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-browser-skillnpx skills add manykarim/robotframework-agentskills --skill robotframework-browser-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 | $0.00059 | $0.02059 |
| Opus 5 | $0.00030 | $0.01030 |
| Sonnet 5 | $0.00012 | $0.00412 |
| Haiku 4.5 | $0.00006 | $0.00206 |
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 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.
This is a copy
91% identical to browser — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Library Skill
Quick Reference
Browser Library uses Playwright for fast, reliable browser automation with built-in auto-waiting and powerful assertion capabilities.
Installation
pip install robotframework-browser
rfbrowser init
Library Import
*** Settings ***
Library Browser auto_closing_level=KEEP
Import options:
auto_closing_level=KEEP- Keep browser open between tests (faster)auto_closing_level=TEST- Close after each test (clean state)timeout=30s- Default timeout for operationsenable_presenter_mode=true- Slow down for demos
Essential Concepts
Browser -> Context -> Page Hierarchy
Browser (chromium/firefox/webkit)
└── Context (isolated session: cookies, storage)
└── Page (single tab/window)
- Browser: The browser process (Chrome, Firefox, or WebKit)
- Context: Isolated browser session with its own cookies, localStorage, and cache
- Page: A single tab or popup window within a context
New Browser chromium headless=false
New Context viewport={'width': 1920, 'height': 1080}
New Page https://example.com
Auto-Waiting
Browser Library automatically waits for elements to be actionable before interacting. No explicit waits needed in most cases.
- Waits for element to be visible
- Waits for element to be stable (not animating)
- Waits for element to be enabled
- Waits for element to receive events
Core Keywords Quick Reference
Navigation
New Browser chromium headless=false
New Context viewport={'width': 1920, 'height': 1080}
New Page https://example.com
Go To https://example.com/login
Reload
Go Back
Go Forward
Locators (Selector Syntax)
# CSS (default)
Click button.submit
Click #login-btn
Click [data-testid="submit"]
# Text
Click text=Login
Click "Login" # Exact text match
# XPath
Click xpath=//button[@type='submit']
# Chained selectors (powerful!)
Click .form >> button.submit
Click #container >> text=Save
# nth-match
Click button >> nth=0 # First button
Click button >> nth=-1 # Last button
# Role selectors (accessibility)
Click role=button[name="Submit"]
What ships with it
14 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 6.1 KB
- assets/examples/basic-web-test.robot 2.9 KB
- assets/examples/file-operations.robot 8.1 KB
- assets/examples/form-handling.robot 5.2 KB
- assets/examples/iframe-shadow-dom.robot 6.5 KB
- references/assertion-engine.md 7.1 KB
- references/authentication-storage.md 8.9 KB
- references/browser-context-page.md 8.5 KB
- references/downloads-uploads.md 8.9 KB
- references/iframes-shadow-dom.md 7.4 KB
- references/keywords-reference.md 12 KB
- references/locators.md 6.0 KB
- references/tabs-windows.md 7.6 KB
- references/troubleshooting.md 9.8 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 · 310 lines · 59 tokens per session scan A 62d792a5d035
rf-browser is a skill published in the GitHub repository manykarim/robotframework-agentskills (30 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 2,059 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to browser, differing in 14 lines, and is treated as a copy.
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…
e2e-deployment-skill
Use this deployment skill to verify shared skills load during Playwright startup.
launch
Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact with the running workbench, automate chat or UI flows, test…
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.
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…
web-preview
Flutter Web版をビルド → サーバー起動 → Playwright でアクセス確認 → URLをユーザーに案内する。.