browser

Lume Browser

Use this skill for ordinary live web navigation and interaction. The Browser runtime is built into Lume and defaults to the shared persistent iab profile, so logins and site storage survive Lume restarts while tab control remains scoped to the current task. Use external Chrome only when the user explicitly requests Chrome or needs its current Chrome tabs, profile, or extensions.

Treat connection setup as internal. Do not mention Browser Broker or runtime plumbing in user-facing updates unless the user asks about the implementation.

Primary control loop: observe → act → observe

The mcp__browser__* tools are available for the whole user request. Never write browser JavaScript for ordinary interaction.

1. Start with mcp__browser__list_tabs to reuse the task's locked tab, or mcp__browser__open (url) when no suitable tab exists.
2. Call mcp__browser__snapshot before interacting. Interactive nodes carry refs such as [ref=e12].
3. Act by ref: mcp__browser__click / double_click / hover / fill / type / press / select / check / scroll with ref: "@e12".
4. Every mutation tool returns a fresh interactive snapshot of the post-action page. Read it before the next action, and use only refs from the newest snapshot.

Large or dense pages: follow the snapshot's next_cursor by passing it as the cursor argument until the tree is exhausted; drill into one subtree with scope_ref; request interactive_only: true first when you only need actionable controls. mcp__browser__screenshot with annotated: true labels visible elements with the same refs for visual inspection — screenshots are never interaction targets.

Tab semantics

The session locks one active tab. open creates a new Agent-owned tab and locks it; switch_tab is the only way to move between Agent-owned tabs. A click that opens a new tab does not switch the lock — call list_tabs, then switch_tab. Navigation on the locked tab uses navigate / back / forward / reload.