What is cursor-browser?

A skill for controlling Cursor IDE's built-in Browser Tab. Cursor is a code editor, and the Browser Tab lets you interact with web pages inside the editor.

Use it to navigate pages, click, type, fill forms, scroll, choose options, wait for changes, take screenshots, and inspect browser output.

It lets you test and operate web interfaces from the same Cursor project, including taking snapshots and checking console or network activity.

cursor-browser — Skill by bcharleson

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/bcharleson/cursor-browser-cli/skill

Any agent

npx skills add bcharleson/cursor-browser-cli --skill skill

Clone the repo

git clone --depth 1 https://github.com/bcharleson/cursor-browser-cli

Made for: Claude Code, Codex.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,646 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00083	$0.01646
Opus 5	$0.00042	$0.00823
Sonnet 5	$0.00017	$0.00329
Haiku 4.5	$0.00008	$0.00165

Measured yesterday against content hash 17e89bf7886c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-browser scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cursor-browser-cli

Control Cursor’s Browser Tab in the matching project window.

This skill is only for the in-IDE Browser Tab. It does not drive an external desktop browser product. Other browser tools (if installed on the machine) are separate and independent — use those when you need a full browser profile, existing cookie sessions, or non-Cursor windows. Prefer this tool for day-to-day app UI work inside Cursor (local servers, fast ref loops, same tab as the IDE).

Install via npm install -g cursor-browser-cli, or clone this repo and run npm install.

Always pin the project first (required multi-window)

Each Cursor project has its own bridge on its own port. Never open a tab until you know which project/port you are targeting.

# 1) What bridges are live? (project → port)
cursor-browser windows

# 2) What project is THIS cwd / workspace?
cursor-browser pin
# or:
cursor-browser --workspace <project-folder> pin

# 3) Pin for the rest of the shell session
eval $(cursor-browser pin --export)
# sets CURSOR_BROWSER_WORKSPACE + CURSOR_BROWSER_CLI_PORT

Or pass every time:

cursor-browser --workspace <project-folder> whoami
cursor-browser --workspace <project-folder> open http://localhost:3000

Prefer --workspace <name> over raw port. Ports can change after recover / Restart Server; the project name stays stable.

Multi-project days: always pass --workspace (or pin via eval $(… pin --export)).

Agent loop (preferred)

# 0) Discover + pin (once per session / project)
cursor-browser windows
cursor-browser pin
eval $(cursor-browser pin --export)
# confirm:
cursor-browser whoami

# 1) Single tab + navigate → ref snapshot printed as text
cursor-browser open http://localhost:3000
# or
cursor-browser nav http://localhost:3000

# 2) Read refs from snapshot output (e1, e5, …)

# 3) Interact by ref
cursor-browser click e5
cursor-browser fill e3 "value"
cursor-browser type e3 "more"
cursor-browser hover e2
cursor-browser press Enter
cursor-browser scroll --y 600
cursor-browser select-option e7 "option-value"

# Optional: fresh refs after same-page interact
cursor-browser fill e3 "x" --snap
# After a navigation click, prefer wait + snapshot (most reliable)
cursor-browser click e5 --wait-nav --timeout 15000
cursor-browser snapshot
# --snap on a nav click also works (CLI falls back if needed) but is slower

# 4) Wait for state (avoid races)
cursor-browser wait --url /dashboard --timeout 15000
cursor-browser wait --text "Welcome"
cursor-browser wait --ref e12

# 5) Lock while automating (optional)
cursor-browser lock
# ... actions ...
cursor-browser unlock

Read the full file on GitHub · 176 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 176 lines · 83 tokens per session scan A 17e89bf7886c

Subscribe to this mod's changes

cursor-browser is a skill published in the GitHub repository bcharleson/cursor-browser-cli (1 stars, last pushed 20d ago), licensed MIT. It adds 83 tokens to every session and 1,646 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

cursor-browser