agent-browser

Browser-control tools for navigating web pages, inspecting their accessible structure, finding elements, reading content, and interacting with controls. They can also run JavaScript in the page and capture screenshots or PDFs.

In plain words
What is it for?
Use them to open pages, click or fill controls, wait for page changes, extract information, run page-level checks, and save visual captures.
Why use it?
They let a coding agent work with websites and inspect what is actually displayed instead of guessing from source code alone.

Skill for Claude CodeCodex

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/rodaddy/mcp2cli/agent-browser
Any agent
npx skills add rodaddy/mcp2cli --skill agent-browser
Clone the repo
git clone --depth 1 https://github.com/rodaddy/mcp2cli

Made for: Claude Code, Codex.

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 283 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.

ModelPer sessionOnce invoked
Fable 5 $0.00009 $0.00283
Opus 5 $0.00005 $0.00142
Sonnet 5 $0.00002 $0.00057
Haiku 4.5 $0.00001 $0.00028

Measured 2d ago against content hash 4f7a2d87ff5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 2d ago.

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.

examples/skills/agent-browser/SKILL.md · 43 lines

What it actually says

agent-browser

MCP tools for agent-browser

Quick Reference

Tool Description
browser_eval Execute arbitrary JavaScript in the browser page context and return the result.
browser_find Find elements using semantic queries -- by ARIA role, visible text, label, place...
browser_get Extract data from the page or elements.
browser_interact Interact with page elements by ref or selector.
browser_navigate Navigate the browser: open a URL, go back/forward, reload, or close the browser.
browser_screenshot Capture the current page as a screenshot (PNG) or PDF.
browser_snapshot Get the current page accessibility tree with element refs.
browser_wait Wait for a condition: element to appear, time to pass, URL to match, or text to ...

Usage

mcp2cli agent-browser <tool> --params '{...}'

See references/ for detailed parameter docs per tool.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 43 lines · 9 tokens per session scan A 4f7a2d87ff5a

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository rodaddy/mcp2cli (8 stars, last pushed 10d ago), licensed MIT. It adds 9 tokens to every session and 283 once invoked, about $0.0000 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.