Agent skill

Web Browse

by initializ in initializ/forge

Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch.

Apache-2.0Auto-check passedProductivity & Automation

Install Web Browse

skills CLI
$ npx skills add initializ/forge --skill web-browse -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install initializ/forge web-browse --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/initializ/forge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/forge-skills/local/embedded/web-browse .claude/skills/web-browse && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
web-browse
GitHub stars
223
Token cost
~1.1k tokens
SKILL.md length
442 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
Apache-2.0

At a glance

Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch.

  • Works in 4 steps: browser_navigate to the target URL. Read… → To act, pass that generation to… → If you act on a stale generation (the… → …
  • Tasks that involve Browser automation
  • SKILL.md covers Tools, Workflow and Notes
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Web Browse is an agent skill from initializ/forge. Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Browser automation and Forms and invoices. It works with JavaScript. The repository describes itself as: Forge is the open-source runtime for Anthropic's Agent Skills standard — built for the agent that runs next to a service, in your environment, on infrastructure you already… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Browser automation
  • Tasks that involve Forms and invoices

Example prompts

  • “/web-browse”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. browser_navigate to the target URL. Read the digest's [N] elements and
  2. To act, pass that generation to browser_click / browser_fill with the
  3. If you act on a stale generation (the page navigated or changed), the tool
  4. For long articles or tables, browser_extract with mode: text and

What it can do on your machine

Read from SKILL.md and the folder at commit 3c608d8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Web Browse loads about 1.1k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 442 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from initializ/forge at commit 3c608d8, republished under its Apache-2.0 licence (© initializ). 442 words, ~1,109 tokens.

Download SKILL.mdSave it as .claude/skills/web-browse/SKILL.md (or your agent's skills folder).
name
web-browse
description
Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch.
icon
🌐
category
web
tags
browser, web, scraping, automation, extraction

Web Browse

Drive a real headless browser (Chromium) to accomplish web tasks that a plain http_request cannot: pages that render content with JavaScript, multi-step flows, forms, and anything gated behind a click.

The browser is registered only because this skill declares requires.capabilities: [browser]. All navigation is forced through the agent's egress proxy, so it obeys the same allowlist, SSRF, and DNS-rebinding protections as every other web tool. Add the domains you need to egress_domains; a page that redirects off-allowlist is blocked.

Tools

You drive the browser through six tools. You never see raw HTML — every observation is a compact digest: the page title, URL, a numbered list of interactive elements ([3] input(email) "Work email"), and the start of the page text.

  • browser_navigate {url, wait_ms?} — load a page, get its digest.
  • browser_state {max_elements?, scroll_pages?, scroll_to_index?} — re-read the current page (after it changed on its own, to scroll, or to see more elements). Returns a fresh digest with new indices and generation.
  • browser_click {index, generation} — click the element at index from the latest digest. Returns the resulting page digest.
  • browser_fill {index, text, generation, submit?} — type into an input (or pick a select option by label). submit: true presses Enter. Password and payment fields are refused unless this skill opts in.
  • browser_extract {mode?, selector?, max_chars?, offset?} — pull page content: text (readable markdown, default), links, or html (scoped to a CSS selector). Long content is paginated — pass the offset from the previous call's header to continue.
  • browser_screenshot {full_page?, filename?} — capture a PNG for the user (attached to the reply; you will not see the image). Use only when the user wants a visual — read pages with digests and browser_extract.
Show full SKILL.md (167 more words)Show less

Workflow

  1. browser_navigate to the target URL. Read the digest's [N] elements and note the Generation number.
  2. To act, pass that generation to browser_click / browser_fill with the element's index. Every action returns a fresh digest — read it, don't assume the old indices still hold.
  3. If you act on a stale generation (the page navigated or changed), the tool returns an error with a fresh digest — retry using the new indices and generation.
  4. For long articles or tables, browser_extract with mode: text and paginate via offset. Use mode: links to enumerate links.

Notes

  • Indices reset whenever the page changes. Always drive from the most recent digest.
  • The browser keeps no cookies or profile between runs.
  • Before using this skill, add the hostnames this agent may reach to egress_domains in the frontmatter above (real domains, wildcards, or $VAR/${VAR} references expanded from the agent env). It ships empty, so every navigation is blocked until at least one host resolves; production builds also reject an open egress policy.

© initializ, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in forge-skills/local/embedded/web-browse of initializ/forge.

Open the folder on GitHubat commit 3c608d8

Compare with similar skills

Web Browse next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Web Browse compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Web Browse this skillinitializ/forge223—~1.1kAutomated safety check: PassApache-2.0
Ego Browserkwakseongjae/oh-my-design5311 repos~4.9kAutomated safety check: PassMIT
Browser Actitwanger/toBeBetterJavaer18k2 repos~932Automated safety check: PassNone
Agent Browseraiskillstore/marketplace4303 repos~2.4kAutomated safety check: PassNone
Browser Automationqualcomm/qai-appbuilder246—~1.6kAutomated safety check: PassCustom licence
C Browserdaxaur/openpaw173—~383Automated safety check: PassMIT

Similar skills

  • Ego Browser

    kwakseongjae/oh-my-design

    When you need a browser, read this Skill by default. An agent skill from kwakseongjae/oh-my-design.

    531 GitHub starsUsed in 1 repo~4.9k tokens
    Productivity & AutomationAuto-check passed
  • Browser Act

    itwanger/toBeBetterJavaer

    Browser automation CLI for AI agents. An agent skill from itwanger/toBeBetterJavaer.

    18k GitHub starsUsed in 2 repos~932 tokens
    Productivity & AutomationAuto-check passed
  • Agent Browser

    aiskillstore/marketplace

    Browser automation for AI agents via inference.sh. An agent skill from aiskillstore/marketplace.

    430 GitHub starsUsed in 3 repos~2.4k tokens
    Productivity & AutomationAuto-check passed
  • Browser Automation

    qualcomm/qai-appbuilder

    A skill your agent uses when working with the browser tool — navigating or inspecting a page, clicking through a flow, filling and submitting a form, acting inside a logged-in session, or…

    246 GitHub stars~1.6k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • C Browser

    daxaur/openpaw

    Headless browser automation — navigate pages, click elements, fill forms, take screenshots, scrape content using agent-browser or playwright-cli.

    173 GitHub stars~383 tokensUpdated 4 mo ago
    Productivity & AutomationAuto-check passed
  • Agent Browser

    quran/quran.com-frontend-next

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    1.9k GitHub starsUsed in 41 repos~3.3k tokens
    Productivity & AutomationAuto-check passed

More from initializ/forge

All 15 skills in this repo
  • Code Plan

    initializ/forge

    Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).

    223 GitHub stars~1.9k tokensUpdated 6 days ago
    Auto-check passed
  • Code Review

    initializ/forge

    AI-powered code review for diffs and individual files using LLM analysis

    223 GitHub stars~3k tokensUpdated 6 days ago
    Auto-check passed
  • Codegen HTML

    initializ/forge

    Scaffold and iterate on standalone Preact + HTM applications with zero build dependencies

    223 GitHub stars~1.5k tokensUpdated 6 days ago
    Auto-check passed
  • Code Agent

    initializ/forge

    General-purpose coding agent that reads, writes, and edits code, and searches codebases.

    223 GitHub stars~2.5k tokensUpdated 6 days ago
    Auto-check: warnings
  • Codegen React

    initializ/forge

    Scaffold and iterate on Vite + React applications. An agent skill from initializ/forge.

    223 GitHub stars~1.8k tokensUpdated 6 days ago
    Auto-check passed
  • K8s Cost Visibility

    initializ/forge

    Estimate Kubernetes infrastructure costs by querying cluster node, pod, PVC/PV, and LoadBalancer data, applying cloud pricing models, and producing cost attribution reports with storage and…

    223 GitHub stars~2.7k tokensUpdated 6 days ago
    Auto-check passed

Works with

Questions about Web Browse

What does Web Browse do?

Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch. Web Browse is an agent skill from initializ/forge. Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch.

When should I use Web Browse?

Web Browse fits situations like: tasks that involve Browser automation; tasks that involve Forms and invoices.

How do I install Web Browse in Claude Code?

Run `npx skills add initializ/forge --skill web-browse -a claude-code`. Or copy the skill folder (forge-skills/local/embedded/web-browse in initializ/forge) into .claude/skills/web-browse in your project. Claude Code loads it when a task matches its description.

How do I install Web Browse in Codex?

Run `npx skills add initializ/forge --skill web-browse -a codex`. Or copy the skill folder (forge-skills/local/embedded/web-browse in initializ/forge) into .agents/skills/web-browse in your project. Codex loads it when a task matches its description.

Can I use Web Browse in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add initializ/forge --skill web-browse -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/web-browse, .gemini/skills/web-browse, .github/skills/web-browse and .opencode/skills/web-browse in your project.

What does Web Browse need to run?

SKILL.md names no scripts, command-line tools or credentials: Web Browse is instructions for the agent only.

Does Web Browse access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Web Browse safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Web Browse use?

Web Browse is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Web Browse use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Web Browse?

Skills that share tags, products or a category with Web Browse: Ego Browser (kwakseongjae/oh-my-design, 531 stars), Browser Act (itwanger/toBeBetterJavaer, 18k stars), Agent Browser (aiskillstore/marketplace, 430 stars) and Browser Automation (qualcomm/qai-appbuilder, 246 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Web Browse?

initializ (a GitHub organization) maintains it in initializ/forge, which has 223 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 1, 2026.

Source: initializ/forge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.