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 bendrucker/claude --skill agent-browsergit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/agent-browser)<a href="https://agentmods.dev/skills/bendrucker/claude/agent-browser"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/agent-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/bendrucker/claude/agent-browser"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 MCP Rug Pull · line 6 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00067 | $0.00332 |
| Opus 5.5 | $0.00027 | $0.00133 |
| Sonnet 5.5 | $0.00013 | $0.00066 |
| Haiku 4.5 | $0.00007 | $0.00033 |
Grade A, and why
agent-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 4d 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.
What it actually says
agent-browser
Native browser-automation CLI (Chrome via CDP, accessibility-tree snapshots, compact @eN element refs).
This stub holds no usage details on purpose — load the version-matched workflow from the CLI before running any agent-browser command:
agent-browser skills get core # start here: workflows, patterns, troubleshooting
agent-browser skills get core --full # full command reference + templates
agent-browser skills get dogfood # exploratory testing / QA / bug hunts
agent-browser skills list # everything on the installed version
Sessions
Each --session runs its own Chrome until it is closed or its idle timeout passes.
- Use one session per agent, named for the agent rather than the item, and reuse it across items by navigating it.
- Run
agent-browser --session <name> closeonce your last item is done. - A brief for browser-driving subagents names one session per subagent, and at most two such subagents run at a time.
Slack automation exists via agent-browser skills get slack, but prefer the Slack MCP tools for reads/sends/searches.
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.
- 4d ago Changed · +8 lines c65956f125ca
- 1mo ago First seen · 24 lines · 67 tokens per session scan A 8fc7ad5c3530
agent-browser is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 332 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
test-site
Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.
preview-screens
Use when the user wants to preview generated screens in a browser without starting Metro / a simulator — for example after /create-mobile-app finishes or after /edit-app regenerates a screen.
broken-link-checker
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
desktop-act
Cross-OS computer-use MCP: multi-agent exclusive desktop leases, Xvnc pool on Linux, single-session macOS/Windows. Use for GUI/desktop automation and concurrent agent desktops.
airbnb-cli
Searches Airbnb from the terminal via cli-web-airbnb — find stays by location, dates, and filters; get listing details, guest reviews, and availability calendars; autocomplete location names. Use when the user asks about Airbnb, vacation rentals, listing prices, availability, or finding places to stay. Prefer…