. When error.outcome is unknown, inspect
the affected state before retrying a write.
Page targets and interaction
statereturns URL and interactive element refs.--diagnosticsalso reports page title and available initial-state globals;--source axselects the AX tree.findlocates elements. Interaction targets accept a ref, CSS selector, or semantic flags such as--role,--name,--label,--text,--testid.- Use
--nthto resolve deliberate multiple matches. On stale refs, read fresh state or locate the element again; refs describe the observed page. fillreplaces a field and verifies its value;typetypes text. Other actions includeclick,select,check,upload,drag,keysanddialog.get text|value|attributes|html,extract,screenshotandevalexpose page data.evalexecutes JavaScript in the page and can mutate state.wait xhr|selector|text|downloadobserves an expected condition. Consult help for timeouts and matching rules.tab list|new|select|closemanages session tabs.--tabaccepts the page identity returned by these commands; these are different from numeric native Chrome IDs.frameslists frame targets;eval --frameevaluates in a selected frame.
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.
- today Changed · -346 lines · -37 tokens per session f9cce45ae035
- 22d ago Changed · -8 lines 1ddf7ba12ba2
- 1mo ago First seen · 445 lines · 80 tokens per session scan A ca08a2371a2e
opencli-browser is a skill published in the GitHub repository jackwener/OpenCLI (30,338 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 1,020 once invoked, about $0.0002 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.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
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…
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
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…
webcmd-browser
Use when a live browser task requires Playwright interaction, authenticated handoff, visible UI verification, or ad-hoc page inspection.
powerskills-browser
Edge browser automation via Chrome DevTools Protocol (CDP). List tabs, navigate, take screenshots, extract page content/HTML, execute JavaScript, click elements, type text, fill forms, scroll. Use when needing to control Edge browser, scrape web content, automate web forms, or take browser screenshots on Windows.…