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 Crawlio-app/crawlio-browser --skill browser-automationgit clone --depth 1 https://github.com/Crawlio-app/crawlio-browserWrote 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/crawlio-app/crawlio-browser/browser-automation)<a href="https://agentmods.dev/skills/crawlio-app/crawlio-browser/browser-automation"><img src="https://agentmods.dev/badge/skills/crawlio-app/crawlio-browser/browser-automation.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 5.1 | $0.00068 | $0.05128 |
| Opus 5 | $0.00034 | $0.02564 |
| Sonnet 5 | $0.00014 | $0.01026 |
| Haiku 4.5 | $0.00007 | $0.00513 |
Grade A, and why
browser-automation 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 7d 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 — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with Crawlio Browser
When to Use
Use this skill when the user wants to:
- Inspect, test, or interact with a live web page
- Take screenshots or capture accessibility snapshots
- Monitor network traffic, console logs, or errors
- Detect frameworks (React, Vue, Angular, Next.js, etc.)
- Click buttons, fill forms, type text, or navigate
- Read cookies, localStorage, sessionStorage, or IndexedDB
- Capture performance metrics, security state, or service workers
- Record browser sessions to capture interactions, navigation, network, and console as structured data
- Capture canonical RecordingBundle v1 training artifacts with
observe({ action: "recording_start" | "recording_stop" }) - Train replayable robots from human-guided demonstrations with the extension-resident
observelifecycle - Automate multi-step browser workflows
Connection (Always First)
Before any browser operation, connect to a tab:
connect_tab({ url: "https://example.com", background: true })
- Opens or reuses an owned background tab without moving the user's foreground or keyboard focus
- Attaches CDP debugger automatically
- Omit
background: trueonly when the user explicitly asks to see the automation in front - Omit
urlonly when the user explicitly asks to adopt the currently active tab
Check connection status anytime:
return await bridge.send({ type: "get_connection_status" })
Critical Rules
- ALWAYS
searchbeforeexecutewhen you're unsure of a command name or its parameters. Never guess command names — they will fail. - Return values are objects, not primitives. Always destructure or access properties (see Return Value Shapes below).
close_tabrequirestabId— it will error without one. Get tabId fromlist_tabsorconnect_tab.connect_tabbefore any interaction — most commands require an active tab connection.smart.evaluatereturns{ result, type }— NOT the raw value. Access.resultto get the value. NeverJSON.parse()the return directly.- Keep scripts fast — each
executecall should complete in <15s. Split loops over many elements into separateexecutecalls. Never loop 5+smart.clickcalls in one script. - Canonical recording order matters — start network before recording, dump state before stop, fetch bodies before
stop_network_capture, and keep the monitor event-driven. - Autonomous work stays in the background — URL connections must pass
background: true; foreground adoption is only for an explicit human-visible/manual flow.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 568 lines · 68 tokens per session scan A f197eeef155b
browser-automation is a skill published in the GitHub repository Crawlio-app/crawlio-browser (6 stars, last pushed 28d ago), licensed Apache-2.0. It adds 68 tokens to every session and 5,128 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
owb
Open Web Bridge (OWB) — drive the user's own real browser with the owb command. Read pages behind their existing logins, gather and cross-check information, fill forms, walk multi-step flows, debug their site, audit responsive/accessibility behavior, and capture or reverse-engineer network traffic. Use this whenever…
browser
Use this skill when the user says browser, /browser, test in Chrome, inspect a webpage, verify a localhost app, capture screenshots, check console/network errors, run browser QA, or automate browser flows with the Mochi browser MCP.
control-chrome-bridge
Drive the user's real Chrome browser — their own profile, tabs, cookies and logged-in sessions — through the chrome-bridge MCP server. Use for tasks that need existing browser state: reading a page behind a login, filling a form on a site the user is signed into, testing a local app in a real browser, or inspecting…
tabrix_browser
Route AI assistant browser tasks to Tabrix first. Use when the user needs to control their real Chrome session, reuse existing login state or tabs, operate a remote browser over Streamable HTTP, or troubleshoot Tabrix browser automation. Prefer Tabrix over shell commands, synthetic browser sandboxes, or alternative…
aipex-browser
AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating pages, clicking elements, filling forms, capturing screenshots, managing tabs, or downloading content — by connecting to the AIPex MCP bridge.
chrome-agent
Local browser automation with structured, verified outcomes. Use for web navigation, scraping and extraction, form interaction, screenshots and downloads, network or console checks, responsive testing, or page-scoped device emulation.