agent-browser

agent-browser is a skill for Claude Code from majiayu000/claude-skill-registry. It costs 108 tokens per session (1,498 once invoked), scanned A, original, MIT.

A command-line browser control skill for AI agents. It lets an agent inspect web pages and interact with their controls.

In plain words
What is it for?
Use it to open websites, fill in forms, click buttons, take screenshots, extract page data, and test web applications.
Why use it?
It removes the need to manually perform repetitive browser steps or guess whether an action succeeded.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to open websites, fill in forms, click buttons, take screenshots, extract page data, and test web applications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-browser-avibebuilder-claude-prime
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.

Any agent
npx skills add majiayu000/claude-skill-registry --skill agent-browser-avibebuilder-claude-prime
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-browser-avibebuilder-claude-prime/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-browser-avibebuilder-claude-prime)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-browser-avibebuilder-claude-prime"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-browser-avibebuilder-claude-prime/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-browser

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-browser-avibebuilder-claude-prime"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-browser-avibebuilder-claude-prime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,498 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 4
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 13
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Excessive Agency · line 105
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 5.1 $0.00108 $0.01498
Opus 5 $0.00054 $0.00749
Sonnet 5 $0.00022 $0.00300
Haiku 4.5 $0.00011 $0.00150

Measured 9d ago against content hash 2960e0e9fa2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/agent/agent-browser-avibebuilder-claude-prime/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with agent-browser

Use this skill to drive websites through the agent-browser CLI. Keep the main loop tight: inspect the page, act with refs, verify the result, and only pull deeper docs when the task actually needs them.

Core workflow

Prefer agent-browser directly for speed. Use npx agent-browser only if it is not installed globally.

For most tasks, follow this loop:

  1. Open the page
  2. Wait for the relevant state
  3. Snapshot with refs
  4. Interact using those refs
  5. Re-snapshot after page or DOM changes
  6. Verify the outcome
  7. Close the session when done
agent-browser open https://example.com/form
agent-browser wait --load networkidle
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"

agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i

Chain commands with && only when you do not need to inspect intermediate output. Good: open && wait && screenshot. Bad: snapshot && click when you still need to read the refs from the snapshot.

Route fast

Read only the reference that matches the task:

Need Read
Full command or flag lookup references/commands.md
Ref lifecycle, stale refs, snapshot strategy references/snapshot-refs.md
Login flows, OAuth, 2FA, saved auth state references/authentication.md
Parallel sessions, state reuse, cleanup references/session-management.md
Recording, profiling, local files, config, iOS, security references/advanced-usage.md
Proxy setup references/proxy-support.md
Recording workflows references/video-recording.md
Profiling workflows references/profiling.md

Read the full file on GitHub · 138 lines

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. 9d ago First seen · 138 lines · 108 tokens per session scan A 2960e0e9fa2a

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository majiayu000/claude-skill-registry (604 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 1,498 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

ui-test-cypress

Use this skill when you need to design Cypress e2e and component testing plans with commands, fixtures, network stubbing, and CI reporting; triggers include Cypress UI testing, UI automation testing, and ui-test-cypress.

naodeng/awesome-qa-skills · 50 tokens

ui-test-playwright

Use this skill when you need to design Playwright Test suites with fixtures, projects, traces, screenshots, API plus UI coverage, and CI reporting; triggers include Playwright UI testing, UI automation testing, and ui-test-playwright.

naodeng/awesome-qa-skills · 52 tokens

ui-test-puppeteer

Use this skill when you need to design Puppeteer automation for Chromium-driven checks, screenshots, PDFs, network interception, and CDP use cases; triggers include Puppeteer UI testing, UI automation testing, and ui-test-puppeteer.

naodeng/awesome-qa-skills · 53 tokens

ui-test-selenium

Use this skill when you need to design Selenium WebDriver UI automation plans with stable locators, waits, Page Objects, Grid, and CI execution; triggers include Selenium UI testing, UI automation testing, and ui-test-selenium.

naodeng/awesome-qa-skills · 51 tokens

ui-test-testcafe

Use this skill when you need to design TestCafe UI automation with fixtures, selectors, roles, browser matrix execution, and reports; triggers include TestCafe UI testing, UI automation testing, and ui-test-testcafe.

naodeng/awesome-qa-skills · 50 tokens

ui-test-webdriverio

Use this skill when you need to design WebdriverIO suites with config, services, runner behavior, Page Objects, capabilities, and reporters; triggers include WebdriverIO UI testing, UI automation testing, and ui-test-webdriverio.

naodeng/awesome-qa-skills · 53 tokens