Drive an authentication flow once, sanitize cookies through AIDefence, and vault a reusable cookie handle in browser-cookies for future sessions
Install
npx skills add https://github.com/ruvnet/ruflo --skill browser-loginSKILL.md
Browser Login
Authenticate against a target site once, then vault the resulting session credentials so subsequent skills (browser-extract, browser-form-fill, browser-test) can reuse them without re-driving the auth flow. Borrows the pattern from Browserbase's cookie-sync/SKILL.md but stores the resulting context in AgentDB rather than on a hosted backend.
When to use
- Establishing reusable auth for a host the agent will visit repeatedly.
- Refreshing a vaulted cookie set whose expiry has passed.
- Capturing an MFA-protected session that requires interactive completion.
Steps
- Open a recorded session via
browser-record. - Drive the auth flow — fill credentials with
browser_fill/browser_type. Credentials come from the user or environment; do not read them from.envor paste them into the trajectory args. - Handle MFA (when
--mfa): pause for user input or invoke the user's TOTP helper; capture only the resulting redirect, not the code itself. - Capture cookies via
browser_eval:
Or use the Playwright context API where exposed.document.cookie // returns the cookie string for the active document - AIDefence sanitize:
Tokens that look raw get vault-wrapped (an opaque handle) before AgentDB store; raw values never enter the namespace.# Each cookie value passes aidefence_scan to flag raw secrets / high-entropy tokens. - Store in
browser-cookies:npx -y @claude-flow/cli@latest memory store --namespace browser-cookies \ --key "<host>" \ --value "{vault_handle:<opaque>, expiry:<iso>, aidefence_verdict:safe}" - Return the vault handle so downstream skills can mount it via the planned
browser_cookie_useMCP tool.
Caveats
- Never log raw cookie values, tokens, or passwords. The trajectory step for the auth POST records only the form field names and a
<redacted>placeholder for values. - The
browser_cookie_useMCP tool is reserved (ADR-0001 §7) but not yet implemented. Until then, downstream skills mount the vaulted cookies via a helper bash function inscripts/(TBD). - Some sites bind cookies to a UA fingerprint; if a vaulted cookie fails on reuse, re-run
browser-login. Do not attempt to fingerprint-match yourself. - This skill is not a credential storage solution. The vault-handle pattern protects against AgentDB leaks, not against compromise of the agent's environment.
Related skills
agent-browservercel-labs967KBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use fojust-scrapescrapegraphai245KSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON from a site, crawl documentation or site sections, monitor a page for changes, inspect request history, check ScrapeGraph credits, or validate API setup.browser-actbrowser-act108Kagent-browser101-skills104KBrowser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video