Core Guide for agent-browser
vercel-labs/agent-browser
Core usage guide for the agent-browser CLI: the snapshot-and-ref workflow for navigating, clicking, filling forms, extracting data and running parallel sessions.
Controls a browser through BrowserWing's local HTTP API: navigation, clicks, typing, data extraction, accessibility snapshots, screenshots and batch operations.
$ npx skills add MemTensor/MemOS --skill browserwing-executor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MemTensor/MemOS browserwing-executor --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/MemTensor/MemOS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/memos-local-openclaw/skill/browserwing-executor .claude/skills/browserwing-executor && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "browserwing-executor" agent skill from https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-openclaw/skill/browserwing-executor into .claude/skills/browserwing-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browserwing-executor", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-openclaw/skill/browserwing-executorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add MemTensor/MemOS --skill browserwing-executor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MemTensor/MemOS browserwing-executor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemTensor/MemOS.git skills-src && mkdir -p .agents/skills && cp -r skills-src/apps/memos-local-openclaw/skill/browserwing-executor .agents/skills/browserwing-executor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "browserwing-executor" agent skill from https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-openclaw/skill/browserwing-executor into .agents/skills/browserwing-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browserwing-executor", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MemTensor/MemOS --skill browserwing-executor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MemTensor/MemOS browserwing-executor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemTensor/MemOS.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/apps/memos-local-openclaw/skill/browserwing-executor .cursor/skills/browserwing-executor && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "browserwing-executor" agent skill from https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-openclaw/skill/browserwing-executor into .cursor/skills/browserwing-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browserwing-executor", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/MemTensor/MemOS.git --path apps/memos-local-openclaw/skill/browserwing-executor--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add MemTensor/MemOS --skill browserwing-executor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MemTensor/MemOS browserwing-executor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemTensor/MemOS.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/apps/memos-local-openclaw/skill/browserwing-executor .gemini/skills/browserwing-executor && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "browserwing-executor" agent skill from https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-openclaw/skill/browserwing-executor into .gemini/skills/browserwing-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browserwing-executor", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install MemTensor/MemOS browserwing-executorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add MemTensor/MemOS --skill browserwing-executor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MemTensor/MemOS.git skills-src && mkdir -p .github/skills && cp -r skills-src/apps/memos-local-openclaw/skill/browserwing-executor .github/skills/browserwing-executor && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "browserwing-executor" agent skill from https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-openclaw/skill/browserwing-executor into .github/skills/browserwing-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browserwing-executor", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MemTensor/MemOS --skill browserwing-executor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MemTensor/MemOS browserwing-executor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemTensor/MemOS.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/apps/memos-local-openclaw/skill/browserwing-executor .opencode/skills/browserwing-executor && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "browserwing-executor" agent skill from https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-openclaw/skill/browserwing-executor into .opencode/skills/browserwing-executor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browserwing-executor", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
browserwing-executorControls a browser through BrowserWing's local HTTP API: navigation, clicks, typing, data extraction, accessibility snapshots, screenshots and batch operations.
The agent talks to a BrowserWing Executor server on localhost, authenticating with an API key header or a bearer token. It is told to call the help endpoint first to see every command and its parameters, and to take an accessibility snapshot after each navigation. The snapshot lists clickable and input elements with stable reference IDs such as @e1, which later calls use as identifiers, and it is described as cleaner for language models than raw DOM.
Core operations are page navigation including back, forward and reload, element interaction such as click, type, select and hover, extracting text, attributes and values, screenshots, JavaScript execution, keyboard input and running several operations in sequence as a batch. The examples are curl calls to endpoints such as navigate and click, each with a small JSON body.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit a7367d0. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
curlFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
BrowserWing Executor API loads about 3.9k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 1,313 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from MemTensor/MemOS at commit a7367d0, republished under its Apache-2.0 licence (© MemTensor). 1,313 words, ~3,907 tokens.
.claude/skills/browserwing-executor/SKILL.md (or your agent's skills folder).BrowserWing Executor provides comprehensive browser automation capabilities through HTTP APIs. You can control browser navigation, interact with page elements, extract data, and analyze page structure.
API Base URL: http://localhost:8080/api/v1/executor
Authentication: Use X-BrowserWing-Key: <api-key> header or Authorization: Bearer <token>
IMPORTANT: Always call this endpoint first to see all available commands and their parameters.
curl -X GET 'http://localhost:8080/api/v1/executor/help'Response: Returns complete list of all commands with parameters, examples, and usage guidelines.
Query specific command:
curl -X GET 'http://localhost:8080/api/v1/executor/help?command=extract'CRITICAL: Always call this after navigation to understand page structure and get element RefIDs.
curl -X GET 'http://localhost:8080/api/v1/executor/snapshot'Response Example:
{
"success": true,
"snapshot_text": "Clickable Elements:\n @e1 Login (role: button)\n @e2 Sign Up (role: link)\n\nInput Elements:\n @e3 Email (role: textbox) [placeholder: your@email.com]\n @e4 Password (role: textbox)"
}Use Cases:
curl -X POST 'http://localhost:8080/api/v1/executor/navigate' \
-H 'Content-Type: application/json' \
-d '{"url": "https://example.com"}'curl -X POST 'http://localhost:8080/api/v1/executor/click' \
-H 'Content-Type: application/json' \
-d '{"identifier": "@e1"}'Identifier formats:
@e1, @e2 (from snapshot)#button-id, .class-name//button[@type='submit']Login (text content)curl -X POST 'http://localhost:8080/api/v1/executor/type' \
-H 'Content-Type: application/json' \
-d '{"identifier": "@e3", "text": "user@example.com"}'curl -X POST 'http://localhost:8080/api/v1/executor/extract' \
-H 'Content-Type: application/json' \
-d '{
"selector": ".product-item",
"fields": ["text", "href"],
"multiple": true
}'curl -X POST 'http://localhost:8080/api/v1/executor/wait' \
-H 'Content-Type: application/json' \
-d '{"identifier": ".loading", "state": "hidden", "timeout": 10}'curl -X POST 'http://localhost:8080/api/v1/executor/batch' \
-H 'Content-Type: application/json' \
-d '{
"operations": [
{"type": "navigate", "params": {"url": "https://example.com"}, "stop_on_error": true},
{"type": "click", "params": {"identifier": "@e1"}, "stop_on_error": true},
{"type": "type", "params": {"identifier": "@e3", "text": "query"}, "stop_on_error": true}
]
}'Step-by-step workflow:
Discover commands: Call GET /help to see all available operations and their parameters (do this first if unsure).
Navigate: Use POST /navigate to open the target webpage.
Analyze page: Call GET /snapshot to understand page structure and get element RefIDs.
Interact: Use element RefIDs (like @e1, @e2) or CSS selectors to:
POST /clickPOST /typePOST /selectPOST /waitExtract data: Use POST /extract to get information from the page.
Present results: Format and show extracted data to the user.
User Request: "Search for 'laptop' on example.com and get the first 5 results"
Your Actions:
curl -X POST 'http://localhost:8080/api/v1/executor/navigate' \
-H 'Content-Type: application/json' \
-d '{"url": "https://example.com/search"}'curl -X GET 'http://localhost:8080/api/v1/executor/snapshot'Response shows: @e3 Search (role: textbox) [placeholder: Search...]
curl -X POST 'http://localhost:8080/api/v1/executor/type' \
-H 'Content-Type: application/json' \
-d '{"identifier": "@e3", "text": "laptop"}'curl -X POST 'http://localhost:8080/api/v1/executor/press-key' \
-H 'Content-Type: application/json' \
-d '{"key": "Enter"}'curl -X POST 'http://localhost:8080/api/v1/executor/wait' \
-H 'Content-Type: application/json' \
-d '{"identifier": ".search-results", "state": "visible", "timeout": 10}'curl -X POST 'http://localhost:8080/api/v1/executor/extract' \
-H 'Content-Type: application/json' \
-d '{
"selector": ".result-item",
"fields": ["text", "href"],
"multiple": true
}'Found 15 results for 'laptop':
1. Gaming Laptop - $1299 (https://...)
2. Business Laptop - $899 (https://...)
...POST /navigate - Navigate to URLPOST /go-back - Go back in historyPOST /go-forward - Go forward in historyPOST /reload - Reload current pagePOST /click - Click element (supports: RefID @e1, CSS selector, XPath, text content)POST /type - Type text into input (supports: RefID @e3, CSS selector, XPath)POST /select - Select dropdown optionPOST /hover - Hover over elementPOST /wait - Wait for element state (visible, hidden, enabled)POST /press-key - Press keyboard key (Enter, Tab, Ctrl+S, etc.)POST /extract - Extract data from elements (supports multiple elements, custom fields)POST /get-text - Get element text contentPOST /get-value - Get input element valueGET /page-info - Get page URL and titleGET /page-text - Get all page textGET /page-content - Get full HTMLGET /snapshot - Get accessibility snapshot (⭐ ALWAYS call after navigation)GET /clickable-elements - Get all clickable elementsGET /input-elements - Get all input elementsPOST /screenshot - Take page screenshot (base64 encoded)POST /evaluate - Execute JavaScript codePOST /batch - Execute multiple operations in sequencePOST /scroll-to-bottom - Scroll to page bottomPOST /resize - Resize browser windowPOST /tabs - Manage browser tabs (list, new, switch, close)POST /fill-form - Intelligently fill multiple form fields at onceGET /console-messages - Get browser console messages (logs, warnings, errors)GET /network-requests - Get network requests made by the pagePOST /handle-dialog - Configure JavaScript dialog (alert, confirm, prompt) handlingPOST /file-upload - Upload files to input elementsPOST /drag - Drag and drop elementsPOST /close-page - Close the current page/tabYou can identify elements using:
RefID (Recommended): @e1, @e2, @e3
/snapshot endpoint"identifier": "@e1"CSS Selector: #id, .class, button[type="submit"]
"identifier": "#login-button"XPath: //button[@id='login'], //a[contains(text(), 'Submit')]
"identifier": "//button[@id='login']"Text Content: Login, Sign Up, Submit
"identifier": "Login"ARIA Label: Elements with aria-label attribute
Before starting:
GET /help if you're unsure about available commands or their parametersDuring automation:
/snapshot after navigation to get page structure and RefIDs@e1) over CSS selectors for reliability and stability/wait for dynamic content that loads asynchronously/batch for multiple sequential operations to improve efficiencyError handling:
/snapshot again to refresh page structureData extraction:
fields parameter to specify what to extract: ["text", "href", "src"]multiple: true to extract from multiple elementsScenario: User wants to login to a website
User: "Please log in to example.com with username 'john' and password 'secret123'"Your Actions:
Step 1: Navigate to login page
POST http://localhost:8080/api/v1/executor/navigate
{"url": "https://example.com/login"}Step 2: Get page structure
GET http://localhost:8080/api/v1/executor/snapshotResponse:
Clickable Elements:
@e1 Login (role: button)
Input Elements:
@e2 Username (role: textbox)
@e3 Password (role: textbox)Step 3: Enter username
POST http://localhost:8080/api/v1/executor/type
{"identifier": "@e2", "text": "john"}Step 4: Enter password
POST http://localhost:8080/api/v1/executor/type
{"identifier": "@e3", "text": "secret123"}Step 5: Click login button
POST http://localhost:8080/api/v1/executor/click
{"identifier": "@e1"}Step 6: Wait for login success (optional)
POST http://localhost:8080/api/v1/executor/wait
{"identifier": ".welcome-message", "state": "visible", "timeout": 10}Step 7: Inform user
"Successfully logged in to example.com!"Scenario: Fill out a form with multiple fields
Instead of making 5 separate API calls, use one batch operation:
curl -X POST 'http://localhost:8080/api/v1/executor/batch' \
-H 'Content-Type: application/json' \
-d '{
"operations": [
{
"type": "navigate",
"params": {"url": "https://example.com/form"},
"stop_on_error": true
},
{
"type": "type",
"params": {"identifier": "#name", "text": "John Doe"},
"stop_on_error": true
},
{
"type": "type",
"params": {"identifier": "#email", "text": "john@example.com"},
"stop_on_error": true
},
{
"type": "select",
"params": {"identifier": "#country", "value": "United States"},
"stop_on_error": true
},
{
"type": "click",
"params": {"identifier": "#submit"},
"stop_on_error": true
}
]
}'/help or /help?command=<name> to learn about commands/snapshot after navigation to understand the page/wait before interacting with elements that load asynchronously/batch for multiple sequential operations/type for each field: @e1, @e2, etc./select for dropdowns/wait/extract with CSS selector and multiple: true["text", "href", "src"]@e2@e3@e1wait_visible: true (default) for reliable element interactionlocalhost:8080 with actual API host addressX-BrowserWing-Key header or JWT tokenElement not found:
/snapshot to see available elementsTimeout errors:
/wait with appropriate state before interactionExtraction returns empty:
/wait first)# Discover commands
GET localhost:8080/api/v1/executor/help
# Navigate
POST localhost:8080/api/v1/executor/navigate {"url": "..."}
# Get page structure
GET localhost:8080/api/v1/executor/snapshot
# Click element
POST localhost:8080/api/v1/executor/click {"identifier": "@e1"}
# Type text
POST localhost:8080/api/v1/executor/type {"identifier": "@e3", "text": "..."}
# Extract data
POST localhost:8080/api/v1/executor/extract {"selector": "...", "fields": [...], "multiple": true}All operations return:
{
"success": true,
"message": "Operation description",
"timestamp": "2026-01-15T10:30:00Z",
"data": {
// Operation-specific data
}
}Error response:
{
"error": "error.operationFailed",
"detail": "Detailed error message"
}© MemTensor, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in apps/memos-local-openclaw/skill/browserwing-executor of MemTensor/MemOS.
Open the folder on GitHubat commit a7367d0
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in MemTensor/MemOS, which our catalogue first saw on October 7, 2026.
BrowserWing Executor API next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| BrowserWing Executor API this skillMemTensor/MemOS | 12k | 2 repos | ~3.9k | Automated safety check: Pass | Apache-2.0 | |
| Core Guide for agent-browservercel-labs/agent-browser | 44k | 4 repos | ~9.5k | Automated safety check: Pass | Apache-2.0 | |
| OpenCLI Browser Controljackwener/OpenCLI | 30k | 2 repos | ~7.3k | Automated safety check: Pass | Apache-2.0 | |
| Cloudflare Browser Renderingcloudflare/moltworker | 9.9k | — | ~742 | Automated safety check: Pass | Apache-2.0 | |
| Browser Control with Omowrightcode-yeongyu/oh-my-openagent | 70k | — | ~2.2k | Automated safety check: Pass | Custom licence | |
| Skyvern Browser AutomationSkyvern-AI/skyvern | 23k | — | ~2.9k | Automated safety check: Pass | AGPL-3.0 |
vercel-labs/agent-browser
Core usage guide for the agent-browser CLI: the snapshot-and-ref workflow for navigating, clicking, filling forms, extracting data and running parallel sessions.
jackwener/OpenCLI
Drives a real Chrome window through the opencli CLI to inspect pages, fill forms, click through logged-in flows and extract data from structured command responses.
cloudflare/moltworker
Drives headless Chrome through Cloudflare Browser Rendering over a CDP WebSocket to take screenshots, navigate and scrape pages, and record multi-page videos.
code-yeongyu/oh-my-openagent
Drives a real browser through the omowright library, either the user's own signed-in browser or a separate browser the code launches, for forms, QA, screenshots and scraping.
Skyvern-AI/skyvern
Picks the right Skyvern CLI command for a web task, from quick yes/no checks to reusable multi-page workflows, instead of falling back to plain page fetching.
nanocoai/nanoclaw
Drives a web browser from the shell with the agent-browser CLI: open pages, read an element snapshot, click and fill by reference, grab text and screenshots.
MemTensor/MemOS
Automates a real browser through short TypeScript scripts that keep page state between runs, for navigating, filling forms, taking screenshots and extracting data.
MemTensor/MemOS
Shows a question as a modal in the interface to clarify a task, collect a preference or get approval, since the user cannot see terminal output.
MemTensor/MemOS
Installs, configures and operates BrowserWing, a browser automation platform, covering Chrome setup, LLM provider configuration, and creating or running automation scripts.
MemTensor/MemOS
Enforces explicit user permission before any file deletion. Activates when you're about to use rm, unlink, fs.rm, or any operation that removes files from…
MemTensor/MemOS
Explains when to call MemOS's own memory tools to search past conversations, after the automatic per-turn recall hook comes up empty.
Categories
Controls a browser through BrowserWing's local HTTP API: navigation, clicks, typing, data extraction, accessibility snapshots, screenshots and batch operations. The agent talks to a BrowserWing Executor server on localhost, authenticating with an API key header or a bearer token. It is told to call the help endpoint first to see every command and its parameters, and to take an accessibility snapshot after each navigation.
BrowserWing Executor API fits situations like: automating a multi-step task in a web page through HTTP calls; extracting text or attributes from specific page elements; understanding a page's interactive elements through an accessibility snapshot; taking screenshots or running JavaScript in a controlled browser session.
Run `npx skills add MemTensor/MemOS --skill browserwing-executor -a claude-code`. Or copy the skill folder (apps/memos-local-openclaw/skill/browserwing-executor in MemTensor/MemOS) into .claude/skills/browserwing-executor in your project. Claude Code loads it when a task matches its description.
Run `npx skills add MemTensor/MemOS --skill browserwing-executor -a codex`. Or copy the skill folder (apps/memos-local-openclaw/skill/browserwing-executor in MemTensor/MemOS) into .agents/skills/browserwing-executor in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MemTensor/MemOS --skill browserwing-executor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/browserwing-executor, .gemini/skills/browserwing-executor, .github/skills/browserwing-executor and .opencode/skills/browserwing-executor in your project.
Going by SKILL.md and its folder, BrowserWing Executor API needs the command-line tools its instructions call (curl). Our summary lists: A running BrowserWing Executor server; An API key or bearer token for its HTTP API.
SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
BrowserWing Executor API is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with BrowserWing Executor API: Core Guide for agent-browser (vercel-labs/agent-browser, 44k stars), OpenCLI Browser Control (jackwener/OpenCLI, 30k stars), Cloudflare Browser Rendering (cloudflare/moltworker, 9.9k stars) and Browser Control with Omowright (code-yeongyu/oh-my-openagent, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
MemTensor (a GitHub organization) maintains it in MemTensor/MemOS, which has 11,738 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on September 29, 2026.
Source: MemTensor/MemOS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.