agent-browser

agent-browser is a skill for Claude Code, Codex from Kevin-Liu-01/Agent-Machines. It costs 80 tokens per session (1,046 once invoked), scanned A, original, MIT.

A browser automation tool that controls Chrome or Chromium from the command line. It can open pages, inspect interactive elements, enter information, click controls, wait for changes, and capture screenshots.

In plain words
What is it for?
Use it to test web interfaces, fill forms, scrape page content, navigate sites, take screenshots, and check pages after dynamic updates.
Why use it?
It removes repetitive manual browser work and provides a repeatable way to interact with and inspect websites. Persistent sessions allow work to continue without starting over each time.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to test web interfaces, fill forms, scrape page content, navigate sites, take screenshots, and check pages after dynamic updates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kevin-liu-01/agent-machines/agent-browser
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 Kevin-Liu-01/Agent-Machines --skill agent-browser
Clone the repo
git clone --depth 1 https://github.com/Kevin-Liu-01/Agent-Machines

Made for: Claude Code, Codex.

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/kevin-liu-01/agent-machines/agent-browser/github.svg)](https://agentmods.dev/skills/kevin-liu-01/agent-machines/agent-browser)
Your own site
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/agent-browser"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/agent-browser/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/kevin-liu-01/agent-machines/agent-browser"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,046 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 pass 7 Sept 2026
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 $0.00080 $0.01046
Opus 5 $0.00040 $0.00523
Sonnet 5 $0.00016 $0.00209
Haiku 4.5 $0.00008 $0.00105

Measured 10d ago against content hash 5ac3974a079e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

knowledge/skills/agent-browser/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with agent-browser

CLI browser automation via Chrome/Chromium CDP. Install: npm i -g agent-browser. Run agent-browser install to download Chrome.

Core Workflow

  1. Navigate: agent-browser open <url>
  2. Snapshot: agent-browser snapshot -i (get element refs like @e1, @e2)
  3. Interact: Use refs to click, fill, select
  4. Re-snapshot: After navigation or DOM changes, get fresh refs
agent-browser open https://example.com/form
agent-browser snapshot -i
agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait 2000
agent-browser snapshot -i

Batch Execution

ALWAYS use batch for 2+ sequential commands:

agent-browser batch "open https://example.com" "snapshot -i"
agent-browser batch "click @e1" "wait 1000" "screenshot"
agent-browser batch "open https://example.com" "snapshot -i" "screenshot"

Only run a single command when you need to read output before deciding the next step.

Essential Commands

# Navigation
agent-browser open <url>
agent-browser close
agent-browser close --all

# Snapshot (get interactive element refs)
agent-browser snapshot -i
agent-browser snapshot -i --urls         # Include href URLs for links
agent-browser snapshot -s "#selector"    # Scope to CSS selector

# Interaction (use @refs from snapshot)
agent-browser click @e1
agent-browser fill @e2 "text"
agent-browser select @e1 "option"
agent-browser press Enter
agent-browser scroll down 500

# Get information
agent-browser get text @e1
agent-browser get url
agent-browser get title

# Wait
agent-browser wait @e1                  # Wait for element
agent-browser wait 2000                 # Wait milliseconds
agent-browser wait --text "Welcome"     # Wait for text
agent-browser wait --url "**/page"      # Wait for URL pattern

# Capture
agent-browser screenshot
agent-browser screenshot --full         # Full page
agent-browser screenshot --annotate     # With numbered element labels
agent-browser pdf output.pdf

# Diff (verify changes)
agent-browser diff snapshot             # Compare current vs last snapshot
agent-browser diff screenshot --baseline before.png

# Tab management
agent-browser tab list
agent-browser tab new https://example.com
agent-browser tab 2
agent-browser tab close

# Sessions
agent-browser --session site1 open https://site-a.com
agent-browser session list

Read the full file on GitHub · 149 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.

  1. 10d ago First seen · 149 lines · 80 tokens per session scan A 5ac3974a079e

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (27 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,046 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 2026-08-30.

Related

Other skills, from other repositories

hunt-cors

Hunt CORS Misconfiguration — origin-reflection with credentials, null-origin trust, subdomain-regex bypass (unanchored vs unescaped-dot vs prefix-only), pre-flight (OPTIONS) gating bypass, postMessage origin checks. High only when an attacker-controlled origin can perform a CREDENTIALED cross-origin read of sensitive…

uphiago/recon-skills · 99 tokens

hunt-dom

Hunt client-side DOM vulnerabilities — DOM Clobbering (overwrite JS globals via HTML injection), PostMessage hijacking (missing origin check), Service Worker abuse (intercept requests from same-origin script), CSS Injection/Exfiltration (attribute selectors → token char-by-char via OOB), client-side template…

uphiago/recon-skills · 168 tokens

web-enumeration

Sensitive file scanning, path traversal bypass, vHost enum, .env extract, log mining, Varnish detect.

uphiago/recon-skills · 28 tokens

humanize-automation

Human-like mouse, keyboard and scroll behavior for behavioral bot bypass.

uphiago/recon-skills · 18 tokens

stealth-browser-launch

Launch stealth Chromium with C++ fingerprint patches for anti-bot bypass.

uphiago/recon-skills · 19 tokens

codexless-browser-repair

Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…

liyana31811/Codexless · 70 tokens