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 mxyhi/ok-skills --skill opencli-browsergit clone --depth 1 https://github.com/mxyhi/ok-skillsWrote 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/mxyhi/ok-skills/opencli-browser)<a href="https://agentmods.dev/skills/mxyhi/ok-skills/opencli-browser"><img src="https://agentmods.dev/badge/skills/mxyhi/ok-skills/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/mxyhi/ok-skills/opencli-browser"><img src="https://agentmods.dev/badge/skills/mxyhi/ok-skills/opencli-browser.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 | $0.00043 | $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 6d 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.
This is a copy
100% identical to opencli-browser — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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.
- 6d ago Changed · -346 lines · -37 tokens per session f9cce45ae035
- 24d 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 mxyhi/ok-skills (505 stars, last pushed 7d ago), 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. It is 100% identical to opencli-browser, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
browser_cdp
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default, browseruse already launches the browser using managed CDP; if the user does not want to expose browser history, cookies, or…
browser_cdp
A guide for connecting browser-control tools to an existing Chrome session through its remote debugging interface. It explains scanning ports, attaching to a browser, choosing a port, sharing a browser, and switching to a more private control mode.
awesome-content-publisher
Publishes prepared posts to the user's own accounts through their live browser, on schedule, with login checks, a no-duplicates ledger and a confirmation gate before anything goes public. Use when asked to publish posts.
browser_visible
A guide to browseruse launch settings for Chromium-based browsers. It covers visible windows, private control, extra browser start options such as incognito mode or a proxy, and choosing a browser executable path.
browser_visible
Use this skill when the user needs to control the browser launch mode for browseruse. By default, browseruse launches the local Chrome/Chromium using managed CDP; headed controls whether the window is visible, and privatemode controls whether CDP is disabled in favor of Playwright.