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 browser-use/desktop --skill browser-harness-jsgit clone --depth 1 https://github.com/browser-use/desktopWrote 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/browser-use/desktop/browser-harness-js)<a href="https://agentmods.dev/skills/browser-use/desktop/browser-harness-js"><img src="https://agentmods.dev/badge/skills/browser-use/desktop/browser-harness-js/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/browser-use/desktop/browser-harness-js"><img src="https://agentmods.dev/badge/skills/browser-use/desktop/browser-harness-js.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 MCP Rug Pull · line 10 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00060 | $0.03189 |
| Opus 5.5 | $0.00024 | $0.01276 |
| Sonnet 5.5 | $0.00012 | $0.00638 |
| Haiku 4.5 | $0.00006 | $0.00319 |
Grade A, and why
cdp 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 1mo 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CDP — browser-harness-js skill
Custom codegen'd CDP SDK (every method from browser_protocol.json + js_protocol.json gets a typed wrapper) plus a tiny HTTP server that holds one persistent CDP Session. The browser-harness-js CLI auto-starts the server on first use and forwards JS snippets to it.
Browser Use Desktop bundles the runtime under ./browser-harness-js/sdk/ and puts that directory on PATH for you. Do not run npx skills add or create global symlinks from inside the desktop harness.
First use in Browser Use Desktop
Connect to the app-assigned target before page-level calls:
browser-harness-js 'await connectToAssignedTarget()'
connectToAssignedTarget() reads BU_TARGET_ID and BU_CDP_PORT, attaches the assigned target when possible, and enables the common Page/DOM/Runtime/Network domains. The CLI auto-installs bun on first run if it is missing. Set BROWSER_HARNESS_SKIP_BUN_INSTALL=1 to opt out.
How to use
Just run browser-harness-js '<JS>'. The first call spawns the server in the background; subsequent calls hit the same process and so reuse the same session, the same WebSocket to Chrome, and any globals you set.
browser-harness-js 'await connectToAssignedTarget()'
browser-harness-js 'await session.Page.navigate({url:"https://example.com"})'
browser-harness-js '(await session.Runtime.evaluate({expression:"document.title",returnByValue:true})).result.value'
Output is the raw result content — no {ok,result} envelope.
| Result type | stdout |
|---|---|
| string | bare text, no JSON quotes (e.g. Example Domain) |
| number / boolean | 42, true |
| object / array (non-empty) | compact JSON (e.g. {"frameId":"..."}, [1,2,3]) |
undefined / null / "" / {} / [] |
empty (no output) |
Errors go to stderr, exit code 1. The CDP error message and JS stack are printed verbatim, e.g.:
Error: CDP -32602: invalid params
at _call (.../session.ts:117:33)
...
Detect failure with if browser-harness-js '...'; then ...; else handle_error; fi or by checking $?.
What ships with it
5 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.
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.
- 1mo ago First seen · 249 lines · 60 tokens per session scan A 64570f439df6
cdp is a skill published in the GitHub repository browser-use/desktop (700 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 3,189 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
browser_harness
../../SKILL.md.
Browser Agent QA Testing
Teach agents to use AI browser agents for exploratory and smoke QA with step budgets, evidence-based assertions, guardrails, and Playwright conversion.
browser-harness
Control a real browser via CDP: clicking, typing, navigation, logged-in sessions, JS-rendered or bot-protected pages. Not for plain HTTP fetches of public content - use curl for those.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.