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 sixb-ai/sixb --skill browsergit clone --depth 1 https://github.com/sixb-ai/sixbWrote 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/sixb-ai/sixb/browser)<a href="https://agentmods.dev/skills/sixb-ai/sixb/browser"><img src="https://agentmods.dev/badge/skills/sixb-ai/sixb/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/sixb-ai/sixb/browser"><img src="https://agentmods.dev/badge/skills/sixb-ai/sixb/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 | $0.00026 | $0.00300 |
| Opus 5.5 | $0.00010 | $0.00120 |
| Sonnet 5.5 | $0.00005 | $0.00060 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade B, and why
browser scanned grade B with 1 finding 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 18d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Publish only requested final files using the worker's output instructions. Browser traces, temporary What it actually says
Use a Node .cjs script with require("/opt/sixb/js/node_modules/playwright"). The matching
Chromium headless shell is already installed at $PLAYWRIGHT_BROWSERS_PATH; use
chromium.launch({ headless: true }). Do not download another browser or select an uninstalled
Chrome channel. Close the browser in finally and set bounded navigation/action timeouts.
Local HTML can be loaded with page.setContent(html) or a file URL without external network access.
External pages, images, fonts, and API calls depend on the sandbox network policy. Report a blocked
source instead of repeatedly reinstalling tools. Requests and Beautiful Soup are also available for
fetching permitted static pages and parsing HTML. Neither provides a search index.
Save screenshots and PDFs inside the workspace. Use view_file to inspect screenshots when image
input is supported; check the resulting page state after interaction. Before printing a PDF, wait for
fonts and relevant images, set print styles/page size, and inspect the resulting PDF page previews
with sixb-render. A successful navigation or screenshot does not prove the page meets the task.
Publish only requested final files using the worker's output instructions. Browser traces, temporary HTML, and screenshots used for verification are working files unless requested.
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.
- 18d ago First seen · 23 lines · 26 tokens per session scan B 503a4312b714
browser is a skill published in the GitHub repository sixb-ai/sixb (115 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 300 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-28.
Other skills, from other repositories
playwright
Use when the task requires capturing or automating a real browser from the terminal.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
browser-tools
Security wrapper over the upstream agent-browser skill, adding URL blocklisting, rate limiting, robots.txt enforcement, and scraping guardrails. Use when automating browser workflows that need safety limits.
qa-screenshot
Screenshot a page (deploy preview or a dev server on localhost) in the sandbox's headless Chromium, look at it, and embed it in a task comment. Use to verify a visual change or record before/after evidence.
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
web-system-tests
The web realization of the system-tests contract — browser-driven system tests with Playwright against a running frontend. Owns the project layout (tests/), the Playwright configuration (baseURL plus webServer, cross-engine projects), the role- and label-based selector policy, code coverage as an opt-in second run…