brianlovin/agent-config

Bash(npx agent-browser:*), Bash(agent-browser:*)

agent-browser open https://example.com/form

# Chain open + wait + snapshot in one call agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i

agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i

# Navigate and capture agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png

agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png

agent-browser --auto-connect state save ./auth.json # Use that auth state agent-browser --state ./auth.json open https://app.example.com/dashboard

agent-browser --state ./auth.json open https://app.example.com/dashboard

# First run: login manually or via automation agent-browser --profile ~/.myapp open https://app.example.com/login

agent-browser --profile ~/.myapp open https://app.example.com/login

# All future runs: already authenticated agent-browser --profile ~/.myapp open https://app.example.com/dashboard

agent-browser --profile ~/.myapp open https://app.example.com/dashboard

agent-browser --session-name myapp open https://app.example.com/login

# Next time: state auto-restored agent-browser --session-name myapp open https://app.example.com/dashboard

agent-browser --session-name myapp open https://app.example.com/dashboard

echo "$PASSWORD" | agent-browser auth save myapp --url https://app.example.com/login --username user --password-stdin

# In a future session: agent-browser state load ./auth.json agent-browser open https://app.example.com/dashboard

agent-browser open https://app.example.com/dashboard

agent-browser open https://example.com/signup

# Save credentials once (encrypted with AGENT_BROWSER_ENCRYPTION_KEY) # Recommended: pipe password via stdin to avoid shell history exposure echo "pass" | agent-browser auth save github --url https://github.com/login --username user --passw

echo "pass" | agent-browser auth save github --url https://github.com/login --username user --password-stdin

# Login once and save state agent-browser open https://app.example.com/login

agent-browser open https://app.example.com/login

# Reuse in future sessions agent-browser state load auth.json agent-browser open https://app.example.com/dashboard

agent-browser open https://app.example.com/dashboard

[Credential-related source omitted]

[Credential-related source omitted]

agent-browser --session-name myapp open https://app.example.com/login

# Next time, state is auto-loaded agent-browser --session-name myapp open https://app.example.com/dashboard

agent-browser --session-name myapp open https://app.example.com/dashboard

# Encrypt state at rest export AGENT_BROWSER_ENCRYPTION_KEY=$(openssl rand -hex 32) agent-browser --session-name secure open https://app.example.com

[Credential-related source omitted]

agent-browser --session-name secure open https://app.example.com

agent-browser open https://example.com/products

agent-browser --session site1 open https://site-a.com

agent-browser --session site2 open https://site-b.com

# Auto-discover running Chrome with remote debugging enabled agent-browser --auto-connect open https://example.com

agent-browser --auto-connect open https://example.com

# Persistent dark mode via flag (applies to all pages and new tabs) agent-browser --color-scheme dark open https://example.com

agent-browser --color-scheme dark open https://example.com

# Or via environment variable AGENT_BROWSER_COLOR_SCHEME=dark agent-browser open https://example.com

AGENT_BROWSER_COLOR_SCHEME=dark agent-browser open https://example.com

agent-browser --headed open https://example.com

# Launch Safari on a specific device agent-browser -p ios --device "iPhone 16 Pro" open https://example.com

agent-browser -p ios --device "iPhone 16 Pro" open https://example.com

agent-browser snapshot # Output: # --- AGENT_BROWSER_PAGE_CONTENT nonce=<hex> origin=https://example.com ---

# Output: # --- AGENT_BROWSER_PAGE_CONTENT nonce=<hex> origin=https://example.com --- # [accessibility tree]

# --- AGENT_BROWSER_PAGE_CONTENT nonce=<hex> origin=https://example.com ---

export AGENT_BROWSER_ALLOWED_DOMAINS="example.com,*.example.com" agent-browser open https://example.com        # OK

agent-browser open https://example.com        # OK

agent-browser open https://malicious.com       # Blocked

# Compare staging vs production agent-browser diff url https://staging.example.com https://prod.example.com --screenshot

agent-browser diff url https://staging.example.com https://prod.example.com --screenshot

agent-browser eval 'document.title'

agent-browser eval 'document.querySelectorAll("img").length'

- Single-line, no nested quotes -> regular `eval 'expression'` with single quotes is fine

{   "headed": true,   "proxy": "http://localhost:8080",

"headed": true,   "proxy": "http://localhost:8080",   "profile": "./browser-data"

"proxy": "http://localhost:8080",

Lightpanda does not support `--extension`, `--profile`, `--state`, or `--allow-file-access`. Install Lightpanda from https://lightpanda.io/docs/open-source/installation.

./templates/form-automation.sh https://example.com/form

./templates/authenticated-session.sh https://app.example.com/login

./templates/capture-workflow.sh https://example.com ./output

Tell user to open: - `https://console.cloud.google.com/apis/library/chromewebstore.googleapis.com`

- `https://console.cloud.google.com/apis/library/chromewebstore.googleapis.com`

Tell user to open one of: - `https://console.cloud.google.com/apis/credentials/consent`

- `https://console.cloud.google.com/apis/credentials/consent`

Tell user to open: - `https://console.cloud.google.com/apis/credentials`

- `https://console.cloud.google.com/apis/credentials`

2. Choose application type `Web application`. 3. Add authorized redirect URI exactly: - `https://developers.google.com/oauthplayground`

3. Add authorized redirect URI exactly: - `https://developers.google.com/oauthplayground` 4. Create client.

- `https://developers.google.com/oauthplayground`

[Credential-related source omitted]

[Credential-related source omitted]

Tell user to open: - `https://developers.google.com/oauthplayground/`

- `https://developers.google.com/oauthplayground/`

[Credential-related source omitted]

[Credential-related source omitted]

4. In Step 1, enter scope: - `https://www.googleapis.com/auth/chromewebstore` 5. Click `Authorize APIs`.

- `https://www.googleapis.com/auth/chromewebstore`

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

- `POST https://oauth2.googleapis.com/token` 4. Fetch CWS status: - `GET https://chromewebstore.googleapis.com/v2/publishers/<publisherId>/items/<extensionId>:fetchStatus`

4. Fetch CWS status: - `GET https://chromewebstore.googleapis.com/v2/publishers/<publisherId>/items/<extensionId>:fetchStatus` 5. Extract current published version from:

- `GET https://chromewebstore.googleapis.com/v2/publishers/<publisherId>/items/<extensionId>:fetchStatus`

- build package zip - upload zip:   `POST https://chromewebstore.googleapis.com/upload/v2/publishers/<publisherId>/items/<extensionId>:upload`

- upload zip:   `POST https://chromewebstore.googleapis.com/upload/v2/publishers/<publisherId>/items/<extensionId>:upload` - handle async upload state with polling when needed

`POST https://chromewebstore.googleapis.com/upload/v2/publishers/<publisherId>/items/<extensionId>:upload`

- handle async upload state with polling when needed - publish:   `POST https://chromewebstore.googleapis.com/v2/publishers/<publisherId>/items/<extensionId>:publish`

`POST https://chromewebstore.googleapis.com/v2/publishers/<publisherId>/items/<extensionId>:publish`

- Chrome Web Store API overview: `https://developer.chrome.com/docs/webstore/using-api`

`https://developer.chrome.com/docs/webstore/using-api`

- Publish endpoint: `https://developer.chrome.com/docs/webstore/publish` - OAuth Playground:

`https://developer.chrome.com/docs/webstore/publish`

- OAuth Playground: `https://developers.google.com/oauthplayground/` - API enablement page:

`https://developers.google.com/oauthplayground/`

- API enablement page: `https://console.cloud.google.com/apis/library/chromewebstore.googleapis.com` - Credentials page:

`https://console.cloud.google.com/apis/library/chromewebstore.googleapis.com`

`https://console.cloud.google.com/apis/credentials`

import { mkdir, rm } from "fs/promises";

force: boolean = false ): Promise<void> {   const url = `https://github.com/oven-sh/bun/releases/download/bun-v${BUN_VERSION}/${file}`;

): Promise<void> {   const url = `https://github.com/oven-sh/bun/releases/download/bun-v${BUN_VERSION}/${file}`;   const outDir = path.join(RESOURCES_DIR, `${platform}-${arch}`);

const url = `https://github.com/oven-sh/bun/releases/download/bun-v${BUN_VERSION}/${file}`;

const response = await fetch(url);

"dev": "concurrently \"npm run dev:web\" \"npm run dev:electron\"",     "dev:web": "cd .. && bun run dev",     "dev:electron": "wait-on http://localhost:3005 && npm run build && ELECTRON_DEV_URL=http://localhost:3005 electron .",

"dev:web": "cd .. && bun run dev",     "dev:electron": "wait-on http://localhost:3005 && npm run build && ELECTRON_DEV_URL=http://localhost:3005 electron .",     "build": "tsc -p tsconfig.main.json && tsc -p tsconfig.preload.json",

"dev:electron": "wait-on http://localhost:3005 && npm run build && ELECTRON_DEV_URL=http://localhost:3005 electron .",

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

rm certificate.p12

[Credential-related source omitted]

[Credential-related source omitted]

rm -rf icon.iconset

): Promise<void> {   const start = Date.now();   const url = `http://localhost:${port}`;

const url = `http://localhost:${port}`;

while (Date.now() - start < timeout) {     try {       const response = await fetch(url);

try {       const response = await fetch(url);       if (response.ok) {

const response = await fetch(url);

// Prevent navigation away from the app   mainWindow.webContents.on("will-navigate", (event, url) => {     const serverUrl = `http://localhost:${port}`;

mainWindow.webContents.on("will-navigate", (event, url) => {     const serverUrl = `http://localhost:${port}`;     if (!url.startsWith(serverUrl)) {

const serverUrl = `http://localhost:${port}`;

mainWindow.loadURL(`http://localhost:${port}`);

"dev": "concurrently \"npm run dev:web\" \"npm run dev:electron\"",     "dev:web": "cd .. && bun run dev",     "dev:electron": "wait-on http://localhost:3005 && npm run build && ELECTRON_DEV_URL=http://localhost:3005 electron ."

"dev:web": "cd .. && bun run dev",     "dev:electron": "wait-on http://localhost:3005 && npm run build && ELECTRON_DEV_URL=http://localhost:3005 electron ."   }

"dev:electron": "wait-on http://localhost:3005 && npm run build && ELECTRON_DEV_URL=http://localhost:3005 electron ."

TypeError: Expected fetch() to be a function

Failed to load URL: http://localhost:3000/login with error: ERR_CONNECTION_REFUSED

export const URLS = {   PRODUCTION: "https://www.yourapp.com",

PRODUCTION: "https://www.yourapp.com",

DEVELOPMENT: "http://localhost:3010", // Must match web app's dev port

"dev": "concurrently \"npm run dev:web\" \"npm run dev:electron\"",     "dev:web": "cd .. && bun run dev",     "dev:electron": "wait-on http://localhost:3005 && npm run build && ELECTRON_DEV_URL=http://localhost:3005 electron .",

"dev:web": "cd .. && bun run dev",     "dev:electron": "wait-on http://localhost:3005 && npm run build && ELECTRON_DEV_URL=http://localhost:3005 electron .",     "build": "tsc -p tsconfig.main.json && esbuild src/preload/index.ts --bundle -

"dev:electron": "wait-on http://localhost:3005 && npm run build && ELECTRON_DEV_URL=http://localhost:3005 electron .",

<?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN"   "http://www.apple.com/DTDs/PropertyList-1.0.dtd">

<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN"   "http://www.apple.com/DTDs/PropertyList-1.0.dtd"> <plist version="1.0">

"http://www.apple.com/DTDs/PropertyList-1.0.dtd">

The Electron main process spawns a bundled Bun binary that runs your server, then loads `http://localhost:{port}` in a `BrowserWindow`. Your web app doesn't know or care that it's inside Electron — it's just a web page with an optional `win

│   ├── dev:web    → cd .. && bun run dev          (Bun dev server with HMR)   │   └── dev:electron   │       ├── wait-on http://localhost:3005           (wait for dev server)

│   └── dev:electron   │       ├── wait-on http://localhost:3005           (wait for dev server)   │       ├── npm run build                           (compile TS)

│       ├── wait-on http://localhost:3005           (wait for dev server)

- **Linux**: `sudo apt install imagemagick`

**Browse skills at:** https://skills.sh/

vercel-labs/agent-skills@vercel-react-best-practices └ https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices

└ https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices

Learn more: https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices

5. **Reproduce** — Use actual failing inputs from Sentry. Call the function with exact data. `fetch()` the URLs that timed out. Verify your understanding.

Full documentation is available here: https://playwriter.dev/

- **Security**: hardcoded secrets in client bundle, eval()

async function fetchData(id) {   return Sentry.startSpan(     { op: "http.client", name: `GET /api/items/${id}` },

return Sentry.startSpan(     { op: "http.client", name: `GET /api/items/${id}` },     async () => {

{ op: "http.client", name: `GET /api/items/${id}` },     async () => {       const response = await fetch(`/api/items/${id}`);

async () => {       const response = await fetch(`/api/items/${id}`);       return response.json();

const response = await fetch(`/api/items/${id}`);

2. **Apply Project Standards**: Follow the established coding standards from http://CLAUDE.md including:

Apache License                            Version 2.0, January 2004                         http://www.apache.org/licenses/

http://www.apache.org/licenses/

http://www.apache.org/licenses/LICENSE-2.0

#!/usr/bin/env python3

#!/usr/bin/env python3

#!/usr/bin/env python3

[Credential-related source omitted]

// GOOD: Each function is independently mockable const api = {   getUser: (id) => fetch(`/users/${id}`),

const api = {   getUser: (id) => fetch(`/users/${id}`),   getOrders: (userId) => fetch(`/users/${userId}/orders`),

getUser: (id) => fetch(`/users/${id}`),

getOrders: (userId) => fetch(`/users/${userId}/orders`),

createOrder: (data) => fetch('/orders', { method: 'POST', body: data }),

// BAD: Mocking requires conditional logic inside the mock const api = {   fetch: (endpoint, options) => fetch(endpoint, options),

const api = {   fetch: (endpoint, options) => fetch(endpoint, options), };

fetch: (endpoint, options) => fetch(endpoint, options),