BrowserOS is an open-source browser system that provides a separate browser for AI agents alongside a browser for personal use. Agents use it to perform tasks in logged-in websites while people monitor or replay their sessions.
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 browseros-ai/BrowserOS --skill test-uigit clone --depth 1 https://github.com/browseros-ai/BrowserOSWrote 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/browseros-ai/browseros/test-ui)<a href="https://agentmods.dev/skills/browseros-ai/browseros/test-ui"><img src="https://agentmods.dev/badge/skills/browseros-ai/browseros/test-ui/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/browseros-ai/browseros/test-ui"><img src="https://agentmods.dev/badge/skills/browseros-ai/browseros/test-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Server-Side Request Forgery · line 235 Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
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 | $0.00059 | $0.02658 |
| Opus 5.5 | $0.00024 | $0.01063 |
| Sonnet 5.5 | $0.00012 | $0.00532 |
| Haiku 4.5 | $0.00006 | $0.00266 |
Grade A, and why
test-ui 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 23d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 23d ago Changed · -1 lines c4fd78087cd0
- 1mo ago First seen · 287 lines · 59 tokens per session scan A 19a36b8c843c
test-ui is a skill published in the GitHub repository browseros-ai/BrowserOS (13,976 stars, last pushed yesterday), licensed AGPL-3.0. It adds 59 tokens to every session and 2,658 once invoked, about $0.0002 per session on Opus 5.5. 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
experimental-code-coverage-cq-debugger
Executes the phased, multi-skill code coverage debugging playbook for triaging underreported code coverage in the Gerrit Commit Queue (CQ).
android-do-not-mock
How to write (or fix) Chromium Java unit tests (Robolectric / JUnit) without mocking or spying android.view.View, android.app.Activity, or their subclasses. Use when removing @SuppressWarnings("DoNotMock"), fixing a "DoNotMock" Error Prone error, replacing Mockito.mock(View.class) / @Mock Activity / spy(view), or when…
sync-new-data-type
Adds scaffolding for a new Sync data type in Chromium across protocol buffers, DataType definitions, feature flags, controller builders, unit tests, and metrics.
test-conversion
Workflow for converting unit tests to browser tests for Project Bedrock. Invoke this when the user wants to remove complex Browser dependencies from tests.
android-unit-test
Guide for writing and converting Chromium Android unit tests across host Robolectric (chromejunittests) and on-device (chromepublicunittestapk) suites.
experimental-code-coverage-build-inspector
Inspects LUCI build details using the inspectcoveragebuild.py script to validate code coverage configurations, test execution, and target file coverage.