web-agent

A web-browsing agent that can open sites, interact with pages, fill in forms, handle logins when needed, and extract information.

In plain words
What is it for?
Use it to navigate pages, click controls, submit forms, collect text or tables, work with dynamic sites, and take screenshots.
Why use it?
It removes the need to manually repeat browser tasks across websites and web applications.

Skill for Claude CodeCodex

Part of the web-agent plugin — 1 skill, 1 agent shipped together

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/pilot617/awesome-claude-code-plugins/web-agent
Any agent
npx skills add pilot617/awesome-claude-code-plugins --skill web-agent
Clone the repo
git clone --depth 1 https://github.com/pilot617/awesome-claude-code-plugins

Made for: Claude Code, Codex.

Or install web-agent, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 460 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 $0.00037 $0.00460
Opus 5 $0.00018 $0.00230
Sonnet 5 $0.00007 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 2d ago against content hash 0d3584ce2ca9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-agent 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.

plugins/web-agent/skills/web-agent/SKILL.md · 63 lines

What it actually says

/web-agent — Web Automation Agent

Automate any web task: navigate websites, interact with UI elements, fill forms, extract data, and handle logins — all powered by Playwright.

Usage

/web-agent <task description>
/web-agent --headed <task description>

Examples

/web-agent "Go to github.com/anthropics/claude-code and extract the star count"
/web-agent "Go to news.ycombinator.com and get the top 5 story titles"
/web-agent --headed "Go to my-app.localhost:3000, log in, and check the dashboard"
/web-agent "Go to npmjs.com, search for 'playwright', and extract the weekly downloads"

What It Can Do

  • Navigate to any URL
  • Click buttons, links, tabs, menu items
  • Fill and submit forms
  • Handle login/authentication flows (asks you for credentials when needed)
  • Extract text, tables, and structured data
  • Take screenshots at any step
  • Work with SPAs and dynamic content
  • Emulate different viewports

Prerequisites

  • Python 3.9+
  • Playwright + Chromium: pip install playwright && python -m playwright install chromium

How It Works

The agent delegates to a specialized web-agent subagent that:

  1. Navigates to the target URL
  2. Analyzes the page (interactive elements, text, screenshots)
  3. Performs actions (click, type, select)
  4. Verifies results via screenshots
  5. Iterates until the task is complete
  6. Returns a summary of what was accomplished

Options

Flag Description
--headed Show the browser window so you can watch the agent work

Pass $ARGUMENTS to the subagent as the task description.

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 · 63 lines · 37 tokens per session scan A 0d3584ce2ca9

Subscribe to this mod's changes

web-agent is a skill published in the GitHub repository pilot617/awesome-claude-code-plugins (7 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 460 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

peekaboo

Provides runtime observation and interaction for native macOS interfaces through accessibility state and screenshots. Use when the task depends on visible or interactive state in a running SwiftUI/AppKit app: what is rendered, focused, selected, enabled, reachable through menus/windows/dialogs, or experienced across a…

johnkozaris/jko-claude-plugins · 104 tokens

electron-playwright-validator

This skill should be used when a user asks to launch, inspect, automate, test, validate, or debug an Electron desktop UI through Playwright/CDP, including blank renderers, runtime import failures, accessibility snapshots, layout defects, click-through flows, or post-change checks. Not for native macOS or mobile apps…

johnkozaris/jko-claude-plugins · 90 tokens

set-lineup

This skill should be used when the user asks to "set my lineup", "start him for me", "swap him into my flex", "update my lineup on Yahoo", "fix my lineup before kickoff", "apply my lineup changes", or wants a lineup change actually applied on their fantasy platform. Drives the user's own logged-in browser session to…

derekrbreese/fantasy-football-skills · 165 tokens

propose-trade

This skill should be used when the user asks to "send the trade", "submit the trade offer", "propose the trade on Yahoo", "send him the offer", "make the trade official", "put the offer in", or wants an agreed trade actually transmitted on their fantasy platform. Drives the user's own logged-in browser session to…

derekrbreese/fantasy-football-skills · 137 tokens

submit-waiver-claim

This skill should be used when the user asks to "put in the claim", "submit my waiver claim", "claim him off waivers", "add him and drop X", "file the waiver for me", "place that bid on Yahoo", or wants a specific add/drop transaction executed on their fantasy platform. Drives the user's own logged-in browser session…

derekrbreese/fantasy-football-skills · 149 tokens

youtube-channel-business-email

YouTube channel business email and contact extractor: accepts a channel id (UCxxx), handle (@name), or URL; navigates the channel About view; extracts the business email from the description text plus full channel metadata (name, id, country, subscriber count, view count, video count, joined date, external links…

browser-act/skills · 324 tokens