web-browse

A browser-control skill for navigating websites that need JavaScript, clicks, form entry, or multiple steps before their content appears.

In plain words
What is it for?
Opening dynamic pages, reading rendered content, clicking controls, filling forms, and completing browser-based tasks.
Why use it?
It handles pages that a basic web request cannot fully load or interact with.

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/initializ/forge/web-browse
Any agent
npx skills add initializ/forge --skill web-browse
Clone the repo
git clone --depth 1 https://github.com/initializ/forge

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,099 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 $0.01099
Opus 5 $0.00018 $0.00549
Sonnet 5 $0.00007 $0.00220
Haiku 4.5 $0.00004 $0.00110

Measured 2d ago against content hash 53107c345db6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-browse 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.

forge-skills/local/embedded/web-browse/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

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.

Read the full file on GitHub · 101 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. 2d ago First seen · 101 lines · 37 tokens per session scan A 53107c345db6

Subscribe to this mod's changes

web-browse is a skill published in the GitHub repository initializ/forge (156 stars, last pushed 5d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,099 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 2026-08-30.