Sample Strands Agent with Amazon Bedrock AgentCore is an end-to-end reference architecture for building multi-agent chatbots on AWS. Teams use it to explore agent orchestration, tool execution, memory, browser automation, and agent-to-agent collaboration with Strands Agents and Bedrock AgentCore.
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/aws-samples/sample-strands-agent-with-agentcore/browser-automationnpx skills add aws-samples/sample-strands-agent-with-agentcore --skill browser-automationgit clone --depth 1 https://github.com/aws-samples/sample-strands-agent-with-agentcoreWrote 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/aws-samples/sample-strands-agent-with-agentcore/browser-automation)<a href="https://agentmods.dev/skills/aws-samples/sample-strands-agent-with-agentcore/browser-automation"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-strands-agent-with-agentcore/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 | $0.00027 | $0.00860 |
| Opus 5 | $0.00014 | $0.00430 |
| Sonnet 5 | $0.00005 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation
Available Tools
- browser_act(instruction, starting_url?): Execute browser actions using natural language (click, type, scroll, select). Use
starting_urlto navigate to a page and act in a single call. - browser_get_page_info(url?, text?, tables?, links?): Get page structure and DOM data (fast, no AI). Use
urlto navigate first;text=Truefor full text,tables=Truefor table data,links=Truefor all links. - browser_manage_tabs(action, tab_index?, url?): Switch, close, or create browser tabs
- browser_save_screenshot(filename): Save current page screenshot to workspace
When to Use
Use browser automation when the task genuinely requires it:
- UI interactions: Filling forms, clicking buttons, navigating multi-step workflows
- Login-required pages: Accessing content behind authentication that APIs cannot reach
- Dynamic/JS-heavy pages: Content rendered client-side that plain HTTP requests can't capture
- Human-like browsing needed: Sites that block bots or require realistic interaction patterns
- Scraping structured data: When no API exists and the data must be extracted from rendered pages
Prefer web search or url_fetcher for general information lookup, news, or publicly accessible pages — browser automation is slower and heavier. Reserve it for tasks where simpler tools are insufficient.
Tool Selection
browser_act: UI interactions (click, type, scroll, form fill). Usestarting_urlto open a page and act in one call.browser_get_page_info: Fast page structure check and optional content extraction (<300ms). Useurlto navigate first.browser_manage_tabs: Switch/close/create tabs (view tabs viaget_page_info)browser_save_screenshot: Save milestone screenshots (search results, confirmations, key data)
browser_act Best Practice
- Combine up to 3 predictable steps: "1. Type 'laptop' in search 2. Click search button 3. Click first result"
- Use
starting_urlwhen opening a fresh page:browser_act(instruction='Search for laptops', starting_url='https://amazon.com') - On failure: check the screenshot to see current state, then retry from that point
- For visual creation (diagrams, drawings), prefer code/text input methods over mouse interactions
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.
- 5d ago First seen · 58 lines · 27 tokens per session scan A ee0e5ea2e401
browser-automation is a skill published in the GitHub repository aws-samples/sample-strands-agent-with-agentcore (192 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 860 once invoked, about $0.0001 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
mk:agent-browser
Browser automation CLI for AI agents using agent-browser. Use for navigating websites, clicking/filling pages, screenshots, data extraction, web app testing, exploratory QA, dogfooding, Electron apps, Slack automation, Vercel Sandbox browser runs, AWS AgentCore cloud browsers, auth-heavy flows, and long autonomous…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
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.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…
pinchtab
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…