browser

A skill that provides instructions for using the installed ChatGPT browser runtime for browser-based tasks. A browser runtime lets an agent navigate and inspect websites through the normal browser interface.

In plain words
What is it for?
Use it for tasks that require the ChatGPT browser, such as navigating pages, inspecting content, taking screenshots, or uploading files with user confirmation for irreversible actions.
Why use it?
It gives browser work a defined, supported process and keeps navigation, screenshots, and uploads within the browser’s safety controls.

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/stickerdaniel/browserjack/browser
Any agent
npx skills add stickerdaniel/browserjack --skill browser
Clone the repo
git clone --depth 1 https://github.com/stickerdaniel/browserjack

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 235 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 $0.00018 $0.00235
Opus 5 $0.00009 $0.00118
Sonnet 5 $0.00004 $0.00047
Haiku 4.5 $0.00002 $0.00023

Measured yesterday against content hash 22a44b68200e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

plugin/skills/browser/SKILL.md · 22 lines

What it actually says

Use the plugin-provided js MCP tool for browser tasks. The MCP initialization instructions contain the exact verified browser-client URL for the installed ChatGPT.app. Import that URL before using agent.browsers.

For the standard /Applications/ChatGPT.app installation:

var browserClient =
  await import("file:///Applications/ChatGPT.app/Contents/Resources/plugins/openai-bundled/plugins/chrome/scripts/browser-client.mjs");
await browserClient.setupBrowserRuntime({ globals: globalThis });
var availableBackends = await agent.browsers.list();

When the initialization instructions provide a different URL, use that exact URL instead.

Use OpenAI's browser abstractions rather than implementing CDP, navigation, screenshots, or file uploads yourself. Respect OpenAI's site and upload confirmations. Never bypass browser safety policy through raw CDP or alternative browser interfaces.

Do not print cookies, tokens, form values, private page content, or browser-profile data. Get explicit user approval immediately before an irreversible or externally visible action.

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. yesterday First seen · 22 lines · 18 tokens per session scan A 22a44b68200e

Subscribe to this mod's changes

browser is a skill published in the GitHub repository stickerdaniel/browserjack (2 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 235 once invoked, about $0.0001 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

macos-harness

Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…

browser-use/macos-harness · 71 tokens

host-computer-use

Beta desktop control through the connected A0 CLI host. Use for the user's host/local computer screenshots, screen inspection, menus, native app UI, OS-level clicking, scrolling, typing, or checking computeruseremote status. Use instead of linux-desktop for host/local machine control. Do not use for ordinary browser…

agent0ai/agent-zero · 78 tokens

video-gen

Video creation and local composition: join existing clips or render mixed image/video timelines with videocompose, generate one AI clip with videogenerate, or make a multi-shot AI film with videorender. Use when the deliverable is a video. Do NOT use for still images (use pi-image-gen directly).

TGYD-helige/pi · 64 tokens

install-shellby-mcp

Install and verify Shellby MCP on a Mac using terminal access only. Use when a user asks an agent to install, set up, configure, or finish a new Shellby MCP installation from this repository.

serbyte-development/shellby-mcp · 47 tokens

web-navigator

Web 浏览器自动化路由规则。通过 webnavigator 将 Web 场景路由到 Playwright MCP 或 mcp-chrome。.

Plocr/Reasonix-computer-use · 30 tokens

league-config

This skill should be used when the user asks to "set up my league", "configure my league", "add my league settings", "update my league config", "onboard my league", "change my scoring settings", or when any fantasy-football-skills skill finds no leagues.md file. Interviews the user once about scoring, roster slots…

derekrbreese/fantasy-football-skills · 99 tokens