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/sirallap/agentglass/browser-usenpx skills add SirAllap/agentglass --skill browser-usegit clone --depth 1 https://github.com/SirAllap/agentglassWrote 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/sirallap/agentglass/browser-use)<a href="https://agentmods.dev/skills/sirallap/agentglass/browser-use"><img src="https://agentmods.dev/badge/skills/sirallap/agentglass/browser-use.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 | $0.00080 | $0.00790 |
| Opus 5 | $0.00040 | $0.00395 |
| Sonnet 5 | $0.00016 | $0.00158 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
browser-use scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Drive agentglass's built-in browser — the one already signed in to the sites this project uses. Use when a task needs a page behind a login (a dashboard, a ticket, a staging app), when a URL fetched with cur How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the built-in browser
curl gets you the signed-out version of everything that matters, because the
session lives in a browser. agentglass has one, in a pane, already signed in to
whatever the person using it is signed in to. agentglass-browser drives it.
agentglass-browser open https://github.com/notifications
agentglass-browser read # title, url, and the visible text
agentglass-browser click "a.notification-list-item-link"
agentglass-browser type "#search" "billing bug" --submit
agentglass-browser wait ".results" # until it appears, or it fails
agentglass-browser shot /tmp/page.png # png on disk; read it if you can see images
agentglass-browser text ".invoice-total" # one element, instead of the whole page
agentglass-browser back # and `forward`
agentglass-browser scroll --to bottom # or --by -400, or --selector "#footer"
agentglass-browser press Escape # Enter, Tab, Escape, arrows, PageUp/Down, Home, End
Every command exits non-zero and prints one line to stderr when it did not do the thing — a selector that matched nothing, a page that never loaded, a window that is not open. Branch on that rather than on the text.
How to work with it
Read before you click. read gives you the page as text. Decide from that
what to click, rather than guessing a selector from the URL.
Then read narrowly. Once you know where the answer is, text ".selector"
costs a fraction of read on a long page. Reach for read to orient yourself,
text to get the value.
Selectors are CSS, and stable ones win. #login, a[href="/settings"],
button[type=submit]. A selector built from a generated class name works once.
Waiting is a verb. After anything that navigates or loads, wait for
something that only exists on the page you expect. It is how you find out you
landed on a login page instead.
Scrolling changes what read returns, because it reports the visible
text. If a page looks truncated, scroll and read again — scroll tells you
where it ended up and whether it is at the bottom.
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.
- 5d ago First seen · 66 lines · 80 tokens per session scan A 65ddd1ec17e9
browser-use is a skill published in the GitHub repository SirAllap/agentglass (289 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 790 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-worldmonitor
Launch and drive the WorldMonitor browser dashboard (Vite app at /dashboard) to prove user-facing behavior with screenshots and transcripts. Use when a change needs proof in the real app rather than only unit tests — panels, map layers, settings, search, country briefs, boot — or when asked to run, screenshot, or…
playwright-mcp-metabase
Drive Metabase's UI with the Playwright MCP browser tools (mcpplaywrightbrowser). Covers the snapshot/act/check pattern, Mantine component pitfalls (Menu race, Select/MultiSelect, the Escape-closes-modal trap, portal scoping), and Metabase-specific login flows. Use whenever a session needs to interact with the…
go-rig
Use this skill when building, reviewing, or refactoring Go code that must follow strict design discipline — ATDD/TDD workflow, explicit dependency injection, package-boundary discipline, and structured code review. Complements CLAUDE.md by focusing on process and design judgment rather than version-specific Go…
frontend-dashboard
Use this skill when editing the embedded dashboard frontend in this repository. It focuses on preserving the single-file embedded SPA model, keeping the UI lightweight, and avoiding unnecessary frontend tooling or dependencies.
project-ops
Use this skill when working on repository operations in this project, including build, test, lint, release, CI alignment, Makefile-driven checks, and operational packaging constraints.
go-review
Use this skill when the task is to review Go code in this repository. Focus on bugs, regressions, API compatibility, test gaps, concurrency risks, and violations of the zero-dependency and root-facade constraints.