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/manykarim/robotframework-agentskills/robotframework-selenium-skillnpx skills add manykarim/robotframework-agentskills --skill robotframework-selenium-skillgit clone --depth 1 https://github.com/manykarim/robotframework-agentskillsWhat 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 | $0.00046 | $0.02592 |
| Opus 5 | $0.00023 | $0.01296 |
| Sonnet 5 | $0.00009 | $0.00518 |
| Haiku 4.5 | $0.00005 | $0.00259 |
Grade A, and why
rf-selenium 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 2d 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 — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SeleniumLibrary Skill
Create browser automation tests using SeleniumLibrary with Selenium WebDriver.
Quick Reference
SeleniumLibrary provides browser automation using Selenium WebDriver. Unlike Browser Library, explicit waits are often required for reliable test execution.
Installation
pip install robotframework-seleniumlibrary
WebDriver binaries (chromedriver, geckodriver, etc.) must be in PATH. Selenium 4.6+ includes
Selenium Manager which handles driver downloads automatically, so executable_path and
webdriver-manager are often unnecessary with modern Selenium. For older versions:
pip install webdriver-manager
Library Import
*** Settings ***
Library SeleniumLibrary timeout=10s implicit_wait=0s
Import Options
| Option | Default | Description |
|---|---|---|
| timeout | 5s | Default timeout for wait keywords |
| implicit_wait | 0s | Implicit wait (0s is recommended; use explicit waits instead) |
| run_on_failure | Capture Page Screenshot | Keyword to run on failure |
| screenshot_root_directory | None | Directory for screenshots |
| plugins | None | Plugin modules to load |
WebDriver Setup Options
Chrome
# Basic
Open Browser ${URL} chrome
# Headless
Open Browser ${URL} headless_chrome
# With Options
Open Browser ${URL} chrome options=add_argument("--headless");add_argument("--no-sandbox")
# With WebDriver Manager
Open Browser ${URL} chrome executable_path=${DRIVER_PATH}
Firefox
Open Browser ${URL} firefox
Open Browser ${URL} headless_firefox
Open Browser ${URL} firefox options=add_argument("--headless")
Edge
Open Browser ${URL} edge
Open Browser ${URL} headless_edge
Locator Strategies
SeleniumLibrary requires strategy prefixes except for id and name attributes.
| Strategy | Syntax | Example |
|---|---|---|
| id | id=value or value |
id=username or username |
| name | name=value or value |
name=email |
| xpath | xpath=expression |
xpath=//button[@type='submit'] |
| css | css=selector |
css=button.primary |
| class | class=name |
class=submit-btn |
| tag | tag=name |
tag=button |
| link | link=text |
link=Click here |
| partial link | partial link=text |
partial link=Click |
| dom | dom=expression |
dom=document.forms[0] |
| jquery | jquery=selector |
jquery=button:visible |
| data | data=attr:value |
data=testid:submit |
| default | (no prefix) | username (tries id, then name) |
What ships with it
13 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/basic-web-test.robot 2.4 KB
- assets/examples/form-handling.robot 5.9 KB
- assets/examples/multi-window.robot 8.6 KB
- assets/examples/selenium-grid.robot 7.8 KB
- assets/examples/wait-patterns.robot 9.2 KB
- references/frames-windows.md 10 KB
- references/javascript-execution.md 12 KB
- references/keywords-reference.md 13 KB
- references/locators.md 8.5 KB
- references/screenshots-logs.md 8.9 KB
- references/troubleshooting.md 9.6 KB
- references/waiting-strategies.md 9.4 KB
- references/webdriver-setup.md 10 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.
- 2d ago First seen · 394 lines · 46 tokens per session scan A d016cd2108e4
rf-selenium is a skill published in the GitHub repository manykarim/robotframework-agentskills (30 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 2,592 once invoked, about $0.0002 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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
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.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
browser_cdp
通过 Chrome DevTools Protocol (CDP) 连接已运行的浏览器，或扫描本机 CDP 端口，用于远程调试与多工具共享浏览器实例。.