DOMShell

Iterate over command output lines. Runs a source command, splits output into lines, and for each line replaces {} in the action template and executes it. Capped at 50 items and 120 seconds. Separator is ' : ' (space-colon-space) to avoid conflicts with URL colons. Examples: for "find --type heading -n 3" : text {} for "eval [...urls].join('\\n')" : open {}

Navigate forward in browser history. Only works after a 'back' command. Automatically refreshes the AX tree after navigation.

List callable global JavaScript functions on the current page. Shows function name, arity (parameter count), and parameter names. Useful for discovering page APIs (e.g. MediaWiki's mw.config.get on Wikipedia). Examples: functions All non-standard window functions functions mw Functions matching 'mw' functions --json Machine-parseable output

Search for elements matching a pattern. Matches against name, role, and value. Case-insensitive. By default, searches only IMMEDIATE children. Use recursive: true to search all descendants — this is almost always what you want for finding sections or elements by name. grep is the primary section-discovery tool. Its output gives you element names and paths that you then use with cd, text, find, and other commands. This is how you chain commands together efficiently. Common patterns: grep 'see_also' (recursive: true) Find a section by name anywhere below grep 'heading' (recursive: tr…

Jump to the active tab in the last focused Chrome window. Use this to quickly enter whichever tab the user is currently looking at, without needing to know the tab ID.

Execute arbitrary JavaScript in the current tab and return the result. Use this for complex DOM queries, CSS selector extraction, or any operation that would take multiple DOMShell commands. The code runs in the page context with full DOM access. Promises are automatically awaited. Results are JSON-serialized (truncated at 10000 chars). Common patterns: js document.title js document.querySelectorAll('a').length js [...document.querySelectorAll('.comment')].map(c => ({user: c.querySelector('.user').textContent, text: c.querySelector('.comment-text').textContent})) js document.querySel…

List children of the current directory. In the DOM tree: shows elements as files and directories. At the browser level (~): shows tabs/windows. Flags: -l Long format (more detail per element) --meta Show DOM properties (href, src, id) inline — great for extracting links --text Show visible text preview per element -r Recursive listing -n N Limit to N results --offset N Skip first N children (pagination) --type ROLE Filter by AX role (link, heading, button, etc.) --count Just count children --textlen N …

Navigate the current tab to a URL. Automatically rebuilds the accessibility tree after navigation completes. Requires a tab context (cd into a tab first). Use this to go to a specific website without opening a new tab.

Open a URL in a new tab and enter it (path becomes ~/tabs/<id>). Automatically builds the accessibility tree after page loads. Works from any location. After opening a page, a typical extraction workflow is: 1. open URL 2. find the section you need (find --type heading, or grep section_name with recursive: true) 3. cd into the container 4. text (for content) or find --type link --meta (for links)

Print the current working directory path in the DOM tree.

Structured subtree extraction — returns the hierarchy of elements under the current directory or a named child, with roles, names, and values in one call. Think of it as 'tree' + 'cat' combined: you get the structure AND the content. Excellent for tables, lists, and nested sections. A single read on a table returns all rows and cells with their roles and values, replacing N separate text calls. Flags: --meta Include DOM properties (href, src, id) per element --text Include visible text preview per element -d N Max depth to traverse (default 5) -n N Max total eleme…

Force re-fetch the Accessibility Tree. Use after page navigation or significant DOM changes. Note: the tree also auto-refreshes when changes are detected.

Capture a PNG screenshot of the current tab. Returns the image for visual inspection. Useful for understanding page layout on unfamiliar sites — one screenshot can replace multiple exploration calls (tree, ls, find) by showing you exactly what the page looks like.

Save and run multi-command scripts. Scripts persist across service worker restarts. Subcommands: script list List saved scripts script save <name> cmd1 ; cmd2 Save commands (separated by ' ; ') script show <name> Show commands in a script script run <name> [args...] Execute with $1, $2 variable substitution script delete <name> Delete a script IMPORTANT: Multi-word arguments for 'script run' MUST be quoted with double quotes: script run search "Artificial intelligence" (correct: $1 = Artificial intelligence) script run search Arti…

Scroll the page or scroll a specific element into view. Use this when content is below the fold or when you need to reach elements not currently visible. Modes: scroll down [N] Scroll page down by N viewport heights (default: 1) scroll up [N] Scroll page up by N viewport heights (default: 1) scroll element_name Scroll a specific element into the center of the viewport Returns current scroll position as percentage. Use after scrolling to verify position. Common patterns: scroll down → ls --text (see what's now visible) scroll heading_name (jump to a section) find --t…

Select an option from a <select> dropdown element. Matches by option value first, then by visible text (case-insensitive). Dispatches change and input events to trigger form updates. Examples: select language_dropdown en select country_select United States

Atomic form submission — focuses input, clears existing value, types new value, then submits (clicks button or presses Enter). Replaces the 3-step focus → type → click pattern in one reliable call. Examples: submit search_input 'machine learning' Type and press Enter submit search_input 'machine learning' --submit search_btn Type and click button

List all open browser tabs with their IDs, titles, URLs, and window info. Use this to find the right tab before switching. Equivalent to 'ls ~/tabs/'.

Extract ALL text content from the current directory or a named child, including every descendant. Returns full textContent in a single call. The name parameter lets you read any child without cd'ing into it first: text paragraph_2994 Read a paragraph's text without cd'ing into it text table_1234 Read an ENTIRE table (all rows, all cells) in one call text list_5678 Read all list items at once text Read everything under current directory Efficiency tip: call text on the HIGHEST container that has the content you need. - Need a table? text o…

Show a tree view of the current directory in the DOM, displaying the hierarchy of elements with type prefixes [d]=directory, [x]=interactive, [-]=static.

Type text into the currently focused element. Use domshell_focus first to target an input field. For search forms: after typing, you may need to either: 1. click the submit/search button, OR 2. type '\n' to simulate pressing Enter If the page doesn't navigate after form submission, use domshell_navigate as a fallback to go to the expected URL directly.

Wait for an element to appear in the AX tree. Polls the tree every 500ms until the element is found or timeout is reached. Use after clicks or navigation that trigger async content loading (SPAs, AJAX). Examples: wait results_list Wait for search results wait submit_btn --type button Wait for a button to appear wait loading_spinner --timeout 10 Wait up to 10 seconds

Re-run a command periodically and collect results. Useful for monitoring dynamic content changes within a single tool call instead of making N separate calls. Options: --interval N Seconds between runs (default: 2, min: 0.5) --times N Number of iterations (default: 5, max: 100) --until-change Stop early when output differs from previous iteration Total runtime capped at 120 seconds. Examples: watch ls --times 3 --interval 1 watch "eval document.title" --until-change --interval 1

Check authentication status by examining cookies for the current page. Shows session cookies and expiry.