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 manykarim/robotframework-agentskills --skill rf-browsergit clone --depth 1 https://github.com/manykarim/robotframework-agentskillsWrote 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/manykarim/robotframework-agentskills/rf-browser)<a href="https://agentmods.dev/skills/manykarim/robotframework-agentskills/rf-browser"><img src="https://agentmods.dev/badge/skills/manykarim/robotframework-agentskills/rf-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/manykarim/robotframework-agentskills/rf-browser"><img src="https://agentmods.dev/badge/skills/manykarim/robotframework-agentskills/rf-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 | $0.00022 | $0.02492 |
| Opus 5.5 | $0.00009 | $0.00997 |
| Sonnet 5.5 | $0.00004 | $0.00498 |
| Haiku 4.5 | $0.00002 | $0.00249 |
Grade A, and why
rf-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 11d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Library Skill
Browser Library drives Chromium, Firefox and WebKit through Playwright: auto-waiting actions, retrying assertions, one isolated context per session. It is the default for new web tests; for suites that already import SeleniumLibrary, use rf-selenium. Verified against Browser 19.14.2, Robot Framework 7.4.
When to use
Load this skill first, before exploring the project or answering from memory, when a Robot Framework web UI test uses Browser Library (Library Browser, Playwright):
- writing or fixing a web test: pages, contexts and tabs, CSS/text/XPath selectors including iframes and shadow DOM, auto-waiting, assertions with an operator, downloads, storage state;
- a click or selector times out (
TimeoutError: locator.click), or the user mentions Browser Library, Playwright or rfbrowser, even if they only say "browser lib"; - a new web test with no library chosen yet: Browser Library is the default.
Not this skill: suites that import SeleniumLibrary or run on WebDriver/Selenium Grid use rf-selenium; installing the library or errors in its Node.js rfbrowser init step use rf-setup.
Installation
Install into the project environment (see rf-setup for uv/venv/Poetry, CI and troubleshooting; follow the project's existing tool):
uv add "robotframework-browser[bb]"
uv run rfbrowser install chromium
BrowserBatteries ([bb]) ships the Playwright wrapper, so no Node.js is needed. rfbrowser install downloads the browser binaries.
Node.js escape hatch — only if no BrowserBatteries wheel exists for your platform, or you need Node plugins (Node 22/24/26 LTS):
uv add robotframework-browser
uv run rfbrowser init chromium
Don't mix the paths: rfbrowser install belongs to [bb], rfbrowser init to the Node.js path.
Import and defaults
Import the library without arguments; its defaults are the recommendation: strict mode on, timeout=10s for actions and waits, retry_assertions_for=1s, auto_closing_level=TEST, and a screenshot on every failing Browser keyword.
What ships with it
11 files 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.
- assets/examples/authentication-flow.robot 1.1 KB
- assets/examples/basic-web-test.robot 868 B
- assets/examples/form-handling.robot 1.6 KB
- assets/examples/iframe-shadow-dom.robot 1.1 KB
- references/assertion-engine.md 4.0 KB
- references/authentication-storage.md 3.2 KB
- references/browser-context-page.md 4.0 KB
- references/downloads-uploads.md 2.2 KB
- references/iframes-shadow-dom.md 2.5 KB
- references/locators.md 3.0 KB
- references/troubleshooting.md 5.1 KB
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.
- 11d ago Changed · -5 tokens per session 1a0c16c9db53
- 17d ago First seen · 132 lines · 27 tokens per session scan A 9173e429f8a3
rf-browser is a skill published in the GitHub repository manykarim/robotframework-agentskills (38 stars, last pushed 5d ago), licensed Apache-2.0. It adds 22 tokens to every session and 2,492 once invoked, about $0.0001 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 2026-10-01.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…