browser

browser is a skill for Codex from arch3rPro/Ark-Space. It costs 47 tokens per session (811 once invoked), scanned A, original, MIT.

A browser-automation skill for using an interactive website through a bounded session. It can inspect the current page and act on controls such as links, forms, and other visible elements.

In plain words
What is it for?
Use it for interactive website tasks such as navigating pages, filling forms, clicking controls, and inspecting accessibility snapshots.
Why use it?
Some sites require clicks, scrolling, pagination, or changing page state that ordinary page retrieval cannot provide. It keeps those actions within a managed browser session.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it for interactive website tasks such as navigating pages, filling forms, clicking controls, and inspecting accessibility snapshots.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arch3rpro/ark-space/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 arch3rPro/Ark-Space --skill browser
Clone the repo
git clone --depth 1 https://github.com/arch3rPro/Ark-Space

Made for: 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 browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/arch3rpro/ark-space/browser/github.svg)](https://agentmods.dev/skills/arch3rpro/ark-space/browser)
Your own site
<a href="https://agentmods.dev/skills/arch3rpro/ark-space/browser"><img src="https://agentmods.dev/badge/skills/arch3rpro/ark-space/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 browser

Your own site · 80×15
<a href="https://agentmods.dev/skills/arch3rpro/ark-space/browser"><img src="https://agentmods.dev/badge/skills/arch3rpro/ark-space/browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 811 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.
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 $0.00047 $0.00811
Opus 5.5 $0.00019 $0.00324
Sonnet 5.5 $0.00009 $0.00162
Haiku 4.5 $0.00005 $0.00081

Measured 1mo ago against content hash fb0d52b3b20e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

skills/browser/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser

Use the installed arks CLI or ArkSpace MCP tools. Prefer the web Skill when Search or Fetch can produce the evidence without browser state.

Readiness

  1. Run arks --version. If unavailable, explain that ArkSpace CLI is required and ask before changing the user's environment.
  2. Run arks doctor --json when Firecrawl readiness is unknown. If credentials are missing, direct the human to run arks setup in a trusted local terminal. Never ask for an API key in conversation or place one in a command argument.
  3. Ask before changing configuration or the user's environment. Explain that an open Firecrawl browser session accrues credits until it is closed or expires.

Session lifecycle

Open only the exact initial HTTP(S) URL needed:

{
  "protocolVersion": 1,
  "capability": "browser.open",
  "input": {
    "url": "https://example.com",
    "ttlSeconds": 600,
    "activityTtlSeconds": 300,
    "timeoutMs": 30000
  }
}

Keep the returned data.sessionId. It is an opaque handle bound to the API key that created the session. Never substitute another account or Provider. ArkSpace intentionally does not return CDP or live-view authority URLs.

Use browser.snapshot before acting. Prefer interactiveOnly: true. The snapshot returns bounded @eN references for the current page state.

Actions and confirmation

browser.interact performs exactly one structured action:

  • navigate with an exact HTTP(S) URL;
  • click with a current @eN reference;
  • fill with a current @eN reference and text;
  • press with an allowed key;
  • scroll with direction and bounded pixels;
  • scrape to read current page content.

Before each action, state the target and intended effect. Obtain explicit user approval before setting "confirmed": true. A click or key press can submit a form, purchase an item, publish content, change account state, or trigger another irreversible effect. Do not infer approval from an earlier request when the concrete target or effect has changed.

Read the full file on GitHub · 70 lines

Files

What ships with it

3 files 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. 1mo ago Changed · +3 lines fb0d52b3b20e
  2. 1mo ago First seen · 67 lines · 47 tokens per session scan A 20a06d72d62c

Subscribe to this mod's changes

browser is a skill published in the GitHub repository arch3rPro/Ark-Space (1 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 811 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-10.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

interactive-login

Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

open-design-browser

Inspect and exercise local HTML design artifacts with the existing agent-browser CLI, including screenshots and keyboard or interaction checks. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser automation.

compozy/compozy · 49 tokens