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/citedy/adclaw/browser_visiblenpx skills add citedy/adclaw --skill browser_visiblegit clone --depth 1 https://github.com/citedy/adclawWrote 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/citedy/adclaw/browser_visible)<a href="https://agentmods.dev/skills/citedy/adclaw/browser_visible"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/browser_visible.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 | $0.00050 | $0.00599 |
| Opus 5 | $0.00025 | $0.00300 |
| Sonnet 5 | $0.00010 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
browser_visible 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visible Browser (Real Window) Reference
By default, browser_use runs in headless mode in the background without opening a browser window. When the user explicitly wants to open a real browser window, see the browser interface, use a browser with a GUI, or use a visible browser, this skill should be used: first launch the browser in headed mode, then open pages and interact as needed.
When to Use
- The user says: "Open a real browser", "Open a browser with a GUI", "I want to see the browser", "Don't run in the background, I want to see the window"
- The user wants to watch the page loading, clicking, form filling, etc. in real time (for demos, debugging, or teaching)
- The user needs to interact with a visible page (e.g., login, CAPTCHA, or other scenarios requiring manual intervention)
How to Use (browser_use)
-
Launch the browser in visible mode first Call browser_use with
actionset tostartand pass headed=true:{"action": "start", "headed": true}On success, a real Chromium browser window will appear.
-
Open pages and interact as needed Usage is the same as in headless mode, for example:
- Open a URL:
{"action": "open", "url": "https://example.com"} - Get the page structure:
{"action": "snapshot"} - Click, type, etc.: use
reforselectorfor click, type, and other actions
- Open a URL:
-
Close the visible browser When finished, call:
{"action": "stop"}to close the browser.
Differences from Default (Headless) Mode
| Mode | Launch Method | Opens a Window? |
|---|---|---|
| Headless | {"action": "start"} |
No (background) |
| Visible | {"action": "start", "headed": true} |
Yes (real window) |
Notes
- If a browser is already running, you must
stopit first and thenstartagain withheaded: trueto switch to a visible window. - Visible mode requires a desktop and graphical environment. It may not work on servers or environments without a display.
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 First seen · 53 lines · 50 tokens per session scan A 03c5c737ea69
browser_visible is a skill published in the GitHub repository citedy/adclaw (35 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 599 once invoked, about $0.0003 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
playwright-uitest
Generate Playwright UI tests and visual smoke reports for delivery POC frontends.
actionbook
MUST USE AUTOMATICALLY when user sends URLs from x.com, twitter.com, or any site that webfetch fails on. Do NOT ask the user — just load this skill and use it. Browser automation and web scraping with anti-detection stealth mode. Capabilities: (1) Scrape Twitter/X content without login, (2) Extract data from…
browser
Управление браузером: открытие страниц, взаимодействие, история, закладки.
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
update-setup
One-time setup wizard for the nanobot upgrade skill. Triggers: setup update, configure update, 设置更新, 初始化更新.