Ego Browser

ego-browser

For installation, connection, or runtime problems, read references/install.md. Use help() or references/api.md for signatures and uncommon options of APIs named below.

Run browser scripts

Run JavaScript through a heredoc:

ego-browser nodejs <<'EOF'
const task = await taskSpace("inspect example page");
const page = task.page("p1");
await page.goto("https://example.com");

console.log({ taskSpaceId: task.spaceId, page: page.label });
console.log(await page.snapshot());
EOF

In some sandbox environments, heredoc input may not work; use -e instead:

ego-browser nodejs -e '
const task = await taskSpace("inspect example page");
const page = task.page("p1");
await page.goto("https://example.com");
console.log({ taskSpaceId: task.spaceId, page: page.label });
console.log(await page.snapshot());
'

In Bash/Zsh, use single quotes around the code and double quotes for JavaScript strings. Single quotes within the code require shell quoting.

The script always runs in Node.js, not in the web Page. Browser helpers and Node.js APIs belong in the script; Page globals such as window, document, location, and DOM APIs do not. Put browser-side JavaScript inside page.evaluate(). Do not import Playwright or launch another browser.

The Node.js runtime uses ESM. When a script needs local files, load built-ins with dynamic imports such as await import("node:fs/promises").

Ego-browser deliberately exposes a small custom API. It is not Playwright, even where method names and options look similar. Use only the TaskSpace, Page, FileChooser, mouse, and keyboard APIs explicitly listed in this Skill. Do not infer Playwright methods such as locator(), getByRole(), context(), expect(), or route(). When the listed API does not cover an operation, use the documented page.evaluate() or page.cdp() escape hatches instead of guessing another method.

Pointer actions accept an optional label with a concise 3-6 word description. Pass it with clicks, hovers, drags, or scrolling to keep the action text next to the visible agent cursor in sync with the action.

When the user explicitly asks for ego-browser, start with a real browser command and diagnose the CLI or installation only if it fails.

Spaces, rounds, and pages

• Use exactly one TaskSpace for the entire user goal. Create it once, print its spaceId, and resume that same space in later rounds. Use multiple spaces only when the user explicitly requests them.
• Never use a new TaskSpace to recover from a stuck, blocked, timed-out, or unexpected Page. Recover within the existing space; if it cannot continue, stop and ask the user.
• Every invocation starts a new Node.js process. Task spaces, tabs, and Page labels persist; JavaScript variables do not.
• A new task space starts with Page p1; navigate it instead of opening another Page.
• Reuse a Page with goto() instead of opening a new Page for every URL.
• All time values are milliseconds.

// Later round: use the space id and Page label printed earlier.
const resumed = await taskSpace(7);
const source = resumed.page("p1");
await source.goto("https://example.com/releases");

Do not inspect or select profiles unless the user explicitly requests a particular Ego Lite profile. A profileId applies only when creating a space; use help("profiles") for the exact workflow.

Supported TaskSpace API:

• State: spaceId, name, ownership, page(label), userPage()
• Pages: await task.pages(), await task.tabs(), newPage(), adopt(page, { as? }), release(label)
• Control: waitForControl(options), handOff(), finish({ keep })
• Advanced: cdp(method, params, options)

Pages receive permanent labels such as p1, p2, and p3. Prefer these labels to custom { as } values. Reuse or close Pages as the task proceeds; the runtime reports the configured Page budget when it is reached.

task.newPage() creates another blank Page when multiple Pages must stay open. Navigate it separately with page.goto().

await task.pages() returns managed Pages. await task.tabs() returns every tab in the space as { label?, page, targetId, title, url, active, openedBy }. A tab without a label is unmanaged; adopt it before operating:

const active = (await task.tabs()).find((item) => item.active);
if (active && !active.label) {
  const page = await task.adopt(active.page);
  console.log({ page: page.label, url: await page.url() });
}

release(label) returns an unknown-origin Page to the user without closing its tab. Close Agent-created Pages with page.close(). Treat openedBy: "unknown" as user-owned when deciding whether a Page may be closed.

Page operations

ego-browser provides the following Page API:

• State and observation: label, spaceId, openedBy, targetId, url(), title(), info(), snapshot(), screenshot()
• Navigation and waits: goto(), reload(), waitForURL(), waitForEvent(), waitForSelector(), waitForLoadState(), waitForFunction(), waitForTimeout()
• Elements: click(), dblclick(), hover(), dragAndDrop(), fill(), selectOption(), focus(), press(), setInputFiles(), waitForFileChooser(), close()
• Dialogs: acceptDialog(promptText?), dismissDialog()
• Pointer: mouse.click(), move(), down(), up(), wheel()
• Keyboard: keyboard.down(), up(), press(), type(), insertText(), paste()
• Page code and protocols: evaluate(fnOrString, argument), fetch(url, options), cdp(method, params, options)

page.evaluate() callbacks run only inside the Page; they cannot read variables or Node.js modules from the surrounding script. Define browser-side helpers inside the callback or pass one JSON-serializable value as its second argument.

Work efficiently:

• Each time you observe, collect only the cheapest page state sufficient to choose the next action. Use a snapshot for semantic or locator ground truth and a screenshot for visual confirmation; do not request both by default.
• If an action does not produce the expected result, inspect the current page before deciding whether to retry. Do not blindly repeat it or immediately fall back to coordinates or raw CDP.
• Once the page clearly shows the requested result, stop; do not confirm the same result through multiple surfaces.

Semantic pages: snapshot and selectors

Prefer snapshots and semantic selectors for ordinary DOM pages. Use screenshots and coordinates only when useful DOM semantics are unavailable.

Before choosing an unfamiliar target, take a snapshot. When the current state is sufficient to plan several actions on the same Page, complete them in one script invocation, then observe the result once. Observe between actions only when an intermediate result changes what should happen next. Keep the action sequence, the wait for its final expected state, and the next snapshot in the same script invocation. Print the snapshot last so the next round can act on it directly. The final snapshot is the next round's starting view of the changed page; without it, that round usually has to spend a separate browser call observing before it can choose the next target, which wastes compute.

Wait for the expected result: use waitForURL() for navigation, waitForSelector() for element state, or waitForFunction() for application state. Avoid fixed delays when an observable condition exists. A snapshot captures the current moment; it does not wait for the page to become stable. page.snapshot() captures the current viewport. For content outside it, use page.snapshot({ scope: "full_page" }).

The default viewport snapshot includes visible iframe content returned by the browser. To focus on a frame's subtree, reuse the ref printed on its iframe line:

console.log(await page.snapshot({ scope: "subtree", root: "@12" }));

Use the refs returned by the subtree for actions inside the iframe. A subtree snapshot does not scope later locator actions; they still prefer actionable matches in the top document before searching frames.

waitForLoadState() defaults to load. waitForFunction() follows the Playwright argument order; pass undefined before options when there is no Page argument:

await page.waitForFunction(() => window.appReady, undefined, {
  timeout: 10_000,
});

// Round 1: inspect and choose targets from this output.
const page = task.page("p1");
console.log(await page.snapshot());

// Next round: act using the previous output, verify, then prepare the next round.
const page = task.page("p1");
await page.fill("@21", "user@example.com");
await page.click("loc=role:button[name='Sign in']");
await page.waitForSelector("loc=css:#account-home", { state: "visible" });
console.log(await page.snapshot());

Element actions accept:

• snapshot refs such as @21 or ref=21
• text=... for page content
• loc=css:, loc=role:, and loc=href: locators
• xpath=...
• raw CSS selectors

Selector actions require exactly one match. Unquoted text normalizes whitespace, ignores case, and matches a substring; quoted text such as text="Save changes" is exact and case-sensitive.

A small Playwright-compatible selector subset is also accepted: css=..., terminal :has-text("...") and :text-is("..."), >> nth=N after a CSS, text, or href selector (N is -1 or non-negative), plus loc=role:...[name*="..."] for accessible-name substrings. Other Playwright selector syntax is not supported.

When a selector identifies a wrapper, focus() and press() may use its interactive ancestor or unique editable descendant; fill() and setInputFiles() only continue to a unique compatible control.

click(), fill(), hover(), and dragAndDrop() automatically bring their target into view with browser wheel input. Do not pre-scroll solely to make a DOM target actionable.

Snapshot node names are accessibility roles. Use a ref now or loc=... to find the element again. After the page changes, take a new snapshot. When a useful node has no ref, construct a selector from its role, text, or surrounding context. CSS searches nested open shadow roots. Actions use an actionable match in the top document first, then search frames when the top document has none. Multiple actionable matches in the selected document or frame are ambiguous.

Select options by value, visible label, or zero-based index. A string matches either value or label; pass an array for a multiple select:

await page.selectOption("select[name=month]", { label: "October" });

Pass null or [] to clear the current selection.